diff --git a/.ipynb_checkpoints/BE2_GAN_and_cGAN-checkpoint.ipynb b/.ipynb_checkpoints/BE2_GAN_and_cGAN-checkpoint.ipynb
new file mode 100644
index 0000000000000000000000000000000000000000..ca9b4968a62683db1e3bf0f0f18749960ef8ddcc
--- /dev/null
+++ b/.ipynb_checkpoints/BE2_GAN_and_cGAN-checkpoint.ipynb
@@ -0,0 +1,1232 @@
+{
+ "cells": [
+  {
+   "cell_type": "markdown",
+   "metadata": {
+    "colab_type": "text",
+    "id": "UGwKsKS4GMTN"
+   },
+   "source": [
+    "<h1 ><big><center>MSO 3.4 - Deep Structured Learning</center></big></h1>\n",
+    "\n",
+    "<h2><big><center> BE 2 - GANs and cGAN </center></big></h2>\n",
+    "\n",
+    "<h5><big><center>Adapted from <i>Projet d'Option</i> of : Mhamed Jabri, Martin Chauvin, Ahmed Sahraoui, Zakariae Moustaïne and Taoufik Bouchikhi\n",
+    "\n",
+    "\n",
+    "<p align=\"center\">\n",
+    "<img height=300px src=\"https://cdn-images-1.medium.com/max/1080/0*tJRy5Chmk4XymxwN.png\"/></p>\n",
+    "<p align=\"center\"></p>"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {
+    "colab_type": "text",
+    "id": "16aVF81lJuiP"
+   },
+   "source": [
+    "The aim of this assignment is to discover GANs, understand how they are implemented and then explore one specific architecture of GANs that allows us to perform image to image translation (which corresponds to the picture that you can see above this text ! )\n",
+    "\n",
+    "Before starting the exploration of the world of GANs, here's  what students should do and send back for this assignement : \n",
+    "* In the \"tutorial\" parts of this assignement that focus on explaining new concepts, you'll find <font color='red'>**questions**</font>  that aim to test your understanding of those concepts. \n",
+    "* In some of the code cells, you'll have to complete the code and you'll find a \"TO DO\" explaining what you should implement."
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {
+    "colab_type": "text",
+    "id": "M-WNKvhOP1ED"
+   },
+   "source": [
+    "# Part1: DC-GAN"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {
+    "colab_type": "text",
+    "id": "y_r8nMTGQI9a"
+   },
+   "source": [
+    "In this part, we aim to learn and understand the basic concepts of **Generative Adversarial Networks** through a DCGAN and generate new celebrities from the learned network after showing it real celebrities. For this purpose, please study the tutorial here: https://pytorch.org/tutorials/beginner/dcgan_faces_tutorial.html\n"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {
+    "colab_type": "text",
+    "id": "jiHCy4_UUBFb"
+   },
+   "source": [
+    "##Work to do\n",
+    "Now we want to generate handwritten digits using the MNIST dataset. It is available within torvision package (https://pytorch.org/vision/stable/generated/torchvision.datasets.MNIST.html#torchvision.datasets.MNIST)\n",
+    "\n",
+    "Please re-train the DCGAN and display some automatically generated handwritten digits.\n",
+    "\n"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {
+    "colab": {},
+    "colab_type": "code",
+    "id": "sIL7UvYAZx6L"
+   },
+   "outputs": [],
+   "source": [
+    "#TO DO: your code here to adapt the code from the tutorial to experiment on MNIST dataset"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {
+    "colab_type": "text",
+    "id": "5fbSgsrE1GqC"
+   },
+   "source": [
+    "# Part2: Conditional GAN (cGAN)"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {
+    "colab_type": "text",
+    "id": "7SjXNoT7BUey"
+   },
+   "source": [
+    "Let's take the example of the set described in the next picture.\n",
+    "![Map to satellite picture](https://raw.githubusercontent.com/Neyri/Projet-cGAN/master/BE/img/map_streetview.png)\n",
+    "\n",
+    "We have a picture of a map (from Google Maps) and we want to create an image of what the satellite view may look like.\n",
+    "\n",
+    "As we are not only trying to generate a random picture but a mapping between a picture to another one, we can't use the standard GAN architecture. We will then use a cGAN.\n",
+    "\n",
+    "A cGAN is a supervised GAN aiming at mapping a label picture to a real one or a real picture to a label one. As you can see in the diagram below, the discriminator will take as input a pair of images and try to predict if the pair was generated or not. The generator will not only generate an image from noise but will also use an image (label or real) to generate another one (real or label).\n",
+    "![Diagram of how a cGan works](https://raw.githubusercontent.com/Neyri/Projet-cGAN/master/BE/img/cgan_map.png)\n"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {
+    "colab_type": "text",
+    "id": "0JRaeHfzl6cO"
+   },
+   "source": [
+    "### Generator\n",
+    "\n",
+    "In the cGAN architecture, the generator chosen is a U-Net.\n",
+    "![U-Net](https://raw.githubusercontent.com/Neyri/Projet-cGAN/master/BE/img/unet.png)\n",
+    "\n",
+    "A U-Net takes as input an image, and outputs another image. \n",
+    "\n",
+    "It can be divided into 2 subparts : an encoder and a decoder. \n",
+    "* The encoder takes the input image and reduces its dimension to encode the main features into a vector. \n",
+    "* The decoder takes this vector and map the features stored into an image.\n",
+    "\n",
+    "A U-Net architecture is different from a classic encoder-decoder in that every layer of the decoder takes as input the previous decoded output as well as the output vector from the encoder layers of the same level. It allows the decoder to map low frequencies information encoded during the descent as well as high frequencies from the original picture. \n",
+    "\n",
+    "![U-Net](https://www.researchgate.net/profile/Baris_Turkbey/publication/315514772/figure/fig2/AS:485824962797569@1492841105670/U-net-architecture-Each-box-corresponds-to-a-multi-channel-features-maps-The-number-of.png)"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {
+    "colab_type": "text",
+    "id": "xFqMOsoYwzFe"
+   },
+   "source": [
+    "The architecture we will implement is the following (the number in the square is the number of filters used).\n",
+    "![UNet Architecture](https://raw.githubusercontent.com/Neyri/Projet-cGAN/master/BE/img/unet_architecture.png)\n",
+    "\n",
+    "The encoder will take as input a colored picture (3 channels: RGB), it will pass through a series of convolution layers to encode the features of the picture. It will then be decoded by the decoder using transposed convolutional layers. These layers will take as input the previous decoded vector AND the encoded features of the same level. "
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {
+    "colab_type": "text",
+    "id": "yzy7y4hmbbX3"
+   },
+   "source": [
+    "Now, let's create or cGAN to generate facades from a template image. For this purpose, we will use the \"Facade\" dataset available at http://cmp.felk.cvut.cz/~tylecr1/facade/.\n"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {
+    "colab_type": "text",
+    "id": "Q_jf9H_NDESm"
+   },
+   "source": [
+    "Let's first create a few classes describing the layers we will use in the U-Net."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {
+    "colab": {},
+    "colab_type": "code",
+    "id": "uOKvYDyu0w8N"
+   },
+   "outputs": [],
+   "source": [
+    "# Importing all the libraries needed\n",
+    "import matplotlib.pyplot as plt\n",
+    "import imageio\n",
+    "import glob\n",
+    "import random\n",
+    "import os\n",
+    "import numpy as np\n",
+    "import math\n",
+    "import itertools\n",
+    "import time\n",
+    "import datetime\n",
+    "import cv2\n",
+    "from pathlib import Path\n",
+    "from PIL import Image\n",
+    "\n",
+    "from torch.utils.data import Dataset, DataLoader\n",
+    "import torchvision.transforms as transforms\n",
+    "from torchvision.utils import save_image, make_grid\n",
+    "from torchvision import datasets\n",
+    "from torch.autograd import Variable\n",
+    "\n",
+    "import torch.nn as nn\n",
+    "import torch.nn.functional as F\n",
+    "import torch"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {
+    "colab": {},
+    "colab_type": "code",
+    "id": "Zk5a6B5hILN2"
+   },
+   "outputs": [],
+   "source": [
+    "# code adapted from https://github.com/milesial/Pytorch-UNet/blob/master/unet/unet_parts.py\n",
+    "\n",
+    "# Input layer\n",
+    "class inconv(nn.Module):\n",
+    "    def __init__(self, in_ch, out_ch):\n",
+    "        super(inconv, self).__init__()\n",
+    "        self.conv = nn.Sequential(\n",
+    "            nn.Conv2d(in_ch, out_ch, kernel_size=4, padding=1, stride=2),\n",
+    "            nn.LeakyReLU(negative_slope=0.2, inplace=True)\n",
+    "        )\n",
+    "\n",
+    "    def forward(self, x):\n",
+    "        x = self.conv(x)\n",
+    "        return x\n",
+    "\n",
+    "# Encoder layer\n",
+    "class down(nn.Module):\n",
+    "    def __init__(self, in_ch, out_ch):\n",
+    "        super(down, self).__init__()\n",
+    "        self.conv = nn.Sequential(\n",
+    "            nn.Conv2d(in_ch, out_ch, kernel_size=4, padding=1, stride=2),\n",
+    "            nn.BatchNorm2d(out_ch),\n",
+    "            nn.LeakyReLU(negative_slope=0.2, inplace=True)\n",
+    "        )\n",
+    "\n",
+    "    def forward(self, x):\n",
+    "        x = self.conv(x)\n",
+    "        return x\n",
+    "\n",
+    "# Decoder layer\n",
+    "class up(nn.Module):\n",
+    "    def __init__(self, in_ch, out_ch, dropout=False):\n",
+    "        super(up, self).__init__()\n",
+    "        if dropout :\n",
+    "            self.conv = nn.Sequential(\n",
+    "                nn.ConvTranspose2d(in_ch, out_ch, kernel_size=4, padding=1, stride=2),\n",
+    "                nn.BatchNorm2d(out_ch),\n",
+    "                nn.Dropout(0.5, inplace=True),\n",
+    "                nn.ReLU(inplace=True)\n",
+    "            )\n",
+    "        else:\n",
+    "            self.conv = nn.Sequential(\n",
+    "                nn.ConvTranspose2d(in_ch, out_ch, kernel_size=4, padding=1, stride=2),\n",
+    "                nn.BatchNorm2d(out_ch),\n",
+    "                nn.ReLU(inplace=True)\n",
+    "            )\n",
+    "\n",
+    "    def forward(self, x1, x2):\n",
+    "        x1 = self.conv(x1)\n",
+    "        x = torch.cat([x1, x2], dim=1)\n",
+    "        return x\n",
+    "\n",
+    "# Output layer\n",
+    "class outconv(nn.Module):\n",
+    "    def __init__(self, in_ch, out_ch):\n",
+    "        super(outconv, self).__init__()\n",
+    "        self.conv = nn.Sequential(\n",
+    "              nn.ConvTranspose2d(in_ch, out_ch, kernel_size=4, padding=1, stride=2),\n",
+    "              nn.Tanh()\n",
+    "        )\n",
+    "\n",
+    "    def forward(self, x):\n",
+    "        x = self.conv(x)\n",
+    "        return x"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {
+    "colab_type": "text",
+    "id": "1rZ5Qz1mBUe8"
+   },
+   "source": [
+    "Now let's create the U-Net using the helper classes defined previously."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {
+    "colab": {},
+    "colab_type": "code",
+    "id": "4Tbp_535EVPW"
+   },
+   "outputs": [],
+   "source": [
+    " class U_Net(nn.Module):\n",
+    "    ''' \n",
+    "    Ck denotes a Convolution-BatchNorm-ReLU layer with k filters.\n",
+    "    CDk denotes a Convolution-BatchNorm-Dropout-ReLU layer with a dropout rate of 50%\n",
+    "    Encoder:\n",
+    "      C64   - C128   - C256   - C512  - C512  - C512 - C512 - C512\n",
+    "    Decoder:\n",
+    "      CD512 - CD1024 - CD1024 - C1024 - C1024 - C512 - C256 - C128\n",
+    "    '''\n",
+    "    def __init__(self, n_channels, n_classes):\n",
+    "        super(U_Net, self).__init__()\n",
+    "        # Encoder\n",
+    "        self.inc = inconv(n_channels, 64) # 64 filters\n",
+    "        # TO DO :\n",
+    "        # Create the 7 encoder layers called \"down1\" to \"down7\" following this sequence\n",
+    "        # C64   - C128   - C256   - C512  - C512  - C512 - C512 - C512\n",
+    "        # The first one has already been implemented\n",
+    "        \n",
+    "        \n",
+    "        # Decoder\n",
+    "        # TO DO :\n",
+    "        # Create the 7 decoder layers called up1 to up7 following this sequence :\n",
+    "        # CD512 - CD1024 - CD1024 - C1024 - C1024 - C512 - C256 - C128\n",
+    "        # The last layer has already been defined\n",
+    "        \n",
+    "        \n",
+    "        self.outc = outconv(128, n_classes) # 128 filters\n",
+    "\n",
+    "    def forward(self, x):\n",
+    "        x1 = self.inc(x)\n",
+    "        x2 = self.down1(x1)\n",
+    "        x3 = self.down2(x2)\n",
+    "        x4 = self.down3(x3)\n",
+    "        x5 = self.down4(x4)\n",
+    "        x6 = self.down5(x5)\n",
+    "        x7 = self.down6(x6)\n",
+    "        x8 = self.down7(x7)\n",
+    "        # At this stage x8 is our encoded vector, we will now decode it\n",
+    "        x = self.up7(x8, x7)\n",
+    "        x = self.up6(x, x6)\n",
+    "        x = self.up5(x, x5)\n",
+    "        x = self.up4(x, x4)\n",
+    "        x = self.up3(x, x3)\n",
+    "        x = self.up2(x, x2)\n",
+    "        x = self.up1(x, x1)\n",
+    "        x = self.outc(x)\n",
+    "        return x"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {
+    "colab": {},
+    "colab_type": "code",
+    "id": "1hmcejTWJSYY"
+   },
+   "outputs": [],
+   "source": [
+    "# We take images that have 3 channels (RGB) as input and output an image that also have 3 channels (RGB)\n",
+    "generator=U_Net(3,3)\n",
+    "# Check that the architecture is as expected\n",
+    "generator"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {
+    "colab_type": "text",
+    "id": "xIXFtHzcBUfO"
+   },
+   "source": [
+    "You should now have a working U-Net."
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {
+    "colab_type": "text",
+    "id": "RqD1katYBUfP"
+   },
+   "source": [
+    "<font color='red'>**Question 1**</font>                                                                  \n",
+    "Knowing the input and output images will be 256x256, what will be the dimension of the encoded vector x8  ?\n",
+    "\n",
+    "<font color='red'>**Question 2**</font>                                                                  \n",
+    "As you can see, U-net has an encoder-decoder architecture with skip connections. Explain why it works better than a traditional encoder-decoder."
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {
+    "colab_type": "text",
+    "id": "cchTp3thBUfR"
+   },
+   "source": [
+    "### Discriminator\n",
+    "\n",
+    "In the cGAN architecture, the chosen discriminator is a Patch GAN. It is a convolutional discriminator which enables to produce a map of the input pictures where each pixel represents a patch of size NxN of the input.\n",
+    "\n",
+    "![patch GAN](https://raw.githubusercontent.com/Neyri/Projet-cGAN/master/BE/img/patchGAN.png)\n",
+    "\n",
+    "The size N is given by the depth of the net. According to this table :\n",
+    "\n",
+    "| Number of layers | N |\n",
+    "| ---- | ---- |\n",
+    "| 1 | 16 |\n",
+    "| 2 | 34 |\n",
+    "| 3 | 70 |\n",
+    "| 4 | 142 |\n",
+    "| 5 | 286 |\n",
+    "| 6 | 574 |\n",
+    "\n",
+    "The number of layers actually means the number of layers with `kernel=(4,4)`, `padding=(1,1)` and `stride=(2,2)`. These layers are followed by 2 layers with `kernel=(4,4)`, `padding=(1,1)` and `stride=(1,1)`.\n",
+    "In our case we are going to create a 70x70 PatchGAN."
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {
+    "colab_type": "text",
+    "id": "ge6I7M0aBUfT"
+   },
+   "source": [
+    "Let's first create a few helping classes."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {
+    "colab": {},
+    "colab_type": "code",
+    "id": "RYqomFO8BUfV"
+   },
+   "outputs": [],
+   "source": [
+    "class conv_block(nn.Module):\n",
+    "    def __init__(self, in_ch, out_ch, use_batchnorm=True, stride=2):\n",
+    "        super(conv_block, self).__init__()\n",
+    "        if use_batchnorm:\n",
+    "            self.conv = nn.Sequential(\n",
+    "                nn.Conv2d(in_ch, out_ch, kernel_size=4, padding=1, stride=stride),\n",
+    "                nn.BatchNorm2d(out_ch),\n",
+    "                nn.LeakyReLU(negative_slope=0.2, inplace=True)\n",
+    "            )\n",
+    "        else:\n",
+    "            self.conv = nn.Sequential(\n",
+    "                nn.Conv2d(in_ch, out_ch, kernel_size=4, padding=1, stride=stride),\n",
+    "                nn.LeakyReLU(negative_slope=0.2, inplace=True)\n",
+    "            )\n",
+    "\n",
+    "    def forward(self, x):\n",
+    "        x = self.conv(x)\n",
+    "        return x\n",
+    "    \n",
+    "\n",
+    "class out_block(nn.Module):\n",
+    "    def __init__(self, in_ch, out_ch):\n",
+    "        super(out_block, self).__init__()\n",
+    "        self.conv = nn.Sequential(\n",
+    "            nn.Conv2d(in_ch, 1, kernel_size=4, padding=1, stride=1),\n",
+    "            nn.Sigmoid()\n",
+    "        )\n",
+    "\n",
+    "    def forward(self, x):\n",
+    "        x = self.conv(x)\n",
+    "        return x"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {
+    "colab_type": "text",
+    "id": "5m4Dnup4BUfc"
+   },
+   "source": [
+    "Now let's create the Patch GAN discriminator.\n",
+    "As we want a 70x70 Patch GAN, the architecture will be as follows :\n",
+    "```\n",
+    "1. C64  - K4, P1, S2\n",
+    "2. C128 - K4, P1, S2\n",
+    "3. C256 - K4, P1, S2\n",
+    "4. C512 - K4, P1, S1\n",
+    "5. C1   - K4, P1, S1 (output)\n",
+    "```\n",
+    "Where Ck denotes a convolution block with k filters, Kk a kernel of size k, Pk is the padding size and Sk the stride applied.\n",
+    "*Note :* For the first layer, we do not use batchnorm."
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {
+    "colab_type": "text",
+    "id": "AH6u5a-PBUfg"
+   },
+   "source": [
+    "<font color='red'>**Question 3**</font>                                                                  \n",
+    "Knowing the input and output images will be 256x256, what will be the dimension of the encoded vector x8  ?Knowing input images will be 256x256 with 3 channels each, how many parameters are there to learn ?"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {
+    "colab": {},
+    "colab_type": "code",
+    "id": "g_9LxNhGBUfi"
+   },
+   "outputs": [],
+   "source": [
+    "class PatchGAN(nn.Module):\n",
+    "    def __init__(self, n_channels, n_classes):\n",
+    "        super(PatchGAN, self).__init__()\n",
+    "        # TODO :\n",
+    "        # create the 4 first layers named conv1 to conv4\n",
+    "        self.conv1 =\n",
+    "        self.conv2 =\n",
+    "        self.conv3 =\n",
+    "        self.conv4 =\n",
+    "        # output layer\n",
+    "        self.out = out_block(512, n_classes)\n",
+    "        \n",
+    "    def forward(self, x1, x2):\n",
+    "        x = torch.cat([x2, x1], dim=1)\n",
+    "        x = self.conv1(x)\n",
+    "        x = self.conv2(x)\n",
+    "        x = self.conv3(x)\n",
+    "        x = self.conv4(x)\n",
+    "        x = self.out(x)\n",
+    "        return x"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {
+    "colab": {},
+    "colab_type": "code",
+    "id": "W_sevZRnBUfn"
+   },
+   "outputs": [],
+   "source": [
+    "# We have 6 input channels as we concatenate 2 images (with 3 channels each)\n",
+    "discriminator = PatchGAN(6,1)\n",
+    "discriminator"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {
+    "colab_type": "text",
+    "id": "v_QubOycBUfv"
+   },
+   "source": [
+    "You should now have a working discriminator."
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {
+    "colab_type": "text",
+    "id": "DiI2CByRBUfz"
+   },
+   "source": [
+    "### Loss functions\n",
+    "\n",
+    "As we have seen in the choice of the various architectures for this GAN, the issue is to map both low and high frequencies.\n",
+    "To tackle this problem, this GAN rely on the architecture to map the high frequencies (U-Net + PatchGAN) and the loss function to learn low frequencies features. The global loss function will indeed be made of 2 parts :\n",
+    "* the first part to map hight frequencies, will try to optimize the mean squared error of the GAN.\n",
+    "* the second part to map low frequencies, will minimize the $\\mathcal{L}_1$ norm of the generated picture.\n",
+    "\n",
+    "So the loss can be defined as $$ G^* = arg\\ \\underset{G}{min}\\ \\underset{D}{max}\\ \\mathcal{L}_{cGAN}(G,D) + \\lambda \\mathcal{L}_1(G)$$"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {
+    "colab": {},
+    "colab_type": "code",
+    "id": "k4G_xewPBUf4"
+   },
+   "outputs": [],
+   "source": [
+    "# Loss functions\n",
+    "criterion_GAN = torch.nn.MSELoss()\n",
+    "criterion_pixelwise = torch.nn.L1Loss()\n",
+    "\n",
+    "# Loss weight of L1 pixel-wise loss between translated image and real image\n",
+    "lambda_pixel = 100"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {
+    "colab_type": "text",
+    "id": "c12q2NwkBUf7"
+   },
+   "source": [
+    "### Training and evaluating models "
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {
+    "colab": {},
+    "colab_type": "code",
+    "id": "vGKjO0UMBUf9"
+   },
+   "outputs": [],
+   "source": [
+    "# parameters\n",
+    "epoch = 0 #  epoch to start training from\n",
+    "n_epoch = 200  #  number of epochs of training\n",
+    "batch_size =10  #  size of the batches\n",
+    "lr = 0.0002 #  adam: learning rate\n",
+    "b1 =0.5  #  adam: decay of first order momentum of gradient\n",
+    "b2 = 0.999  # adam: decay of first order momentum of gradient\n",
+    "decay_epoch = 100  # epoch from which to start lr decay\n",
+    "img_height = 256  # size of image height\n",
+    "img_width = 256  # size of image width\n",
+    "channels = 3  # number of image channels\n",
+    "sample_interval = 500 # interval between sampling of images from generators\n",
+    "checkpoint_interval = -1 # interval between model checkpoints\n",
+    "cuda = True if torch.cuda.is_available() else False # do you have cuda ?"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {
+    "colab_type": "text",
+    "id": "PhPkU7BDYooV"
+   },
+   "source": [
+    "Download the dataset. \n"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {
+    "colab": {},
+    "colab_type": "code",
+    "id": "8wyPjAxPYsNF"
+   },
+   "outputs": [],
+   "source": [
+    "import urllib.request\n",
+    "from tqdm import tqdm\n",
+    "import os\n",
+    "import zipfile\n",
+    "\n",
+    "def download_hook(t):\n",
+    "    \"\"\"Wraps tqdm instance.\n",
+    "    Don't forget to close() or __exit__()\n",
+    "    the tqdm instance once you're done with it (easiest using `with` syntax).\n",
+    "    Example\n",
+    "    -------\n",
+    "    >>> with tqdm(...) as t:\n",
+    "    ...     reporthook = my_hook(t)\n",
+    "    ...     urllib.request.urlretrieve(..., reporthook=reporthook)\n",
+    "    \"\"\"\n",
+    "    last_b = [0]\n",
+    "\n",
+    "    def update_to(b=1, bsize=1, tsize=None):\n",
+    "        \"\"\"\n",
+    "        b  : int, optional\n",
+    "            Number of blocks transferred so far [default: 1].\n",
+    "        bsize  : int, optional\n",
+    "            Size of each block (in tqdm units) [default: 1].\n",
+    "        tsize  : int, optional\n",
+    "            Total size (in tqdm units). If [default: None] remains unchanged.\n",
+    "        \"\"\"\n",
+    "        if tsize is not None:\n",
+    "            t.total = tsize\n",
+    "        t.update((b - last_b[0]) * bsize)\n",
+    "        last_b[0] = b\n",
+    "\n",
+    "    return update_to\n",
+    "\n",
+    "def download(url, save_dir):\n",
+    "    filename = url.split('/')[-1]\n",
+    "    with tqdm(unit = 'B', unit_scale = True, unit_divisor = 1024, miniters = 1, desc = filename) as t:\n",
+    "        urllib.request.urlretrieve(url, filename = os.path.join(save_dir, filename), reporthook = download_hook(t), data = None)\n",
+    "\n",
+    "if __name__ == '__main__':\n",
+    "    # Download ground truth\n",
+    "    if not os.path.exists(\"CMP_facade_DB_base.zip\"):\n",
+    "        download(\"http://cmp.felk.cvut.cz/~tylecr1/facade/CMP_facade_DB_base.zip\", \"./\")\n",
+    "    # Extract in the correct folder\n",
+    "    with zipfile.ZipFile(\"CMP_facade_DB_base.zip\", 'r') as zip_ref:\n",
+    "        zip_ref.extractall(\"./facades\")\n",
+    "        os.rename(\"./facades/base\", \"./facades/train\")\n",
+    "\n",
+    "    # Download ground truth\n",
+    "    if not os.path.exists(\"CMP_facade_DB_extended.zip\"):\n",
+    "        download(\"http://cmp.felk.cvut.cz/~tylecr1/facade/CMP_facade_DB_extended.zip\", \"./\")\n",
+    "    # Extract in the correct folder\n",
+    "    with zipfile.ZipFile(\"CMP_facade_DB_extended.zip\", 'r') as zip_ref:\n",
+    "        zip_ref.extractall(\"./facades\")\n",
+    "        os.rename(\"./facades/extended\", \"./facades/val\")\n"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {
+    "colab_type": "text",
+    "id": "6DHT9c0_BUgA"
+   },
+   "source": [
+    "Configure the dataloader"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {
+    "colab": {},
+    "colab_type": "code",
+    "id": "rxi_QIpgBUgB"
+   },
+   "outputs": [],
+   "source": [
+    "class ImageDataset(Dataset):\n",
+    "    def __init__(self, root, transforms_=None, mode='train'):\n",
+    "        self.transform = transforms.Compose(transforms_)\n",
+    "\n",
+    "        self.files_img = sorted(glob.glob(os.path.join(root, mode) + '/*.jpg'))\n",
+    "        if mode == 'val':\n",
+    "            self.files_img.extend(\n",
+    "                sorted(glob.glob(os.path.join(root, 'val') + '/*.jpg')))\n",
+    "\n",
+    "        self.files_mask = sorted(glob.glob(os.path.join(root, mode) + '/*.png'))\n",
+    "        if mode == 'val':\n",
+    "            self.files_mask.extend(\n",
+    "                sorted(glob.glob(os.path.join(root, 'val') + '/*.png')))\n",
+    "            \n",
+    "        assert len(self.files_img) == len(self.files_mask)\n",
+    "\n",
+    "    def __getitem__(self, index):\n",
+    "\n",
+    "        img = Image.open(self.files_img[index % len(self.files_img)])\n",
+    "        mask = Image.open(self.files_mask[index % len(self.files_img)])\n",
+    "        mask = mask.convert('RGB')\n",
+    "\n",
+    "        img = self.transform(img)\n",
+    "        mask = self.transform(mask)\n",
+    "\n",
+    "        return img, mask\n",
+    "\n",
+    "    def __len__(self):\n",
+    "        return len(self.files_img)\n",
+    "    \n",
+    "# Configure dataloaders\n",
+    "transforms_ = [transforms.Resize((img_height, img_width), Image.BICUBIC),\n",
+    "               transforms.ToTensor()]  # transforms.Normalize((0.5,0.5,0.5), (0.5,0.5,0.5))\n",
+    "\n",
+    "dataloader = DataLoader(ImageDataset(\"facades\", transforms_=transforms_),\n",
+    "                        batch_size=16, shuffle=True)\n",
+    "\n",
+    "val_dataloader = DataLoader(ImageDataset(\"facades\", transforms_=transforms_, mode='val'),\n",
+    "                            batch_size=8, shuffle=False)\n",
+    "\n",
+    "# Tensor type\n",
+    "Tensor = torch.cuda.FloatTensor if cuda else torch.FloatTensor"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {
+    "colab_type": "text",
+    "id": "Okb3LU76BUgG"
+   },
+   "source": [
+    "Check the loading works and a few helper functions"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {
+    "colab": {},
+    "colab_type": "code",
+    "id": "xuxq4TZRBUgJ"
+   },
+   "outputs": [],
+   "source": [
+    "def plot2x2Array(image, mask):\n",
+    "    f, axarr = plt.subplots(1, 2)\n",
+    "    axarr[0].imshow(image)\n",
+    "    axarr[1].imshow(mask)\n",
+    "\n",
+    "    axarr[0].set_title('Image')\n",
+    "    axarr[1].set_title('Mask')\n",
+    "\n",
+    "\n",
+    "def reverse_transform(image):\n",
+    "    image = image.numpy().transpose((1, 2, 0))\n",
+    "    image = np.clip(image, 0, 1)\n",
+    "    image = (image * 255).astype(np.uint8)\n",
+    "\n",
+    "    return image\n",
+    "\n",
+    "def plot2x3Array(image, mask,predict):\n",
+    "    f, axarr = plt.subplots(1,3,figsize=(15,15))\n",
+    "    axarr[0].imshow(image)\n",
+    "    axarr[1].imshow(mask)\n",
+    "    axarr[2].imshow(predict)\n",
+    "    axarr[0].set_title('input')\n",
+    "    axarr[1].set_title('real')\n",
+    "    axarr[2].set_title('fake')"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {
+    "colab": {},
+    "colab_type": "code",
+    "id": "m2NxLrQEBUgM"
+   },
+   "outputs": [],
+   "source": [
+    "image, mask = next(iter(dataloader))\n",
+    "image = reverse_transform(image[0])\n",
+    "mask = reverse_transform(mask[0])\n",
+    "plot2x2Array(image, mask)"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {
+    "colab_type": "text",
+    "id": "zAvaxAbxBUgQ"
+   },
+   "source": [
+    "Initialize our GAN"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {
+    "colab": {},
+    "colab_type": "code",
+    "id": "dVgF3qfDBUgR"
+   },
+   "outputs": [],
+   "source": [
+    "# Calculate output of image discriminator (PatchGAN)\n",
+    "patch = (1, img_height//2**3-2, img_width//2**3-2)\n",
+    "\n",
+    "if cuda:\n",
+    "    generator = generator.cuda()\n",
+    "    discriminator = discriminator.cuda()\n",
+    "    criterion_GAN.cuda()\n",
+    "    criterion_pixelwise.cuda()\n",
+    "    \n",
+    "# Optimizers\n",
+    "optimizer_G = torch.optim.Adam(generator.parameters(), lr=lr, betas=(b1, b2))\n",
+    "optimizer_D = torch.optim.Adam(discriminator.parameters(), lr=lr, betas=(b1, b2))"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {
+    "colab_type": "text",
+    "id": "rN3cbiWaBUgf"
+   },
+   "source": [
+    "Start training"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {
+    "colab": {},
+    "colab_type": "code",
+    "id": "msmQQUX-BUgh"
+   },
+   "outputs": [],
+   "source": [
+    "def save_model(epoch):\n",
+    "    # save your work\n",
+    "    torch.save({\n",
+    "                'epoch': epoch,\n",
+    "                'model_state_dict': generator.state_dict(),\n",
+    "                'optimizer_state_dict': optimizer_G.state_dict(),\n",
+    "                'loss': loss_G,\n",
+    "                }, 'generator_'+str(epoch)+'.pth')\n",
+    "    torch.save({\n",
+    "                'epoch': epoch,\n",
+    "                'model_state_dict': discriminator.state_dict(),\n",
+    "                'optimizer_state_dict': optimizer_D.state_dict(),\n",
+    "                'loss': loss_D,\n",
+    "                }, 'discriminator_'+str(epoch)+'.pth')\n",
+    "    \n",
+    "def weights_init_normal(m):\n",
+    "  classname = m.__class__.__name__\n",
+    "  if classname.find('Conv') != -1:\n",
+    "      torch.nn.init.normal_(m.weight.data, 0.0, 0.02)\n",
+    "  elif classname.find('BatchNorm2d') != -1:\n",
+    "      torch.nn.init.normal_(m.weight.data, 1.0, 0.02)\n",
+    "      torch.nn.init.constant_(m.bias.data, 0.0)"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {
+    "colab_type": "text",
+    "id": "6UXrZLLNBUgq"
+   },
+   "source": [
+    "<font color='red'>Complete the loss function </font>  in the following training code and train your network:  "
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {
+    "colab": {},
+    "colab_type": "code",
+    "id": "7NUuGcQ0SiJw"
+   },
+   "outputs": [],
+   "source": [
+    "# ----------\n",
+    "#  Training\n",
+    "# ----------\n",
+    "\n",
+    "losses = []\n",
+    "num_epochs = 200\n",
+    "\n",
+    "# Initialize weights\n",
+    "generator.apply(weights_init_normal)\n",
+    "discriminator.apply(weights_init_normal)\n",
+    "epoch_D = 0\n",
+    "epoch_G = 0\n",
+    "\n",
+    "# train the network\n",
+    "discriminator.train()\n",
+    "generator.train()\n",
+    "print_every = 400\n",
+    "\n",
+    "for epoch in range(epoch_G, num_epochs):\n",
+    "    for i, batch in enumerate(dataloader):\n",
+    "\n",
+    "        # Model inputs\n",
+    "        real_A = Variable(batch[0].type(Tensor))\n",
+    "        real_B = Variable(batch[1].type(Tensor))\n",
+    "\n",
+    "        # Adversarial ground truths\n",
+    "        valid = Variable(Tensor(np.ones((real_B.size(0), *patch))), requires_grad=False)\n",
+    "        fake = Variable(Tensor(np.zeros((real_B.size(0), *patch))), requires_grad=False)\n",
+    "\n",
+    "        # ------------------\n",
+    "        #  Train Generators\n",
+    "        # ------------------\n",
+    "\n",
+    "        optimizer_G.zero_grad()\n",
+    "\n",
+    "        # GAN loss\n",
+    "        # TO DO: Put here your GAN loss\n",
+    "\n",
+    "        # Pixel-wise loss\n",
+    "        # TO DO: Put here your pixel loss\n",
+    "\n",
+    "        # Total loss\n",
+    "        # TO DO: Put here your total loss\n",
+    "\n",
+    "        loss_G.backward()\n",
+    "\n",
+    "        optimizer_G.step()\n",
+    "\n",
+    "        # ---------------------\n",
+    "        #  Train Discriminator\n",
+    "        # ---------------------\n",
+    "\n",
+    "        optimizer_D.zero_grad()\n",
+    "\n",
+    "        # Real loss\n",
+    "        pred_real = discriminator(real_A, real_B)\n",
+    "        loss_real = criterion_GAN(pred_real, valid)\n",
+    "\n",
+    "        # Fake loss\n",
+    "        pred_fake = discriminator(fake_A.detach(), real_B)\n",
+    "        loss_fake = criterion_GAN(pred_fake, fake)\n",
+    "\n",
+    "        # Total loss\n",
+    "        loss_D = 0.5 * (loss_real + loss_fake)\n",
+    "\n",
+    "        loss_D.backward()\n",
+    "        optimizer_D.step()\n",
+    "        \n",
+    "        # Print some loss stats\n",
+    "        if i % print_every == 0:\n",
+    "            # print discriminator and generator loss\n",
+    "            print('Epoch [{:5d}/{:5d}] | d_loss: {:6.4f} | g_loss: {:6.4f}'.format(\n",
+    "                    epoch+1, num_epochs, loss_D.item(), loss_G.item()))\n",
+    "    ## AFTER EACH EPOCH##\n",
+    "    # append discriminator loss and generator loss\n",
+    "    losses.append((loss_D.item(), loss_G.item()))\n",
+    "    if epoch % 100 == 0:\n",
+    "        print('Saving model...')\n",
+    "        save_model(epoch)\n"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {
+    "colab_type": "text",
+    "id": "Ed-ZbuVWBUgu"
+   },
+   "source": [
+    "Observation of the loss along the training"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {
+    "colab": {},
+    "colab_type": "code",
+    "id": "nOLW054DTLpg"
+   },
+   "outputs": [],
+   "source": [
+    "fig, ax = plt.subplots()\n",
+    "losses = np.array(losses)\n",
+    "plt.plot(losses.T[0], label='Discriminator')\n",
+    "plt.plot(losses.T[1], label='Generator')\n",
+    "plt.title(\"Training Losses\")\n",
+    "plt.legend()\n"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {
+    "colab_type": "text",
+    "id": "S58kJj9HBUgV"
+   },
+   "source": [
+    "If the training takes too much time, you can use a pretrained model in the meantime, to evaluate its performance.\n",
+    "\n",
+    "It is available at : https://partage.liris.cnrs.fr/index.php/s/xwEFmxn9ANeq4zY"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {
+    "colab_type": "text",
+    "id": "i0TC5qK3BUg4"
+   },
+   "source": [
+    "### Evaluate your cGAN"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {
+    "colab": {},
+    "colab_type": "code",
+    "id": "fYBRR6NYBUg6"
+   },
+   "outputs": [],
+   "source": [
+    "def load_model(epoch=200):\n",
+    "    if 'generator_'+str(epoch)+'.pth' in os.listdir() and 'discriminator_'+str(epoch)+'.pth' in os.listdir():\n",
+    "        if cuda:\n",
+    "            checkpoint_generator = torch.load('generator_'+str(epoch)+'.pth')\n",
+    "        else:\n",
+    "            checkpoint_generator = torch.load('generator_'+str(epoch)+'.pth', map_location='cpu')\n",
+    "        generator.load_state_dict(checkpoint_generator['model_state_dict'])\n",
+    "        optimizer_G.load_state_dict(checkpoint_generator['optimizer_state_dict'])\n",
+    "        epoch_G = checkpoint_generator['epoch']\n",
+    "        loss_G = checkpoint_generator['loss']\n",
+    "\n",
+    "        if cuda:\n",
+    "            checkpoint_discriminator = torch.load('discriminator_'+str(epoch)+'.pth')\n",
+    "        else:\n",
+    "            checkpoint_discriminator = torch.load('discriminator_'+str(epoch)+'.pth', map_location='cpu')\n",
+    "        discriminator.load_state_dict(checkpoint_discriminator['model_state_dict'])\n",
+    "        optimizer_D.load_state_dict(checkpoint_discriminator['optimizer_state_dict'])\n",
+    "        epoch_D = checkpoint_discriminator['epoch']\n",
+    "        loss_D = checkpoint_discriminator['loss']\n",
+    "    else:\n",
+    "        print('There isn\\' a training available with this number of epochs')"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {
+    "colab": {},
+    "colab_type": "code",
+    "id": "4V0DwQomBUg9"
+   },
+   "outputs": [],
+   "source": [
+    "load_model(epoch=200)\n",
+    "\n",
+    "# switching mode\n",
+    "generator.eval()"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {
+    "colab": {},
+    "colab_type": "code",
+    "id": "gyvmvkIvBUhB"
+   },
+   "outputs": [],
+   "source": [
+    "# show a sample evaluation image on the training base\n",
+    "image, mask = next(iter(dataloader))\n",
+    "output = generator(mask.type(Tensor))\n",
+    "output = output.view(16, 3, 256, 256)\n",
+    "output = output.cpu().detach()\n",
+    "for i in range(8):\n",
+    "    image_plot = reverse_transform(image[i])\n",
+    "    output_plot = reverse_transform(output[i])\n",
+    "    mask_plot = reverse_transform(mask[i])\n",
+    "    plot2x3Array(mask_plot,image_plot,output_plot)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {
+    "colab": {},
+    "colab_type": "code",
+    "id": "nqvrxBoGBUhD"
+   },
+   "outputs": [],
+   "source": [
+    "# show a sample evaluation image on the validation dataset\n",
+    "image, mask = next(iter(val_dataloader))\n",
+    "output = generator(mask.type(Tensor))\n",
+    "output = output.view(8, 3, 256, 256)\n",
+    "output = output.cpu().detach()\n",
+    "for i in range(8):\n",
+    "    image_plot = reverse_transform(image[i])\n",
+    "    output_plot = reverse_transform(output[i])\n",
+    "    mask_plot = reverse_transform(mask[i])\n",
+    "    plot2x3Array(mask_plot,image_plot,output_plot)"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {
+    "colab_type": "text",
+    "id": "qkFVjRsOBUhG"
+   },
+   "source": [
+    "<font color='red'>**Question 4**</font>                                                                  \n",
+    "Compare results for 100 and 200 epochs"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {
+    "colab": {},
+    "colab_type": "code",
+    "id": "k85Cl5_UDWyv"
+   },
+   "outputs": [],
+   "source": [
+    "# TO DO : Your code here to load and evaluate with a few samples\n",
+    "#         a model after 100 epochs\n",
+    "\n"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {
+    "colab": {},
+    "colab_type": "code",
+    "id": "_GbMIfRXBUhH"
+   },
+   "outputs": [],
+   "source": [
+    "# And finally :\n",
+    "if cuda:\n",
+    "    torch.cuda.empty_cache()"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {
+    "colab_type": "text",
+    "id": "rVxSSPJgK60P"
+   },
+   "source": [
+    "# How to submit your Work ?\n",
+    "\n",
+    "This work must be done individually. The expected output is a repository named gan-cgan on https://gitlab.ec-lyon.fr. It must contain your notebook (or python files) and a README.md file that explains briefly the successive steps of the project. The last commit is due before 11:59 pm on Wednesday, March 29, 2023. Subsequent commits will not be considered."
+   ]
+  }
+ ],
+ "metadata": {
+  "colab": {
+   "collapsed_sections": [],
+   "name": "BE2 - GAN and cGAN.ipynb",
+   "provenance": []
+  },
+  "kernelspec": {
+   "display_name": "Python 3",
+   "language": "python",
+   "name": "python3"
+  },
+  "language_info": {
+   "codemirror_mode": {
+    "name": "ipython",
+    "version": 3
+   },
+   "file_extension": ".py",
+   "mimetype": "text/x-python",
+   "name": "python",
+   "nbconvert_exporter": "python",
+   "pygments_lexer": "ipython3",
+   "version": "3.8.8"
+  }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 1
+}
diff --git a/BE2_GAUDRY_GAN_and_cGAN_.ipynb b/BE2_GAUDRY_GAN_and_cGAN_.ipynb
new file mode 100644
index 0000000000000000000000000000000000000000..81a3d024f045612381bd7b43a5ec4d7e92dadbdc
--- /dev/null
+++ b/BE2_GAUDRY_GAN_and_cGAN_.ipynb
@@ -0,0 +1 @@
+{"cells":[{"cell_type":"markdown","metadata":{"id":"UGwKsKS4GMTN"},"source":["<h1 ><big><center>MSO 3.4 - Deep Structured Learning</center></big></h1>\n","\n","<h2><big><center> BE 2 - GANs and cGAN </center></big></h2>\n","\n","<h5><big><center>Adapted from <i>Projet d'Option</i> of : Mhamed Jabri, Martin Chauvin, Ahmed Sahraoui, Zakariae Moustaïne and Taoufik Bouchikhi\n","\n","\n","<p align=\"center\">\n","<img height=300px src=\"https://cdn-images-1.medium.com/max/1080/0*tJRy5Chmk4XymxwN.png\"/></p>\n","<p align=\"center\"></p>"]},{"cell_type":"markdown","metadata":{"id":"16aVF81lJuiP"},"source":["The aim of this assignment is to discover GANs, understand how they are implemented and then explore one specific architecture of GANs that allows us to perform image to image translation (which corresponds to the picture that you can see above this text ! )\n","\n","Before starting the exploration of the world of GANs, here's  what students should do and send back for this assignement : \n","* In the \"tutorial\" parts of this assignement that focus on explaining new concepts, you'll find <font color='red'>**questions**</font>  that aim to test your understanding of those concepts. \n","* In some of the code cells, you'll have to complete the code and you'll find a \"TO DO\" explaining what you should implement."]},{"cell_type":"markdown","metadata":{"id":"M-WNKvhOP1ED"},"source":["# Part1: DC-GAN"]},{"cell_type":"markdown","metadata":{"id":"y_r8nMTGQI9a"},"source":["In this part, we aim to learn and understand the basic concepts of **Generative Adversarial Networks** through a DCGAN and generate new celebrities from the learned network after showing it real celebrities. For this purpose, please study the tutorial here: https://pytorch.org/tutorials/beginner/dcgan_faces_tutorial.html\n"]},{"cell_type":"markdown","metadata":{"id":"jiHCy4_UUBFb"},"source":["##Work to do\n","Now we want to generate handwritten digits using the MNIST dataset. It is available within torvision package (https://pytorch.org/vision/stable/generated/torchvision.datasets.MNIST.html#torchvision.datasets.MNIST)\n","\n","Please re-train the DCGAN and display some automatically generated handwritten digits.\n","\n"]},{"cell_type":"code","execution_count":null,"metadata":{"colab":{"base_uri":"https://localhost:8080/"},"id":"sIL7UvYAZx6L","executionInfo":{"status":"ok","timestamp":1678882421601,"user_tz":-60,"elapsed":186,"user":{"displayName":"Florian Gaudry","userId":"04425733722793549516"}},"outputId":"8cec459d-66cc-479a-eece-47d48150690c"},"outputs":[{"output_type":"stream","name":"stdout","text":["Random Seed:  999\n"]},{"output_type":"execute_result","data":{"text/plain":["<torch._C.Generator at 0x7fb1a1d89bd0>"]},"metadata":{},"execution_count":4}],"source":["#TO DO: your code here to adapt the code from the tutorial to experiment on MNIST dataset\n","from __future__ import print_function\n","#%matplotlib inline\n","import argparse\n","import os\n","import random\n","import torch\n","import torch.nn as nn\n","import torch.nn.parallel\n","import torch.backends.cudnn as cudnn\n","import torch.optim as optim\n","import torch.utils.data\n","import torchvision.datasets as dset\n","import torchvision.transforms as transforms\n","import torchvision.utils as vutils\n","import numpy as np\n","import matplotlib.pyplot as plt\n","import matplotlib.animation as animation\n","from IPython.display import HTML\n","\n","# Set random seed for reproducibility\n","manualSeed = 999\n","#manualSeed = random.randint(1, 10000) # use if you want new results\n","print(\"Random Seed: \", manualSeed)\n","random.seed(manualSeed)\n","torch.manual_seed(manualSeed)"]},{"cell_type":"code","execution_count":7,"metadata":{"id":"55YH_FQBLAKA","executionInfo":{"status":"ok","timestamp":1679064156042,"user_tz":-60,"elapsed":234,"user":{"displayName":"Florian Gaudry","userId":"04425733722793549516"}}},"outputs":[],"source":["# Root directory for dataset\n","dataroot = \"data/celeba\"\n","\n","# Number of workers for dataloader\n","workers = 2\n","\n","# Batch size during training\n","batch_size = 128\n","\n","# Spatial size of training images. All images will be resized to this\n","#   size using a transformer.\n","image_size = 64\n","\n","# Number of channels in the training images. For color images this is 3\n","nc = 1\n","\n","# Size of z latent vector (i.e. size of generator input)\n","nz = 100\n","\n","# Size of feature maps in generator\n","ngf = 64\n","\n","# Size of feature maps in discriminator\n","ndf = 64\n","\n","# Number of training epochs\n","num_epochs = 5\n","\n","# Learning rate for optimizers\n","lr = 0.0002\n","\n","# Beta1 hyperparam for Adam optimizers\n","beta1 = 0.5\n","\n","# Number of GPUs available. Use 0 for CPU mode.\n","ngpu = 1"]},{"cell_type":"code","execution_count":null,"metadata":{"colab":{"base_uri":"https://localhost:8080/","height":443,"referenced_widgets":["1e36689c6e3b4540af78f20862d04898","3a07c521ad8f44e7ba6ef57c182c01e0","e8c931c1361b41a395f9c257e77bba9c","c9681befe58c4bd992c1c93c193b9f6f","8c67d3b695994062a7161f56eaa99530","a1a14cdea09342c1ad80273469cec5a0","f49a0430fcc448ad980ebbfd0ec9b58e","9d8022f8bf7a44218e482b83f46fd947","c706ba9682dd4384997a6059aca253cb","eac304c981804cd9b5f29803acfc7efd","ca37bab93af74dae87f01916dc49ee24","e2867e04986a42e3944412d1c7129656","31fa538191fc4e67ab2fea1cb7e4ea04","dbe3af00397c4f408dedc9543c7fbcac","c40a461f12644f2c8c1ea80190d90bd2","637143360d734d7398e64c003da291c1","4e09360f2a7d4a6cbf94798fbe5105cb","d2555ebdd173497a9f49054f2ca82793","b3ffa36739ec4c5c9d0f0690e9920d19","b0bd56c6c26d49adac84eaaaeac75e9c","8a84f6f970ee41ebb69f82aa2a006f8a","ce1790d859da42fe8dfe59dbe7c9d232","3cb8c9bc538e47108f56a375a61843dc","de5b309afba74b2994887b655a785740","d8f1a2b25b9e4aa38bb9b360e635a0e1","c76733e8e9444e05aeb16f749d22e101","a424e4dc9ff444ee9e91e18f3811a0ba","02631df0e525476198fab343808cf032","7e491dbf2a9d4dbeb0b456bb489ce642","d7cb13eae183456685915195cfc39672","d8df861c33d44b2fbd9d96d42c797025","0320ce9f267f450692259fa6e985e848","8c5be51ac95f40a5aeb7bab19b1b7ee9","82bbfe059d2443e6aecefe547f675843","c254657012b84acf9326e55d7e842d09","56351b86306d402984d6ec489f12cdb1","13422fcd179a4792b9b94c173667958e","57a5d6d615a847c19eec394b14db6b2d","2ea85461d5654243b12e1c088dbeb036","b692a33348a24c74a201325b8b0699c5","8111287f856643548d03e1670a82065f","a5808ce132484f5da81fabf5a2bc335c","5ecc7186a0874145bce0655c99a51c44","6071a8fa5dc64f8fbfa05d1096134610"]},"id":"Zl67nkScLAKB","executionInfo":{"status":"ok","timestamp":1678865557776,"user_tz":-60,"elapsed":1266,"user":{"displayName":"Florian Gaudry","userId":"04425733722793549516"}},"outputId":"11e8ae94-c74e-4904-c13f-cebf0a103c2c"},"outputs":[{"output_type":"stream","name":"stdout","text":["Downloading http://yann.lecun.com/exdb/mnist/train-images-idx3-ubyte.gz\n","Downloading http://yann.lecun.com/exdb/mnist/train-images-idx3-ubyte.gz to data/celeba/MNIST/raw/train-images-idx3-ubyte.gz\n"]},{"output_type":"display_data","data":{"text/plain":["  0%|          | 0/9912422 [00:00<?, ?it/s]"],"application/vnd.jupyter.widget-view+json":{"version_major":2,"version_minor":0,"model_id":"1e36689c6e3b4540af78f20862d04898"}},"metadata":{}},{"output_type":"stream","name":"stdout","text":["Extracting data/celeba/MNIST/raw/train-images-idx3-ubyte.gz to data/celeba/MNIST/raw\n","\n","Downloading http://yann.lecun.com/exdb/mnist/train-labels-idx1-ubyte.gz\n","Downloading http://yann.lecun.com/exdb/mnist/train-labels-idx1-ubyte.gz to data/celeba/MNIST/raw/train-labels-idx1-ubyte.gz\n"]},{"output_type":"display_data","data":{"text/plain":["  0%|          | 0/28881 [00:00<?, ?it/s]"],"application/vnd.jupyter.widget-view+json":{"version_major":2,"version_minor":0,"model_id":"e2867e04986a42e3944412d1c7129656"}},"metadata":{}},{"output_type":"stream","name":"stdout","text":["Extracting data/celeba/MNIST/raw/train-labels-idx1-ubyte.gz to data/celeba/MNIST/raw\n","\n","Downloading http://yann.lecun.com/exdb/mnist/t10k-images-idx3-ubyte.gz\n","Downloading http://yann.lecun.com/exdb/mnist/t10k-images-idx3-ubyte.gz to data/celeba/MNIST/raw/t10k-images-idx3-ubyte.gz\n"]},{"output_type":"display_data","data":{"text/plain":["  0%|          | 0/1648877 [00:00<?, ?it/s]"],"application/vnd.jupyter.widget-view+json":{"version_major":2,"version_minor":0,"model_id":"3cb8c9bc538e47108f56a375a61843dc"}},"metadata":{}},{"output_type":"stream","name":"stdout","text":["Extracting data/celeba/MNIST/raw/t10k-images-idx3-ubyte.gz to data/celeba/MNIST/raw\n","\n","Downloading http://yann.lecun.com/exdb/mnist/t10k-labels-idx1-ubyte.gz\n","Downloading http://yann.lecun.com/exdb/mnist/t10k-labels-idx1-ubyte.gz to data/celeba/MNIST/raw/t10k-labels-idx1-ubyte.gz\n"]},{"output_type":"display_data","data":{"text/plain":["  0%|          | 0/4542 [00:00<?, ?it/s]"],"application/vnd.jupyter.widget-view+json":{"version_major":2,"version_minor":0,"model_id":"82bbfe059d2443e6aecefe547f675843"}},"metadata":{}},{"output_type":"stream","name":"stdout","text":["Extracting data/celeba/MNIST/raw/t10k-labels-idx1-ubyte.gz to data/celeba/MNIST/raw\n","\n"]}],"source":["# Create the dataset\n","transform = transforms.Compose([\n","    transforms.Resize(image_size),\n","    transforms.ToTensor(),\n","    transforms.Normalize((0.5,), (0.5,))\n","])\n","\n","dataset = dset.MNIST(root=dataroot, train=True, download=True, transform=transform)"]},{"cell_type":"code","execution_count":null,"metadata":{"colab":{"base_uri":"https://localhost:8080/","height":499},"id":"PSRjjp2kLAKB","executionInfo":{"status":"ok","timestamp":1678865566973,"user_tz":-60,"elapsed":5908,"user":{"displayName":"Florian Gaudry","userId":"04425733722793549516"}},"outputId":"75ec9ea2-c915-4ea6-b477-f30a1c5185b4"},"outputs":[{"output_type":"execute_result","data":{"text/plain":["<matplotlib.image.AxesImage at 0x7ff68a370fd0>"]},"metadata":{},"execution_count":5},{"output_type":"display_data","data":{"text/plain":["<Figure size 576x576 with 1 Axes>"],"image/png":"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\n"},"metadata":{"needs_background":"light"}}],"source":["# Create the dataloader\n","dataloader = torch.utils.data.DataLoader(dataset, batch_size=batch_size,\n","                                         shuffle=True, num_workers=workers)\n","\n","# Decide which device we want to run on\n","device = torch.device(\"cuda:0\" if (torch.cuda.is_available() and ngpu > 0) else \"cpu\")\n","\n","# Plot some training images\n","real_batch = next(iter(dataloader))\n","plt.figure(figsize=(8,8))\n","plt.axis(\"off\")\n","plt.title(\"Training Images\")\n","plt.imshow(np.transpose(vutils.make_grid(real_batch[0].to(device)[:64], padding=2, normalize=True).cpu(),(1,2,0)))"]},{"cell_type":"code","execution_count":null,"metadata":{"id":"9s21lENoLAKC"},"outputs":[],"source":["# custom weights initialization called on netG and netD\n","def weights_init(m):\n","    classname = m.__class__.__name__\n","    if classname.find('Conv') != -1:\n","        nn.init.normal_(m.weight.data, 0.0, 0.02)\n","    elif classname.find('BatchNorm') != -1:\n","        nn.init.normal_(m.weight.data, 1.0, 0.02)\n","        nn.init.constant_(m.bias.data, 0)"]},{"cell_type":"code","execution_count":null,"metadata":{"id":"cKxyWhXjLAKC"},"outputs":[],"source":["# Generator Code\n","\n","class Generator(nn.Module):\n","    def __init__(self, ngpu):\n","        super(Generator, self).__init__()\n","        self.ngpu = ngpu\n","        self.main = nn.Sequential(\n","            # input is Z, going into a convolution\n","            nn.ConvTranspose2d( nz, ngf * 8, 4, 1, 0, bias=False),\n","            nn.BatchNorm2d(ngf * 8),\n","            nn.ReLU(True),\n","            # state size. (ngf*8) x 4 x 4\n","            nn.ConvTranspose2d(ngf * 8, ngf * 4, 4, 2, 1, bias=False),\n","            nn.BatchNorm2d(ngf * 4),\n","            nn.ReLU(True),\n","            # state size. (ngf*4) x 8 x 8\n","            nn.ConvTranspose2d( ngf * 4, ngf * 2, 4, 2, 1, bias=False),\n","            nn.BatchNorm2d(ngf * 2),\n","            nn.ReLU(True),\n","            # state size. (ngf*2) x 16 x 16\n","            nn.ConvTranspose2d( ngf * 2, ngf, 4, 2, 1, bias=False),\n","            nn.BatchNorm2d(ngf),\n","            nn.ReLU(True),\n","            # state size. (ngf) x 32 x 32\n","            nn.ConvTranspose2d( ngf, nc, 4, 2, 1, bias=False),\n","            nn.Tanh()\n","            # state size. (nc) x 64 x 64\n","        )\n","\n","    def forward(self, input):\n","        return self.main(input)"]},{"cell_type":"code","execution_count":null,"metadata":{"colab":{"base_uri":"https://localhost:8080/"},"id":"w4MuGztGLAKD","executionInfo":{"status":"ok","timestamp":1678865573128,"user_tz":-60,"elapsed":5,"user":{"displayName":"Florian Gaudry","userId":"04425733722793549516"}},"outputId":"9974dedb-f5da-41a0-c381-342e416b325b"},"outputs":[{"output_type":"stream","name":"stdout","text":["Generator(\n","  (main): Sequential(\n","    (0): ConvTranspose2d(100, 512, kernel_size=(4, 4), stride=(1, 1), bias=False)\n","    (1): BatchNorm2d(512, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n","    (2): ReLU(inplace=True)\n","    (3): ConvTranspose2d(512, 256, kernel_size=(4, 4), stride=(2, 2), padding=(1, 1), bias=False)\n","    (4): BatchNorm2d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n","    (5): ReLU(inplace=True)\n","    (6): ConvTranspose2d(256, 128, kernel_size=(4, 4), stride=(2, 2), padding=(1, 1), bias=False)\n","    (7): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n","    (8): ReLU(inplace=True)\n","    (9): ConvTranspose2d(128, 64, kernel_size=(4, 4), stride=(2, 2), padding=(1, 1), bias=False)\n","    (10): BatchNorm2d(64, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n","    (11): ReLU(inplace=True)\n","    (12): ConvTranspose2d(64, 1, kernel_size=(4, 4), stride=(2, 2), padding=(1, 1), bias=False)\n","    (13): Tanh()\n","  )\n",")\n"]}],"source":["# Create the generator\n","netG = Generator(ngpu).to(device)\n","\n","# Handle multi-gpu if desired\n","if (device.type == 'cuda') and (ngpu > 1):\n","    netG = nn.DataParallel(netG, list(range(ngpu)))\n","\n","# Apply the weights_init function to randomly initialize all weights\n","#  to mean=0, stdev=0.02.\n","netG.apply(weights_init)\n","\n","# Print the model\n","print(netG)"]},{"cell_type":"code","execution_count":null,"metadata":{"id":"GuXNXYBxLAKD"},"outputs":[],"source":["class Discriminator(nn.Module):\n","    def __init__(self, ngpu):\n","        super(Discriminator, self).__init__()\n","        self.ngpu = ngpu\n","        self.main = nn.Sequential(\n","            # input is (nc) x 64 x 64\n","            nn.Conv2d(nc, ndf, 4, 2, 1, bias=False),\n","            nn.LeakyReLU(0.2, inplace=True),\n","            # state size. (ndf) x 32 x 32\n","            nn.Conv2d(ndf, ndf * 2, 4, 2, 1, bias=False),\n","            nn.BatchNorm2d(ndf * 2),\n","            nn.LeakyReLU(0.2, inplace=True),\n","            # state size. (ndf*2) x 16 x 16\n","            nn.Conv2d(ndf * 2, ndf * 4, 4, 2, 1, bias=False),\n","            nn.BatchNorm2d(ndf * 4),\n","            nn.LeakyReLU(0.2, inplace=True),\n","            # state size. (ndf*4) x 8 x 8\n","            nn.Conv2d(ndf * 4, ndf * 8, 4, 2, 1, bias=False),\n","            nn.BatchNorm2d(ndf * 8),\n","            nn.LeakyReLU(0.2, inplace=True),\n","            # state size. (ndf*8) x 4 x 4\n","            nn.Conv2d(ndf * 8, 1, 4, 1, 0, bias=False),\n","            nn.Sigmoid()\n","        )\n","\n","    def forward(self, input):\n","        return self.main(input)"]},{"cell_type":"code","execution_count":null,"metadata":{"colab":{"base_uri":"https://localhost:8080/"},"id":"ILkL6QCmLAKE","executionInfo":{"status":"ok","timestamp":1678865576418,"user_tz":-60,"elapsed":8,"user":{"displayName":"Florian Gaudry","userId":"04425733722793549516"}},"outputId":"7e4543ae-6df6-4ac4-d02a-fefc64a3bfe4"},"outputs":[{"output_type":"stream","name":"stdout","text":["Discriminator(\n","  (main): Sequential(\n","    (0): Conv2d(1, 64, kernel_size=(4, 4), stride=(2, 2), padding=(1, 1), bias=False)\n","    (1): LeakyReLU(negative_slope=0.2, inplace=True)\n","    (2): Conv2d(64, 128, kernel_size=(4, 4), stride=(2, 2), padding=(1, 1), bias=False)\n","    (3): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n","    (4): LeakyReLU(negative_slope=0.2, inplace=True)\n","    (5): Conv2d(128, 256, kernel_size=(4, 4), stride=(2, 2), padding=(1, 1), bias=False)\n","    (6): BatchNorm2d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n","    (7): LeakyReLU(negative_slope=0.2, inplace=True)\n","    (8): Conv2d(256, 512, kernel_size=(4, 4), stride=(2, 2), padding=(1, 1), bias=False)\n","    (9): BatchNorm2d(512, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n","    (10): LeakyReLU(negative_slope=0.2, inplace=True)\n","    (11): Conv2d(512, 1, kernel_size=(4, 4), stride=(1, 1), bias=False)\n","    (12): Sigmoid()\n","  )\n",")\n"]}],"source":["# Create the Discriminator\n","netD = Discriminator(ngpu).to(device)\n","\n","# Handle multi-gpu if desired\n","if (device.type == 'cuda') and (ngpu > 1):\n","    netD = nn.DataParallel(netD, list(range(ngpu)))\n","\n","# Apply the weights_init function to randomly initialize all weights\n","#  to mean=0, stdev=0.2.\n","netD.apply(weights_init)\n","\n","# Print the model\n","print(netD)"]},{"cell_type":"code","execution_count":null,"metadata":{"id":"XU1_xAH4LAKE"},"outputs":[],"source":["# Initialize BCELoss function\n","criterion = nn.BCELoss()\n","\n","# Create batch of latent vectors that we will use to visualize\n","#  the progression of the generator\n","fixed_noise = torch.randn(64, nz, 1, 1, device=device)\n","\n","# Establish convention for real and fake labels during training\n","real_label = 1.\n","fake_label = 0.\n","\n","# Setup Adam optimizers for both G and D\n","optimizerD = optim.Adam(netD.parameters(), lr=lr, betas=(beta1, 0.999))\n","optimizerG = optim.Adam(netG.parameters(), lr=lr, betas=(beta1, 0.999))"]},{"cell_type":"code","execution_count":null,"metadata":{"colab":{"base_uri":"https://localhost:8080/"},"id":"knrQ3bAsLAKE","executionInfo":{"status":"ok","timestamp":1678866016098,"user_tz":-60,"elapsed":433433,"user":{"displayName":"Florian Gaudry","userId":"04425733722793549516"}},"outputId":"d1bb0821-ed27-4a1b-d758-e296db0ca132"},"outputs":[{"output_type":"stream","name":"stdout","text":["Starting Training Loop...\n","[0/5][0/469]\tLoss_D: 1.6647\tLoss_G: 3.5638\tD(x): 0.5276\tD(G(z)): 0.5480 / 0.0425\n","[0/5][20/469]\tLoss_D: 1.0491\tLoss_G: 21.8343\tD(x): 0.5174\tD(G(z)): 0.0000 / 0.0000\n","[0/5][40/469]\tLoss_D: 0.0239\tLoss_G: 22.6823\tD(x): 0.9784\tD(G(z)): 0.0000 / 0.0000\n","[0/5][60/469]\tLoss_D: 0.0231\tLoss_G: 4.2523\tD(x): 0.9860\tD(G(z)): 0.0041 / 0.0181\n","[0/5][80/469]\tLoss_D: 1.8581\tLoss_G: 26.7094\tD(x): 0.9890\tD(G(z)): 0.7315 / 0.0000\n","[0/5][100/469]\tLoss_D: 0.0737\tLoss_G: 4.5835\tD(x): 0.9727\tD(G(z)): 0.0427 / 0.0188\n","[0/5][120/469]\tLoss_D: 0.1439\tLoss_G: 5.7041\tD(x): 0.9509\tD(G(z)): 0.0810 / 0.0062\n","[0/5][140/469]\tLoss_D: 0.0786\tLoss_G: 4.8198\tD(x): 0.9627\tD(G(z)): 0.0236 / 0.0127\n","[0/5][160/469]\tLoss_D: 0.2643\tLoss_G: 4.8105\tD(x): 0.9252\tD(G(z)): 0.1388 / 0.0145\n","[0/5][180/469]\tLoss_D: 0.2085\tLoss_G: 4.7257\tD(x): 0.9291\tD(G(z)): 0.1136 / 0.0129\n","[0/5][200/469]\tLoss_D: 0.0612\tLoss_G: 5.4904\tD(x): 0.9604\tD(G(z)): 0.0102 / 0.0055\n","[0/5][220/469]\tLoss_D: 0.2815\tLoss_G: 10.9832\tD(x): 0.8375\tD(G(z)): 0.0009 / 0.0001\n","[0/5][240/469]\tLoss_D: 0.1576\tLoss_G: 3.9767\tD(x): 0.9064\tD(G(z)): 0.0256 / 0.0321\n","[0/5][260/469]\tLoss_D: 0.1244\tLoss_G: 4.0045\tD(x): 0.9155\tD(G(z)): 0.0287 / 0.0285\n","[0/5][280/469]\tLoss_D: 0.1200\tLoss_G: 4.3942\tD(x): 0.9539\tD(G(z)): 0.0626 / 0.0204\n","[0/5][300/469]\tLoss_D: 0.7372\tLoss_G: 2.6610\tD(x): 0.6373\tD(G(z)): 0.1194 / 0.1047\n","[0/5][320/469]\tLoss_D: 0.2920\tLoss_G: 3.0283\tD(x): 0.8504\tD(G(z)): 0.0890 / 0.0742\n","[0/5][340/469]\tLoss_D: 0.2042\tLoss_G: 3.1349\tD(x): 0.9075\tD(G(z)): 0.0894 / 0.0666\n","[0/5][360/469]\tLoss_D: 0.1342\tLoss_G: 3.8071\tD(x): 0.9180\tD(G(z)): 0.0421 / 0.0330\n","[0/5][380/469]\tLoss_D: 0.9034\tLoss_G: 2.1673\tD(x): 0.9204\tD(G(z)): 0.4430 / 0.1795\n","[0/5][400/469]\tLoss_D: 0.3743\tLoss_G: 2.2810\tD(x): 0.8238\tD(G(z)): 0.1373 / 0.1278\n","[0/5][420/469]\tLoss_D: 0.2814\tLoss_G: 2.5952\tD(x): 0.8171\tD(G(z)): 0.0528 / 0.0986\n","[0/5][440/469]\tLoss_D: 0.1571\tLoss_G: 3.4449\tD(x): 0.9390\tD(G(z)): 0.0856 / 0.0434\n","[0/5][460/469]\tLoss_D: 0.1536\tLoss_G: 3.1575\tD(x): 0.9385\tD(G(z)): 0.0808 / 0.0594\n","[1/5][0/469]\tLoss_D: 2.2123\tLoss_G: 2.3706\tD(x): 0.2470\tD(G(z)): 0.0019 / 0.1546\n","[1/5][20/469]\tLoss_D: 0.1598\tLoss_G: 3.1073\tD(x): 0.9228\tD(G(z)): 0.0710 / 0.0610\n","[1/5][40/469]\tLoss_D: 0.1417\tLoss_G: 3.6814\tD(x): 0.9493\tD(G(z)): 0.0784 / 0.0381\n","[1/5][60/469]\tLoss_D: 0.3697\tLoss_G: 2.5002\tD(x): 0.7730\tD(G(z)): 0.0780 / 0.1147\n","[1/5][80/469]\tLoss_D: 0.2574\tLoss_G: 3.1578\tD(x): 0.9000\tD(G(z)): 0.1287 / 0.0594\n","[1/5][100/469]\tLoss_D: 0.6026\tLoss_G: 1.6531\tD(x): 0.6256\tD(G(z)): 0.0292 / 0.2517\n","[1/5][120/469]\tLoss_D: 0.2989\tLoss_G: 4.1414\tD(x): 0.9702\tD(G(z)): 0.2183 / 0.0233\n","[1/5][140/469]\tLoss_D: 0.6138\tLoss_G: 1.5258\tD(x): 0.6835\tD(G(z)): 0.1611 / 0.2514\n","[1/5][160/469]\tLoss_D: 0.4902\tLoss_G: 2.7283\tD(x): 0.8559\tD(G(z)): 0.2556 / 0.0926\n","[1/5][180/469]\tLoss_D: 0.3013\tLoss_G: 2.7193\tD(x): 0.8909\tD(G(z)): 0.1585 / 0.0836\n","[1/5][200/469]\tLoss_D: 0.3867\tLoss_G: 3.5924\tD(x): 0.9520\tD(G(z)): 0.2594 / 0.0387\n","[1/5][220/469]\tLoss_D: 1.1077\tLoss_G: 2.3051\tD(x): 0.5405\tD(G(z)): 0.1041 / 0.1711\n","[1/5][240/469]\tLoss_D: 0.4449\tLoss_G: 1.4495\tD(x): 0.7266\tD(G(z)): 0.0817 / 0.2749\n","[1/5][260/469]\tLoss_D: 0.2762\tLoss_G: 2.7816\tD(x): 0.8940\tD(G(z)): 0.1372 / 0.0808\n","[1/5][280/469]\tLoss_D: 1.0179\tLoss_G: 3.5747\tD(x): 0.8276\tD(G(z)): 0.4899 / 0.0483\n","[1/5][300/469]\tLoss_D: 0.6471\tLoss_G: 1.0353\tD(x): 0.6202\tD(G(z)): 0.0695 / 0.3963\n","[1/5][320/469]\tLoss_D: 0.2517\tLoss_G: 2.9403\tD(x): 0.8976\tD(G(z)): 0.1225 / 0.0719\n","[1/5][340/469]\tLoss_D: 1.5847\tLoss_G: 2.0929\tD(x): 0.2890\tD(G(z)): 0.0056 / 0.1767\n","[1/5][360/469]\tLoss_D: 0.3511\tLoss_G: 2.0518\tD(x): 0.8279\tD(G(z)): 0.1323 / 0.1532\n","[1/5][380/469]\tLoss_D: 0.3219\tLoss_G: 3.1617\tD(x): 0.9282\tD(G(z)): 0.2090 / 0.0520\n","[1/5][400/469]\tLoss_D: 0.7635\tLoss_G: 2.1162\tD(x): 0.6598\tD(G(z)): 0.1758 / 0.1863\n","[1/5][420/469]\tLoss_D: 0.3821\tLoss_G: 2.3514\tD(x): 0.8491\tD(G(z)): 0.1757 / 0.1212\n","[1/5][440/469]\tLoss_D: 0.3880\tLoss_G: 1.6788\tD(x): 0.7534\tD(G(z)): 0.0729 / 0.2369\n","[1/5][460/469]\tLoss_D: 0.6067\tLoss_G: 4.5046\tD(x): 0.9781\tD(G(z)): 0.4085 / 0.0149\n","[2/5][0/469]\tLoss_D: 1.2548\tLoss_G: 3.7427\tD(x): 0.9799\tD(G(z)): 0.6052 / 0.0562\n","[2/5][20/469]\tLoss_D: 0.2899\tLoss_G: 2.4680\tD(x): 0.8374\tD(G(z)): 0.0870 / 0.1160\n","[2/5][40/469]\tLoss_D: 0.1841\tLoss_G: 3.4789\tD(x): 0.9094\tD(G(z)): 0.0801 / 0.0419\n","[2/5][60/469]\tLoss_D: 0.6342\tLoss_G: 1.7657\tD(x): 0.6471\tD(G(z)): 0.1340 / 0.2204\n","[2/5][80/469]\tLoss_D: 0.3200\tLoss_G: 2.6653\tD(x): 0.8595\tD(G(z)): 0.1382 / 0.0936\n","[2/5][100/469]\tLoss_D: 1.4193\tLoss_G: 4.1833\tD(x): 0.9590\tD(G(z)): 0.6669 / 0.0288\n","[2/5][120/469]\tLoss_D: 0.3381\tLoss_G: 2.7596\tD(x): 0.8656\tD(G(z)): 0.1539 / 0.0840\n","[2/5][140/469]\tLoss_D: 0.2122\tLoss_G: 2.6243\tD(x): 0.8752\tD(G(z)): 0.0660 / 0.0964\n","[2/5][160/469]\tLoss_D: 0.2174\tLoss_G: 1.8438\tD(x): 0.8705\tD(G(z)): 0.0641 / 0.2004\n","[2/5][180/469]\tLoss_D: 0.2597\tLoss_G: 3.1734\tD(x): 0.8448\tD(G(z)): 0.0688 / 0.0611\n","[2/5][200/469]\tLoss_D: 0.3135\tLoss_G: 3.9417\tD(x): 0.9440\tD(G(z)): 0.2079 / 0.0271\n","[2/5][220/469]\tLoss_D: 1.6299\tLoss_G: 6.6208\tD(x): 0.9919\tD(G(z)): 0.7251 / 0.0032\n","[2/5][240/469]\tLoss_D: 0.2912\tLoss_G: 2.9018\tD(x): 0.9035\tD(G(z)): 0.1603 / 0.0707\n","[2/5][260/469]\tLoss_D: 0.2321\tLoss_G: 3.9806\tD(x): 0.9671\tD(G(z)): 0.1679 / 0.0260\n","[2/5][280/469]\tLoss_D: 0.8318\tLoss_G: 3.7707\tD(x): 0.8823\tD(G(z)): 0.4557 / 0.0360\n","[2/5][300/469]\tLoss_D: 0.3730\tLoss_G: 2.6488\tD(x): 0.8467\tD(G(z)): 0.1703 / 0.0928\n","[2/5][320/469]\tLoss_D: 0.5773\tLoss_G: 1.0385\tD(x): 0.6247\tD(G(z)): 0.0270 / 0.4125\n","[2/5][340/469]\tLoss_D: 0.1735\tLoss_G: 3.6815\tD(x): 0.9550\tD(G(z)): 0.1089 / 0.0366\n","[2/5][360/469]\tLoss_D: 0.3676\tLoss_G: 1.6565\tD(x): 0.7280\tD(G(z)): 0.0139 / 0.2521\n","[2/5][380/469]\tLoss_D: 0.1300\tLoss_G: 3.3063\tD(x): 0.9025\tD(G(z)): 0.0197 / 0.0542\n","[2/5][400/469]\tLoss_D: 0.1578\tLoss_G: 6.8877\tD(x): 0.9899\tD(G(z)): 0.1290 / 0.0016\n","[2/5][420/469]\tLoss_D: 1.2078\tLoss_G: 1.0852\tD(x): 0.4183\tD(G(z)): 0.1233 / 0.4049\n","[2/5][440/469]\tLoss_D: 0.9360\tLoss_G: 0.6809\tD(x): 0.4693\tD(G(z)): 0.0530 / 0.5842\n","[2/5][460/469]\tLoss_D: 0.7680\tLoss_G: 1.8053\tD(x): 0.5921\tD(G(z)): 0.1293 / 0.2121\n","[3/5][0/469]\tLoss_D: 0.3613\tLoss_G: 1.7326\tD(x): 0.7619\tD(G(z)): 0.0618 / 0.2229\n","[3/5][20/469]\tLoss_D: 0.2535\tLoss_G: 2.8364\tD(x): 0.8741\tD(G(z)): 0.1013 / 0.0765\n","[3/5][40/469]\tLoss_D: 0.2285\tLoss_G: 3.0179\tD(x): 0.8545\tD(G(z)): 0.0532 / 0.0723\n","[3/5][60/469]\tLoss_D: 0.1930\tLoss_G: 4.4164\tD(x): 0.9469\tD(G(z)): 0.1223 / 0.0167\n","[3/5][80/469]\tLoss_D: 0.1275\tLoss_G: 2.8571\tD(x): 0.9214\tD(G(z)): 0.0382 / 0.0783\n","[3/5][100/469]\tLoss_D: 0.1011\tLoss_G: 4.6010\tD(x): 0.9765\tD(G(z)): 0.0711 / 0.0152\n","[3/5][120/469]\tLoss_D: 0.9349\tLoss_G: 3.0213\tD(x): 0.8747\tD(G(z)): 0.4930 / 0.0749\n","[3/5][140/469]\tLoss_D: 0.3836\tLoss_G: 4.2895\tD(x): 0.9294\tD(G(z)): 0.2467 / 0.0185\n","[3/5][160/469]\tLoss_D: 0.5059\tLoss_G: 5.0388\tD(x): 0.9096\tD(G(z)): 0.3147 / 0.0086\n","[3/5][180/469]\tLoss_D: 0.6824\tLoss_G: 4.2530\tD(x): 0.9481\tD(G(z)): 0.4199 / 0.0229\n","[3/5][200/469]\tLoss_D: 0.1721\tLoss_G: 3.5859\tD(x): 0.9409\tD(G(z)): 0.0992 / 0.0388\n","[3/5][220/469]\tLoss_D: 0.1103\tLoss_G: 3.8898\tD(x): 0.9291\tD(G(z)): 0.0318 / 0.0314\n","[3/5][240/469]\tLoss_D: 0.1186\tLoss_G: 4.2645\tD(x): 0.9650\tD(G(z)): 0.0749 / 0.0204\n","[3/5][260/469]\tLoss_D: 0.0863\tLoss_G: 3.8458\tD(x): 0.9524\tD(G(z)): 0.0335 / 0.0325\n","[3/5][280/469]\tLoss_D: 1.9907\tLoss_G: 0.8730\tD(x): 0.2008\tD(G(z)): 0.0137 / 0.4847\n","[3/5][300/469]\tLoss_D: 0.2260\tLoss_G: 2.9362\tD(x): 0.8619\tD(G(z)): 0.0627 / 0.0750\n","[3/5][320/469]\tLoss_D: 0.5636\tLoss_G: 2.1276\tD(x): 0.8402\tD(G(z)): 0.2738 / 0.1506\n","[3/5][340/469]\tLoss_D: 1.2364\tLoss_G: 3.8159\tD(x): 0.8996\tD(G(z)): 0.6032 / 0.0325\n","[3/5][360/469]\tLoss_D: 0.3635\tLoss_G: 3.6984\tD(x): 0.9014\tD(G(z)): 0.2020 / 0.0372\n","[3/5][380/469]\tLoss_D: 0.1724\tLoss_G: 3.7482\tD(x): 0.9454\tD(G(z)): 0.1022 / 0.0342\n","[3/5][400/469]\tLoss_D: 0.3728\tLoss_G: 2.0156\tD(x): 0.7385\tD(G(z)): 0.0286 / 0.1723\n","[3/5][420/469]\tLoss_D: 0.1875\tLoss_G: 5.2759\tD(x): 0.9815\tD(G(z)): 0.1439 / 0.0077\n","[3/5][440/469]\tLoss_D: 0.5550\tLoss_G: 2.4147\tD(x): 0.7251\tD(G(z)): 0.1599 / 0.1167\n","[3/5][460/469]\tLoss_D: 0.3303\tLoss_G: 3.3768\tD(x): 0.7814\tD(G(z)): 0.0477 / 0.0528\n","[4/5][0/469]\tLoss_D: 0.2588\tLoss_G: 4.3290\tD(x): 0.9516\tD(G(z)): 0.1762 / 0.0180\n","[4/5][20/469]\tLoss_D: 0.3605\tLoss_G: 3.0257\tD(x): 0.9473\tD(G(z)): 0.2448 / 0.0658\n","[4/5][40/469]\tLoss_D: 0.1929\tLoss_G: 2.9097\tD(x): 0.8471\tD(G(z)): 0.0139 / 0.0740\n","[4/5][60/469]\tLoss_D: 0.1052\tLoss_G: 3.3399\tD(x): 0.9365\tD(G(z)): 0.0355 / 0.0488\n","[4/5][80/469]\tLoss_D: 0.0875\tLoss_G: 4.1164\tD(x): 0.9588\tD(G(z)): 0.0420 / 0.0235\n","[4/5][100/469]\tLoss_D: 0.0549\tLoss_G: 4.0624\tD(x): 0.9680\tD(G(z)): 0.0213 / 0.0260\n","[4/5][120/469]\tLoss_D: 0.5664\tLoss_G: 9.6782\tD(x): 0.9891\tD(G(z)): 0.3813 / 0.0001\n","[4/5][140/469]\tLoss_D: 0.5782\tLoss_G: 2.2732\tD(x): 0.8172\tD(G(z)): 0.2774 / 0.1293\n","[4/5][160/469]\tLoss_D: 0.7162\tLoss_G: 4.0503\tD(x): 0.9677\tD(G(z)): 0.4352 / 0.0243\n","[4/5][180/469]\tLoss_D: 0.5347\tLoss_G: 4.6463\tD(x): 0.9511\tD(G(z)): 0.3409 / 0.0140\n","[4/5][200/469]\tLoss_D: 0.7841\tLoss_G: 2.2462\tD(x): 0.8457\tD(G(z)): 0.4102 / 0.1315\n","[4/5][220/469]\tLoss_D: 0.4378\tLoss_G: 2.3203\tD(x): 0.7956\tD(G(z)): 0.1620 / 0.1232\n","[4/5][240/469]\tLoss_D: 0.4551\tLoss_G: 2.6825\tD(x): 0.7763\tD(G(z)): 0.1380 / 0.1081\n","[4/5][260/469]\tLoss_D: 0.6022\tLoss_G: 1.4781\tD(x): 0.6045\tD(G(z)): 0.0172 / 0.3008\n","[4/5][280/469]\tLoss_D: 0.2226\tLoss_G: 3.3953\tD(x): 0.8940\tD(G(z)): 0.0917 / 0.0504\n","[4/5][300/469]\tLoss_D: 0.4697\tLoss_G: 3.8812\tD(x): 0.9508\tD(G(z)): 0.3125 / 0.0298\n","[4/5][320/469]\tLoss_D: 0.1739\tLoss_G: 3.2010\tD(x): 0.9059\tD(G(z)): 0.0622 / 0.0607\n","[4/5][340/469]\tLoss_D: 0.1799\tLoss_G: 4.0136\tD(x): 0.9249\tD(G(z)): 0.0887 / 0.0262\n","[4/5][360/469]\tLoss_D: 0.1800\tLoss_G: 3.5262\tD(x): 0.9167\tD(G(z)): 0.0826 / 0.0405\n","[4/5][380/469]\tLoss_D: 0.1289\tLoss_G: 5.0465\tD(x): 0.9828\tD(G(z)): 0.1003 / 0.0093\n","[4/5][400/469]\tLoss_D: 0.8568\tLoss_G: 0.4310\tD(x): 0.4982\tD(G(z)): 0.0383 / 0.6853\n","[4/5][420/469]\tLoss_D: 0.2431\tLoss_G: 2.5467\tD(x): 0.8584\tD(G(z)): 0.0681 / 0.1079\n","[4/5][440/469]\tLoss_D: 0.6409\tLoss_G: 2.5286\tD(x): 0.7866\tD(G(z)): 0.2927 / 0.1032\n","[4/5][460/469]\tLoss_D: 0.2507\tLoss_G: 3.5977\tD(x): 0.8427\tD(G(z)): 0.0585 / 0.0419\n"]}],"source":["# Training Loop\n","\n","# Lists to keep track of progress\n","img_list = []\n","G_losses = []\n","D_losses = []\n","iters = 0\n","\n","print(\"Starting Training Loop...\")\n","# For each epoch\n","for epoch in range(num_epochs):\n","    # For each batch in the dataloader\n","    for i, data in enumerate(dataloader, 0):\n","\n","        ############################\n","        # (1) Update D network: maximize log(D(x)) + log(1 - D(G(z)))\n","        ###########################\n","        ## Train with all-real batch\n","        netD.zero_grad()\n","        # Format batch\n","        real_cpu = data[0].to(device)\n","        b_size = real_cpu.size(0)\n","        label = torch.full((b_size,), real_label, dtype=torch.float, device=device)\n","        # Forward pass real batch through D\n","        output = netD(real_cpu).view(-1)\n","        # Calculate loss on all-real batch\n","        errD_real = criterion(output, label)\n","        # Calculate gradients for D in backward pass\n","        errD_real.backward()\n","        D_x = output.mean().item()\n","\n","        ## Train with all-fake batch\n","        # Generate batch of latent vectors\n","        noise = torch.randn(b_size, nz, 1, 1, device=device)\n","        # Generate fake image batch with G\n","        fake = netG(noise)\n","        label.fill_(fake_label)\n","        # Classify all fake batch with D\n","        output = netD(fake.detach()).view(-1)\n","        # Calculate D's loss on the all-fake batch\n","        errD_fake = criterion(output, label)\n","        # Calculate the gradients for this batch, accumulated (summed) with previous gradients\n","        errD_fake.backward()\n","        D_G_z1 = output.mean().item()\n","        # Compute error of D as sum over the fake and the real batches\n","        errD = errD_real + errD_fake\n","        # Update D\n","        optimizerD.step()\n","\n","        ############################\n","        # (2) Update G network: maximize log(D(G(z)))\n","        ###########################\n","        netG.zero_grad()\n","        label.fill_(real_label)  # fake labels are real for generator cost\n","        # Since we just updated D, perform another forward pass of all-fake batch through D\n","        output = netD(fake).view(-1)\n","        # Calculate G's loss based on this output\n","        errG = criterion(output, label)\n","        # Calculate gradients for G\n","        errG.backward()\n","        D_G_z2 = output.mean().item()\n","        # Update G\n","        optimizerG.step()\n","\n","        # Output training stats\n","        if i % 20 == 0:\n","            print('[%d/%d][%d/%d]\\tLoss_D: %.4f\\tLoss_G: %.4f\\tD(x): %.4f\\tD(G(z)): %.4f / %.4f'\n","                  % (epoch, num_epochs, i, len(dataloader),\n","                     errD.item(), errG.item(), D_x, D_G_z1, D_G_z2))\n","\n","        # Save Losses for plotting later\n","        G_losses.append(errG.item())\n","        D_losses.append(errD.item())\n","\n","        # Check how the generator is doing by saving G's output on fixed_noise\n","        if (iters % 500 == 0) or ((epoch == num_epochs-1) and (i == len(dataloader)-1)):\n","            with torch.no_grad():\n","                fake = netG(fixed_noise).detach().cpu()\n","            img_list.append(vutils.make_grid(fake, padding=2, normalize=True))\n","\n","        iters += 1"]},{"cell_type":"code","source":["plt.figure(figsize=(10,5))\n","plt.title(\"Generator and Discriminator Loss During Training\")\n","plt.plot(G_losses,label=\"G\")\n","plt.plot(D_losses,label=\"D\")\n","plt.xlabel(\"iterations\")\n","plt.ylabel(\"Loss\")\n","plt.legend()\n","plt.show()"],"metadata":{"colab":{"base_uri":"https://localhost:8080/","height":350},"id":"RkX3NlBgNoEa","executionInfo":{"status":"ok","timestamp":1678866037554,"user_tz":-60,"elapsed":801,"user":{"displayName":"Florian Gaudry","userId":"04425733722793549516"}},"outputId":"873c176b-c436-4c29-f412-2dfc676e4982"},"execution_count":null,"outputs":[{"output_type":"display_data","data":{"text/plain":["<Figure size 720x360 with 1 Axes>"],"image/png":"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\n"},"metadata":{"needs_background":"light"}}]},{"cell_type":"code","source":["fig = plt.figure(figsize=(8,8))\n","plt.axis(\"off\")\n","ims = [[plt.imshow(np.transpose(i,(1,2,0)), animated=True)] for i in img_list]\n","ani = animation.ArtistAnimation(fig, ims, interval=1000, repeat_delay=1000, blit=True)\n","\n","HTML(ani.to_jshtml())"],"metadata":{"colab":{"base_uri":"https://localhost:8080/","height":1000,"output_embedded_package_id":"1LmAn9mtIrVu5HCwEwaipkUCEKjWejYbq"},"id":"MdH8DHiqNvRf","executionInfo":{"status":"ok","timestamp":1678866071479,"user_tz":-60,"elapsed":2969,"user":{"displayName":"Florian Gaudry","userId":"04425733722793549516"}},"outputId":"d5cd4669-cadb-4714-b3e9-0decd123a546"},"execution_count":null,"outputs":[{"output_type":"display_data","data":{"text/plain":"Output hidden; open in https://colab.research.google.com to view."},"metadata":{}}]},{"cell_type":"code","source":["# Grab a batch of real images from the dataloader\n","real_batch = next(iter(dataloader))\n","\n","# Plot the real images\n","plt.figure(figsize=(15,15))\n","plt.subplot(1,2,1)\n","plt.axis(\"off\")\n","plt.title(\"Real Images\")\n","plt.imshow(np.transpose(vutils.make_grid(real_batch[0].to(device)[:64], padding=5, normalize=True).cpu(),(1,2,0)))\n","\n","# Plot the fake images from the last epoch\n","plt.subplot(1,2,2)\n","plt.axis(\"off\")\n","plt.title(\"Fake Images\")\n","plt.imshow(np.transpose(img_list[-1],(1,2,0)))\n","plt.show()"],"metadata":{"colab":{"base_uri":"https://localhost:8080/","height":421},"id":"3Lj8BDz2Nu5V","executionInfo":{"status":"ok","timestamp":1678866114002,"user_tz":-60,"elapsed":1373,"user":{"displayName":"Florian Gaudry","userId":"04425733722793549516"}},"outputId":"b37bd02e-5b9f-4cf2-a674-fc9c26933eab"},"execution_count":null,"outputs":[{"output_type":"display_data","data":{"text/plain":["<Figure size 1080x1080 with 2 Axes>"],"image/png":"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\n"},"metadata":{"needs_background":"light"}}]},{"cell_type":"markdown","metadata":{"id":"5fbSgsrE1GqC"},"source":["# Part2: Conditional GAN (cGAN)"]},{"cell_type":"markdown","metadata":{"id":"7SjXNoT7BUey"},"source":["Let's take the example of the set described in the next picture.\n","![Map to satellite picture](https://raw.githubusercontent.com/Neyri/Projet-cGAN/master/BE/img/map_streetview.png)\n","\n","We have a picture of a map (from Google Maps) and we want to create an image of what the satellite view may look like.\n","\n","As we are not only trying to generate a random picture but a mapping between a picture to another one, we can't use the standard GAN architecture. We will then use a cGAN.\n","\n","A cGAN is a supervised GAN aiming at mapping a label picture to a real one or a real picture to a label one. As you can see in the diagram below, the discriminator will take as input a pair of images and try to predict if the pair was generated or not. The generator will not only generate an image from noise but will also use an image (label or real) to generate another one (real or label).\n","![Diagram of how a cGan works](https://raw.githubusercontent.com/Neyri/Projet-cGAN/master/BE/img/cgan_map.png)\n"]},{"cell_type":"markdown","metadata":{"id":"0JRaeHfzl6cO"},"source":["### Generator\n","\n","In the cGAN architecture, the generator chosen is a U-Net.\n","![U-Net](https://raw.githubusercontent.com/Neyri/Projet-cGAN/master/BE/img/unet.png)\n","\n","A U-Net takes as input an image, and outputs another image. \n","\n","It can be divided into 2 subparts : an encoder and a decoder. \n","* The encoder takes the input image and reduces its dimension to encode the main features into a vector. \n","* The decoder takes this vector and map the features stored into an image.\n","\n","A U-Net architecture is different from a classic encoder-decoder in that every layer of the decoder takes as input the previous decoded output as well as the output vector from the encoder layers of the same level. It allows the decoder to map low frequencies information encoded during the descent as well as high frequencies from the original picture. \n","\n","![U-Net](https://www.researchgate.net/profile/Baris_Turkbey/publication/315514772/figure/fig2/AS:485824962797569@1492841105670/U-net-architecture-Each-box-corresponds-to-a-multi-channel-features-maps-The-number-of.png)"]},{"cell_type":"markdown","metadata":{"id":"xFqMOsoYwzFe"},"source":["The architecture we will implement is the following (the number in the square is the number of filters used).\n","![UNet Architecture](https://raw.githubusercontent.com/Neyri/Projet-cGAN/master/BE/img/unet_architecture.png)\n","\n","The encoder will take as input a colored picture (3 channels: RGB), it will pass through a series of convolution layers to encode the features of the picture. It will then be decoded by the decoder using transposed convolutional layers. These layers will take as input the previous decoded vector AND the encoded features of the same level. "]},{"cell_type":"markdown","metadata":{"id":"yzy7y4hmbbX3"},"source":["Now, let's create or cGAN to generate facades from a template image. For this purpose, we will use the \"Facade\" dataset available at http://cmp.felk.cvut.cz/~tylecr1/facade/.\n"]},{"cell_type":"markdown","metadata":{"id":"Q_jf9H_NDESm"},"source":["Let's first create a few classes describing the layers we will use in the U-Net."]},{"cell_type":"code","execution_count":2,"metadata":{"id":"uOKvYDyu0w8N","executionInfo":{"status":"ok","timestamp":1679064106464,"user_tz":-60,"elapsed":3955,"user":{"displayName":"Florian Gaudry","userId":"04425733722793549516"}}},"outputs":[],"source":["# Importing all the libraries needed\n","import matplotlib.pyplot as plt\n","import imageio\n","import glob\n","import random\n","import os\n","import numpy as np\n","import math\n","import itertools\n","import time\n","import datetime\n","import cv2\n","from pathlib import Path\n","from PIL import Image\n","\n","from torch.utils.data import Dataset, DataLoader\n","import torchvision.transforms as transforms\n","from torchvision.utils import save_image, make_grid\n","from torchvision import datasets\n","from torch.autograd import Variable\n","\n","import torch.nn as nn\n","import torch.nn.functional as F\n","import torch"]},{"cell_type":"code","execution_count":3,"metadata":{"id":"Zk5a6B5hILN2","executionInfo":{"status":"ok","timestamp":1679064110827,"user_tz":-60,"elapsed":401,"user":{"displayName":"Florian Gaudry","userId":"04425733722793549516"}}},"outputs":[],"source":["# code adapted from https://github.com/milesial/Pytorch-UNet/blob/master/unet/unet_parts.py\n","\n","# Input layer\n","class inconv(nn.Module):\n","    def __init__(self, in_ch, out_ch):\n","        super(inconv, self).__init__()\n","        self.conv = nn.Sequential(\n","            nn.Conv2d(in_ch, out_ch, kernel_size=4, padding=1, stride=2),\n","            nn.LeakyReLU(negative_slope=0.2, inplace=True)\n","        )\n","\n","    def forward(self, x):\n","        x = self.conv(x)\n","        return x\n","\n","# Encoder layer\n","class down(nn.Module):\n","    def __init__(self, in_ch, out_ch):\n","        super(down, self).__init__()\n","        self.conv = nn.Sequential(\n","            nn.Conv2d(in_ch, out_ch, kernel_size=4, padding=1, stride=2),\n","            nn.BatchNorm2d(out_ch),\n","            nn.LeakyReLU(negative_slope=0.2, inplace=True)\n","        )\n","\n","    def forward(self, x):\n","        x = self.conv(x)\n","        return x\n","\n","# Decoder layer\n","class up(nn.Module):\n","    def __init__(self, in_ch, out_ch, dropout=False):\n","        super(up, self).__init__()\n","        if dropout :\n","            self.conv = nn.Sequential(\n","                nn.ConvTranspose2d(in_ch, out_ch, kernel_size=4, padding=1, stride=2),\n","                nn.BatchNorm2d(out_ch),\n","                nn.Dropout(0.5, inplace=True),\n","                nn.ReLU(inplace=True)\n","            )\n","        else:\n","            self.conv = nn.Sequential(\n","                nn.ConvTranspose2d(in_ch, out_ch, kernel_size=4, padding=1, stride=2),\n","                nn.BatchNorm2d(out_ch),\n","                nn.ReLU(inplace=True)\n","            )\n","\n","    def forward(self, x1, x2):\n","        x1 = self.conv(x1)\n","        x = torch.cat([x1, x2], dim=1)\n","        return x\n","\n","# Output layer\n","class outconv(nn.Module):\n","    def __init__(self, in_ch, out_ch):\n","        super(outconv, self).__init__()\n","        self.conv = nn.Sequential(\n","              nn.ConvTranspose2d(in_ch, out_ch, kernel_size=4, padding=1, stride=2),\n","              nn.Tanh()\n","        )\n","\n","    def forward(self, x):\n","        x = self.conv(x)\n","        return x"]},{"cell_type":"markdown","metadata":{"id":"1rZ5Qz1mBUe8"},"source":["Now let's create the U-Net using the helper classes defined previously."]},{"cell_type":"code","execution_count":4,"metadata":{"id":"4Tbp_535EVPW","executionInfo":{"status":"ok","timestamp":1679064113799,"user_tz":-60,"elapsed":4,"user":{"displayName":"Florian Gaudry","userId":"04425733722793549516"}}},"outputs":[],"source":["class U_Net(nn.Module):\n","    ''' \n","    Ck denotes a Convolution-BatchNorm-ReLU layer with k filters.\n","    CDk denotes a Convolution-BatchNorm-Dropout-ReLU layer with a dropout rate of 50%\n","    Encoder:\n","      C64   - C128   - C256   - C512  - C512  - C512 - C512 - C512\n","    Decoder:\n","      CD512 - CD1024 - CD1024 - C1024 - C1024 - C512 - C256 - C128\n","    '''\n","    def __init__(self, n_channels, n_classes):\n","        super(U_Net, self).__init__()\n","        # Encoder\n","        self.inc = inconv(n_channels, 64) # 64 filters\n","        # TO DO :\n","        # Create the 7 encoder layers called \"down1\" to \"down7\" following this sequence\n","        # C64   - C128   - C256   - C512  - C512  - C512 - C512 - C512\n","        # The first one has already been implemented\n","        self.down1 = down(64,128)\n","        self.down2 = down(128,256)\n","        self.down3 = down(256,512)\n","        self.down4 = down(512,512)\n","        self.down5 = down(512,512)\n","        self.down6 = down(512,512)\n","        self.down7 = down(512,512)\n","        \n","        \n","        # Decoder\n","        # TO DO :\n","        # Create the 7 decoder layers called up1 to up7 following this sequence :\n","        # CD512 - CD1024 - CD1024 - C1024 - C1024 - C512 - C256 - C128\n","        # The last layer has already been defined\n","        self.up7 = up(512,512, dropout=True)\n","        self.up6 = up(1024,512, dropout=True)\n","        self.up5 = up(1024,512, dropout=True)\n","        self.up4 = up(1024,512)\n","        self.up3 = up(1024,256)\n","        self.up2 = up(512,128)\n","        self.up1 = up(256,64)\n","        \n","        \n","        self.outc = outconv(128, n_classes) # 128 filters\n","\n","    def forward(self, x):\n","        x1 = self.inc(x)\n","        x2 = self.down1(x1)\n","        x3 = self.down2(x2)\n","        x4 = self.down3(x3)\n","        x5 = self.down4(x4)\n","        x6 = self.down5(x5)\n","        x7 = self.down6(x6)\n","        x8 = self.down7(x7)\n","        # At this stage x8 is our encoded vector, we will now decode it\n","        x = self.up7(x8, x7)\n","        x = self.up6(x, x6)\n","        x = self.up5(x, x5)\n","        x = self.up4(x, x4)\n","        x = self.up3(x, x3)\n","        x = self.up2(x, x2)\n","        x = self.up1(x, x1)\n","        x = self.outc(x)\n","        return x"]},{"cell_type":"code","execution_count":9,"metadata":{"colab":{"base_uri":"https://localhost:8080/"},"id":"1hmcejTWJSYY","executionInfo":{"status":"ok","timestamp":1679064183351,"user_tz":-60,"elapsed":5534,"user":{"displayName":"Florian Gaudry","userId":"04425733722793549516"}},"outputId":"e4fe0b96-d743-4a3b-db69-4a7d17e2b21c"},"outputs":[{"output_type":"execute_result","data":{"text/plain":["U_Net(\n","  (inc): inconv(\n","    (conv): Sequential(\n","      (0): Conv2d(3, 64, kernel_size=(4, 4), stride=(2, 2), padding=(1, 1))\n","      (1): LeakyReLU(negative_slope=0.2, inplace=True)\n","    )\n","  )\n","  (down1): down(\n","    (conv): Sequential(\n","      (0): Conv2d(64, 128, kernel_size=(4, 4), stride=(2, 2), padding=(1, 1))\n","      (1): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n","      (2): LeakyReLU(negative_slope=0.2, inplace=True)\n","    )\n","  )\n","  (down2): down(\n","    (conv): Sequential(\n","      (0): Conv2d(128, 256, kernel_size=(4, 4), stride=(2, 2), padding=(1, 1))\n","      (1): BatchNorm2d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n","      (2): LeakyReLU(negative_slope=0.2, inplace=True)\n","    )\n","  )\n","  (down3): down(\n","    (conv): Sequential(\n","      (0): Conv2d(256, 512, kernel_size=(4, 4), stride=(2, 2), padding=(1, 1))\n","      (1): BatchNorm2d(512, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n","      (2): LeakyReLU(negative_slope=0.2, inplace=True)\n","    )\n","  )\n","  (down4): down(\n","    (conv): Sequential(\n","      (0): Conv2d(512, 512, kernel_size=(4, 4), stride=(2, 2), padding=(1, 1))\n","      (1): BatchNorm2d(512, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n","      (2): LeakyReLU(negative_slope=0.2, inplace=True)\n","    )\n","  )\n","  (down5): down(\n","    (conv): Sequential(\n","      (0): Conv2d(512, 512, kernel_size=(4, 4), stride=(2, 2), padding=(1, 1))\n","      (1): BatchNorm2d(512, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n","      (2): LeakyReLU(negative_slope=0.2, inplace=True)\n","    )\n","  )\n","  (down6): down(\n","    (conv): Sequential(\n","      (0): Conv2d(512, 512, kernel_size=(4, 4), stride=(2, 2), padding=(1, 1))\n","      (1): BatchNorm2d(512, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n","      (2): LeakyReLU(negative_slope=0.2, inplace=True)\n","    )\n","  )\n","  (down7): down(\n","    (conv): Sequential(\n","      (0): Conv2d(512, 512, kernel_size=(4, 4), stride=(2, 2), padding=(1, 1))\n","      (1): BatchNorm2d(512, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n","      (2): LeakyReLU(negative_slope=0.2, inplace=True)\n","    )\n","  )\n","  (up7): up(\n","    (conv): Sequential(\n","      (0): ConvTranspose2d(512, 512, kernel_size=(4, 4), stride=(2, 2), padding=(1, 1))\n","      (1): BatchNorm2d(512, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n","      (2): Dropout(p=0.5, inplace=True)\n","      (3): ReLU(inplace=True)\n","    )\n","  )\n","  (up6): up(\n","    (conv): Sequential(\n","      (0): ConvTranspose2d(1024, 512, kernel_size=(4, 4), stride=(2, 2), padding=(1, 1))\n","      (1): BatchNorm2d(512, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n","      (2): Dropout(p=0.5, inplace=True)\n","      (3): ReLU(inplace=True)\n","    )\n","  )\n","  (up5): up(\n","    (conv): Sequential(\n","      (0): ConvTranspose2d(1024, 512, kernel_size=(4, 4), stride=(2, 2), padding=(1, 1))\n","      (1): BatchNorm2d(512, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n","      (2): Dropout(p=0.5, inplace=True)\n","      (3): ReLU(inplace=True)\n","    )\n","  )\n","  (up4): up(\n","    (conv): Sequential(\n","      (0): ConvTranspose2d(1024, 512, kernel_size=(4, 4), stride=(2, 2), padding=(1, 1))\n","      (1): BatchNorm2d(512, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n","      (2): ReLU(inplace=True)\n","    )\n","  )\n","  (up3): up(\n","    (conv): Sequential(\n","      (0): ConvTranspose2d(1024, 256, kernel_size=(4, 4), stride=(2, 2), padding=(1, 1))\n","      (1): BatchNorm2d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n","      (2): ReLU(inplace=True)\n","    )\n","  )\n","  (up2): up(\n","    (conv): Sequential(\n","      (0): ConvTranspose2d(512, 128, kernel_size=(4, 4), stride=(2, 2), padding=(1, 1))\n","      (1): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n","      (2): ReLU(inplace=True)\n","    )\n","  )\n","  (up1): up(\n","    (conv): Sequential(\n","      (0): ConvTranspose2d(256, 64, kernel_size=(4, 4), stride=(2, 2), padding=(1, 1))\n","      (1): BatchNorm2d(64, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n","      (2): ReLU(inplace=True)\n","    )\n","  )\n","  (outc): outconv(\n","    (conv): Sequential(\n","      (0): ConvTranspose2d(128, 3, kernel_size=(4, 4), stride=(2, 2), padding=(1, 1))\n","      (1): Tanh()\n","    )\n","  )\n",")"]},"metadata":{},"execution_count":9}],"source":["# We take images that have 3 channels (RGB) as input and output an image that also have 3 channels (RGB)\n","generator=U_Net(3,3).to(device)\n","# Check that the architecture is as expected\n","generator"]},{"cell_type":"markdown","metadata":{"id":"xIXFtHzcBUfO"},"source":["You should now have a working U-Net."]},{"cell_type":"markdown","metadata":{"id":"RqD1katYBUfP"},"source":["<font color='red'>**Question 1**</font>                                                                  \n","Knowing the input and output images will be 256x256, what will be the dimension of the encoded vector x8  ?\n","\n","Our kernel size is 4x4 and the stride is 2. With a padding of 1, it means that the dimension of our input is divided by 2 at each layer.\n","\n","With the inconv layer and the 7 down layers, our input dimension are divided by 2^8.\n","\n","So if the input image is 256x256, the dimension of the encoded vector x8 = [1, 1, 512]\n","\n","<font color='red'>**Question 2**</font>                                                                  \n","As you can see, U-net has an encoder-decoder architecture with skip connections. Explain why it works better than a traditional encoder-decoder.\n","\n","As we are going deeper with downs layer, we extract the main features from the input images but we lose the spatial information. By implementing the skip connections, we allow our decoder to get those spatial information to create a better output."]},{"cell_type":"markdown","metadata":{"id":"cchTp3thBUfR"},"source":["### Discriminator\n","\n","In the cGAN architecture, the chosen discriminator is a Patch GAN. It is a convolutional discriminator which enables to produce a map of the input pictures where each pixel represents a patch of size NxN of the input.\n","\n","![patch GAN](https://raw.githubusercontent.com/Neyri/Projet-cGAN/master/BE/img/patchGAN.png)\n","\n","The size N is given by the depth of the net. According to this table :\n","\n","| Number of layers | N |\n","| ---- | ---- |\n","| 1 | 16 |\n","| 2 | 34 |\n","| 3 | 70 |\n","| 4 | 142 |\n","| 5 | 286 |\n","| 6 | 574 |\n","\n","The number of layers actually means the number of layers with `kernel=(4,4)`, `padding=(1,1)` and `stride=(2,2)`. These layers are followed by 2 layers with `kernel=(4,4)`, `padding=(1,1)` and `stride=(1,1)`.\n","In our case we are going to create a 70x70 PatchGAN."]},{"cell_type":"markdown","metadata":{"id":"ge6I7M0aBUfT"},"source":["Let's first create a few helping classes."]},{"cell_type":"code","execution_count":10,"metadata":{"id":"RYqomFO8BUfV","executionInfo":{"status":"ok","timestamp":1679064190100,"user_tz":-60,"elapsed":381,"user":{"displayName":"Florian Gaudry","userId":"04425733722793549516"}}},"outputs":[],"source":["class conv_block(nn.Module):\n","    def __init__(self, in_ch, out_ch, use_batchnorm=True, stride=2):\n","        super(conv_block, self).__init__()\n","        if use_batchnorm:\n","            self.conv = nn.Sequential(\n","                nn.Conv2d(in_ch, out_ch, kernel_size=4, padding=1, stride=stride),\n","                nn.BatchNorm2d(out_ch),\n","                nn.LeakyReLU(negative_slope=0.2, inplace=True)\n","            )\n","        else:\n","            self.conv = nn.Sequential(\n","                nn.Conv2d(in_ch, out_ch, kernel_size=4, padding=1, stride=stride),\n","                nn.LeakyReLU(negative_slope=0.2, inplace=True)\n","            )\n","\n","    def forward(self, x):\n","        x = self.conv(x)\n","        return x\n","    \n","\n","class out_block(nn.Module):\n","    def __init__(self, in_ch, out_ch):\n","        super(out_block, self).__init__()\n","        self.conv = nn.Sequential(\n","            nn.Conv2d(in_ch, 1, kernel_size=4, padding=1, stride=1),\n","            nn.Sigmoid()\n","        )\n","\n","    def forward(self, x):\n","        x = self.conv(x)\n","        return x"]},{"cell_type":"markdown","metadata":{"id":"5m4Dnup4BUfc"},"source":["Now let's create the Patch GAN discriminator.\n","As we want a 70x70 Patch GAN, the architecture will be as follows :\n","```\n","1. C64  - K4, P1, S2\n","2. C128 - K4, P1, S2\n","3. C256 - K4, P1, S2\n","4. C512 - K4, P1, S1\n","5. C1   - K4, P1, S1 (output)\n","```\n","Where Ck denotes a convolution block with k filters, Kk a kernel of size k, Pk is the padding size and Sk the stride applied.\n","*Note :* For the first layer, we do not use batchnorm."]},{"cell_type":"markdown","metadata":{"id":"AH6u5a-PBUfg"},"source":["<font color='red'>**Question 3**</font>                                                                  \n","Knowing input images will be 256x256 with 3 channels each, how many parameters are there to learn ?\n","\n","For each layers, the number of parameters to learn is : size of kernel filter * number of entry channels * number of filter) + number of filter\n","\n","conv1 : (4 * 4 * 3 * 64) + 64 = 3 136\n","\n","conv2 : (4 * 4 * 64 * 128) + 128 = 131 200\n","\n","conv3 : (4 * 4 * 128 * 256) + 256 = 524 544\n","\n","conv4 : (4 * 4 * 256 * 512) + 512 = 2 097 664\n","\n","out : (4 * 4 * 512 * 1) + 1 = 8 193\n","\n","So the total of parameters to learn is : 3136 + 131200 + 524544 + 2097664 + 8193 = 2 764 737"]},{"cell_type":"code","execution_count":11,"metadata":{"id":"g_9LxNhGBUfi","executionInfo":{"status":"ok","timestamp":1679064194778,"user_tz":-60,"elapsed":259,"user":{"displayName":"Florian Gaudry","userId":"04425733722793549516"}}},"outputs":[],"source":["class PatchGAN(nn.Module):\n","    def __init__(self, n_channels, n_classes):\n","        super(PatchGAN, self).__init__()\n","        # TODO :\n","        # create the 4 first layers named conv1 to conv4\n","        self.conv1 = conv_block(n_channels, 64, use_batchnorm=False)\n","        self.conv2 = conv_block(64, 128)\n","        self.conv3 = conv_block(128, 256)\n","        self.conv4 = conv_block(256, 512,stride=1)\n","        # output layer\n","        self.out = out_block(512, n_classes)\n","        \n","    def forward(self, x1, x2):\n","        x = torch.cat([x2, x1], dim=1)\n","        x = self.conv1(x)\n","        x = self.conv2(x)\n","        x = self.conv3(x)\n","        x = self.conv4(x)\n","        x = self.out(x)\n","        return x"]},{"cell_type":"code","execution_count":12,"metadata":{"colab":{"base_uri":"https://localhost:8080/"},"id":"W_sevZRnBUfn","executionInfo":{"status":"ok","timestamp":1679064198494,"user_tz":-60,"elapsed":236,"user":{"displayName":"Florian Gaudry","userId":"04425733722793549516"}},"outputId":"45189aea-d638-46de-cb36-e596000cfe50"},"outputs":[{"output_type":"execute_result","data":{"text/plain":["PatchGAN(\n","  (conv1): conv_block(\n","    (conv): Sequential(\n","      (0): Conv2d(6, 64, kernel_size=(4, 4), stride=(2, 2), padding=(1, 1))\n","      (1): LeakyReLU(negative_slope=0.2, inplace=True)\n","    )\n","  )\n","  (conv2): conv_block(\n","    (conv): Sequential(\n","      (0): Conv2d(64, 128, kernel_size=(4, 4), stride=(2, 2), padding=(1, 1))\n","      (1): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n","      (2): LeakyReLU(negative_slope=0.2, inplace=True)\n","    )\n","  )\n","  (conv3): conv_block(\n","    (conv): Sequential(\n","      (0): Conv2d(128, 256, kernel_size=(4, 4), stride=(2, 2), padding=(1, 1))\n","      (1): BatchNorm2d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n","      (2): LeakyReLU(negative_slope=0.2, inplace=True)\n","    )\n","  )\n","  (conv4): conv_block(\n","    (conv): Sequential(\n","      (0): Conv2d(256, 512, kernel_size=(4, 4), stride=(1, 1), padding=(1, 1))\n","      (1): BatchNorm2d(512, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n","      (2): LeakyReLU(negative_slope=0.2, inplace=True)\n","    )\n","  )\n","  (out): out_block(\n","    (conv): Sequential(\n","      (0): Conv2d(512, 1, kernel_size=(4, 4), stride=(1, 1), padding=(1, 1))\n","      (1): Sigmoid()\n","    )\n","  )\n",")"]},"metadata":{},"execution_count":12}],"source":["# We have 6 input channels as we concatenate 2 images (with 3 channels each)\n","discriminator = PatchGAN(6,1).to(device)\n","discriminator"]},{"cell_type":"markdown","metadata":{"id":"v_QubOycBUfv"},"source":["You should now have a working discriminator."]},{"cell_type":"markdown","metadata":{"id":"DiI2CByRBUfz"},"source":["### Loss functions\n","\n","As we have seen in the choice of the various architectures for this GAN, the issue is to map both low and high frequencies.\n","To tackle this problem, this GAN rely on the architecture to map the high frequencies (U-Net + PatchGAN) and the loss function to learn low frequencies features. The global loss function will indeed be made of 2 parts :\n","* the first part to map hight frequencies, will try to optimize the mean squared error of the GAN.\n","* the second part to map low frequencies, will minimize the $\\mathcal{L}_1$ norm of the generated picture.\n","\n","So the loss can be defined as $$ G^* = arg\\ \\underset{G}{min}\\ \\underset{D}{max}\\ \\mathcal{L}_{cGAN}(G,D) + \\lambda \\mathcal{L}_1(G)$$"]},{"cell_type":"code","execution_count":13,"metadata":{"id":"k4G_xewPBUf4","executionInfo":{"status":"ok","timestamp":1679064202454,"user_tz":-60,"elapsed":231,"user":{"displayName":"Florian Gaudry","userId":"04425733722793549516"}}},"outputs":[],"source":["# Loss functions\n","criterion_GAN = torch.nn.MSELoss()\n","criterion_pixelwise = torch.nn.L1Loss()\n","\n","# Loss weight of L1 pixel-wise loss between translated image and real image\n","lambda_pixel = 100"]},{"cell_type":"markdown","metadata":{"id":"c12q2NwkBUf7"},"source":["### Training and evaluating models "]},{"cell_type":"code","execution_count":14,"metadata":{"id":"vGKjO0UMBUf9","executionInfo":{"status":"ok","timestamp":1679064205191,"user_tz":-60,"elapsed":241,"user":{"displayName":"Florian Gaudry","userId":"04425733722793549516"}}},"outputs":[],"source":["# parameters\n","epoch = 0 #  epoch to start training from\n","n_epoch = 200  #  number of epochs of training\n","batch_size =10  #  size of the batches\n","lr = 0.0002 #  adam: learning rate\n","b1 =0.5  #  adam: decay of first order momentum of gradient\n","b2 = 0.999  # adam: decay of first order momentum of gradient\n","decay_epoch = 100  # epoch from which to start lr decay\n","img_height = 256  # size of image height\n","img_width = 256  # size of image width\n","channels = 3  # number of image channels\n","sample_interval = 500 # interval between sampling of images from generators\n","checkpoint_interval = -1 # interval between model checkpoints\n","cuda = True if torch.cuda.is_available() else False # do you have cuda ?"]},{"cell_type":"markdown","metadata":{"id":"PhPkU7BDYooV"},"source":["Download the dataset. \n"]},{"cell_type":"code","execution_count":15,"metadata":{"id":"8wyPjAxPYsNF","colab":{"base_uri":"https://localhost:8080/"},"executionInfo":{"status":"ok","timestamp":1679064222773,"user_tz":-60,"elapsed":9547,"user":{"displayName":"Florian Gaudry","userId":"04425733722793549516"}},"outputId":"63a09f6b-27ca-4568-8935-bcbfa7aa5811"},"outputs":[{"output_type":"stream","name":"stderr","text":["CMP_facade_DB_base.zip: 34.8MB [00:05, 7.30MB/s]                            \n","CMP_facade_DB_extended.zip: 19.4MB [00:03, 6.15MB/s]                            \n"]}],"source":["import urllib.request\n","from tqdm import tqdm\n","import os\n","import zipfile\n","\n","def download_hook(t):\n","    \"\"\"Wraps tqdm instance.\n","    Don't forget to close() or __exit__()\n","    the tqdm instance once you're done with it (easiest using `with` syntax).\n","    Example\n","    -------\n","    >>> with tqdm(...) as t:\n","    ...     reporthook = my_hook(t)\n","    ...     urllib.request.urlretrieve(..., reporthook=reporthook)\n","    \"\"\"\n","    last_b = [0]\n","\n","    def update_to(b=1, bsize=1, tsize=None):\n","        \"\"\"\n","        b  : int, optional\n","            Number of blocks transferred so far [default: 1].\n","        bsize  : int, optional\n","            Size of each block (in tqdm units) [default: 1].\n","        tsize  : int, optional\n","            Total size (in tqdm units). If [default: None] remains unchanged.\n","        \"\"\"\n","        if tsize is not None:\n","            t.total = tsize\n","        t.update((b - last_b[0]) * bsize)\n","        last_b[0] = b\n","\n","    return update_to\n","\n","def download(url, save_dir):\n","    filename = url.split('/')[-1]\n","    with tqdm(unit = 'B', unit_scale = True, unit_divisor = 1024, miniters = 1, desc = filename) as t:\n","        urllib.request.urlretrieve(url, filename = os.path.join(save_dir, filename), reporthook = download_hook(t), data = None)\n","\n","if __name__ == '__main__':\n","    # Download ground truth\n","    if not os.path.exists(\"CMP_facade_DB_base.zip\"):\n","        download(\"http://cmp.felk.cvut.cz/~tylecr1/facade/CMP_facade_DB_base.zip\", \"./\")\n","    # Extract in the correct folder\n","    with zipfile.ZipFile(\"CMP_facade_DB_base.zip\", 'r') as zip_ref:\n","        zip_ref.extractall(\"./facades\")\n","        os.rename(\"./facades/base\", \"./facades/train\")\n","\n","    # Download ground truth\n","    if not os.path.exists(\"CMP_facade_DB_extended.zip\"):\n","        download(\"http://cmp.felk.cvut.cz/~tylecr1/facade/CMP_facade_DB_extended.zip\", \"./\")\n","    # Extract in the correct folder\n","    with zipfile.ZipFile(\"CMP_facade_DB_extended.zip\", 'r') as zip_ref:\n","        zip_ref.extractall(\"./facades\")\n","        os.rename(\"./facades/extended\", \"./facades/val\")\n"]},{"cell_type":"markdown","metadata":{"id":"6DHT9c0_BUgA"},"source":["Configure the dataloader"]},{"cell_type":"code","execution_count":16,"metadata":{"id":"rxi_QIpgBUgB","executionInfo":{"status":"ok","timestamp":1679064227339,"user_tz":-60,"elapsed":240,"user":{"displayName":"Florian Gaudry","userId":"04425733722793549516"}},"colab":{"base_uri":"https://localhost:8080/"},"outputId":"0d63d632-7a3b-42a1-fda8-1994af6d340a"},"outputs":[{"output_type":"stream","name":"stderr","text":["/usr/local/lib/python3.9/dist-packages/torchvision/transforms/transforms.py:329: UserWarning: Argument 'interpolation' of type int is deprecated since 0.13 and will be removed in 0.15. Please use InterpolationMode enum.\n","  warnings.warn(\n"]}],"source":["class ImageDataset(Dataset):\n","    def __init__(self, root, transforms_=None, mode='train'):\n","        self.transform = transforms.Compose(transforms_)\n","\n","        self.files_img = sorted(glob.glob(os.path.join(root, mode) + '/*.jpg'))\n","        if mode == 'val':\n","            self.files_img.extend(\n","                sorted(glob.glob(os.path.join(root, 'val') + '/*.jpg')))\n","\n","        self.files_mask = sorted(glob.glob(os.path.join(root, mode) + '/*.png'))\n","        if mode == 'val':\n","            self.files_mask.extend(\n","                sorted(glob.glob(os.path.join(root, 'val') + '/*.png')))\n","            \n","        assert len(self.files_img) == len(self.files_mask)\n","\n","    def __getitem__(self, index):\n","\n","        img = Image.open(self.files_img[index % len(self.files_img)])\n","        mask = Image.open(self.files_mask[index % len(self.files_img)])\n","        mask = mask.convert('RGB')\n","\n","        img = self.transform(img)\n","        mask = self.transform(mask)\n","\n","        return img, mask\n","\n","    def __len__(self):\n","        return len(self.files_img)\n","    \n","# Configure dataloaders\n","transforms_ = [transforms.Resize((img_height, img_width), Image.BICUBIC),\n","               transforms.ToTensor()]  # transforms.Normalize((0.5,0.5,0.5), (0.5,0.5,0.5))\n","\n","dataloader = DataLoader(ImageDataset(\"facades\", transforms_=transforms_),\n","                        batch_size=16, shuffle=True)\n","\n","val_dataloader = DataLoader(ImageDataset(\"facades\", transforms_=transforms_, mode='val'),\n","                            batch_size=8, shuffle=False)\n","\n","# Tensor type\n","Tensor = torch.cuda.FloatTensor if cuda else torch.FloatTensor"]},{"cell_type":"markdown","metadata":{"id":"Okb3LU76BUgG"},"source":["Check the loading works and a few helper functions"]},{"cell_type":"code","execution_count":17,"metadata":{"id":"xuxq4TZRBUgJ","executionInfo":{"status":"ok","timestamp":1679064231138,"user_tz":-60,"elapsed":1,"user":{"displayName":"Florian Gaudry","userId":"04425733722793549516"}}},"outputs":[],"source":["def plot2x2Array(image, mask):\n","    f, axarr = plt.subplots(1, 2)\n","    axarr[0].imshow(image)\n","    axarr[1].imshow(mask)\n","\n","    axarr[0].set_title('Image')\n","    axarr[1].set_title('Mask')\n","\n","\n","def reverse_transform(image):\n","    image = image.numpy().transpose((1, 2, 0))\n","    image = np.clip(image, 0, 1)\n","    image = (image * 255).astype(np.uint8)\n","\n","    return image\n","\n","def plot2x3Array(image, mask,predict):\n","    f, axarr = plt.subplots(1,3,figsize=(15,15))\n","    axarr[0].imshow(image)\n","    axarr[1].imshow(mask)\n","    axarr[2].imshow(predict)\n","    axarr[0].set_title('input')\n","    axarr[1].set_title('real')\n","    axarr[2].set_title('fake')"]},{"cell_type":"code","execution_count":18,"metadata":{"colab":{"base_uri":"https://localhost:8080/","height":216},"id":"m2NxLrQEBUgM","executionInfo":{"status":"ok","timestamp":1679064234751,"user_tz":-60,"elapsed":1471,"user":{"displayName":"Florian Gaudry","userId":"04425733722793549516"}},"outputId":"6f80a9b4-169f-4aec-a51d-dbf859ce1577"},"outputs":[{"output_type":"display_data","data":{"text/plain":["<Figure size 432x288 with 2 Axes>"],"image/png":"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\n"},"metadata":{"needs_background":"light"}}],"source":["image, mask = next(iter(dataloader))\n","image = reverse_transform(image[0])\n","mask = reverse_transform(mask[0])\n","plot2x2Array(image, mask)"]},{"cell_type":"markdown","metadata":{"id":"zAvaxAbxBUgQ"},"source":["Initialize our GAN"]},{"cell_type":"code","execution_count":19,"metadata":{"id":"dVgF3qfDBUgR","executionInfo":{"status":"ok","timestamp":1679064241675,"user_tz":-60,"elapsed":245,"user":{"displayName":"Florian Gaudry","userId":"04425733722793549516"}}},"outputs":[],"source":["# Calculate output of image discriminator (PatchGAN)\n","patch = (1, img_height//2**3-2, img_width//2**3-2)\n","\n","if cuda:\n","    generator = generator.cuda()\n","    discriminator = discriminator.cuda()\n","    criterion_GAN.cuda()\n","    criterion_pixelwise.cuda()\n","    \n","# Optimizers\n","optimizer_G = torch.optim.Adam(generator.parameters(), lr=lr, betas=(b1, b2))\n","optimizer_D = torch.optim.Adam(discriminator.parameters(), lr=lr, betas=(b1, b2))"]},{"cell_type":"markdown","metadata":{"id":"rN3cbiWaBUgf"},"source":["Start training"]},{"cell_type":"code","execution_count":20,"metadata":{"id":"msmQQUX-BUgh","executionInfo":{"status":"ok","timestamp":1679064245840,"user_tz":-60,"elapsed":279,"user":{"displayName":"Florian Gaudry","userId":"04425733722793549516"}}},"outputs":[],"source":["def save_model(epoch):\n","    # save your work\n","    torch.save({\n","                'epoch': epoch,\n","                'model_state_dict': generator.state_dict(),\n","                'optimizer_state_dict': optimizer_G.state_dict(),\n","                'loss': loss_G,\n","                }, 'generator_'+str(epoch)+'.pth')\n","    torch.save({\n","                'epoch': epoch,\n","                'model_state_dict': discriminator.state_dict(),\n","                'optimizer_state_dict': optimizer_D.state_dict(),\n","                'loss': loss_D,\n","                }, 'discriminator_'+str(epoch)+'.pth')\n","    \n","def weights_init_normal(m):\n","  classname = m.__class__.__name__\n","  if classname.find('Conv') != -1:\n","      torch.nn.init.normal_(m.weight.data, 0.0, 0.02)\n","  elif classname.find('BatchNorm2d') != -1:\n","      torch.nn.init.normal_(m.weight.data, 1.0, 0.02)\n","      torch.nn.init.constant_(m.bias.data, 0.0)"]},{"cell_type":"markdown","metadata":{"id":"6UXrZLLNBUgq"},"source":["<font color='red'>Complete the loss function </font>  in the following training code and train your network:  "]},{"cell_type":"code","execution_count":37,"metadata":{"colab":{"base_uri":"https://localhost:8080/"},"id":"7NUuGcQ0SiJw","executionInfo":{"status":"ok","timestamp":1679068148590,"user_tz":-60,"elapsed":3590319,"user":{"displayName":"Florian Gaudry","userId":"04425733722793549516"}},"outputId":"5292e2cd-3bd9-48fb-97f7-0c9c5baa9092"},"outputs":[{"output_type":"stream","name":"stdout","text":["Epoch [    1/  202] | d_loss: 0.3035 | g_loss: 57.4566\n","Saving model...\n","Epoch [    2/  202] | d_loss: 0.0716 | g_loss: 21.5139\n","Epoch [    3/  202] | d_loss: 0.1238 | g_loss: 18.9235\n","Epoch [    4/  202] | d_loss: 0.1244 | g_loss: 18.6385\n","Epoch [    5/  202] | d_loss: 0.0611 | g_loss: 17.8513\n","Epoch [    6/  202] | d_loss: 0.0275 | g_loss: 16.5954\n","Epoch [    7/  202] | d_loss: 0.0168 | g_loss: 16.7388\n","Epoch [    8/  202] | d_loss: 0.0041 | g_loss: 16.2255\n","Epoch [    9/  202] | d_loss: 0.0082 | g_loss: 14.8197\n","Epoch [   10/  202] | d_loss: 0.0038 | g_loss: 15.7094\n","Epoch [   11/  202] | d_loss: 0.0146 | g_loss: 14.3846\n","Epoch [   12/  202] | d_loss: 0.0096 | g_loss: 14.2333\n","Epoch [   13/  202] | d_loss: 0.4831 | g_loss: 14.9921\n","Epoch [   14/  202] | d_loss: 0.0011 | g_loss: 13.3179\n","Epoch [   15/  202] | d_loss: 0.0007 | g_loss: 13.4762\n","Epoch [   16/  202] | d_loss: 0.0007 | g_loss: 12.2438\n","Epoch [   17/  202] | d_loss: 0.0002 | g_loss: 12.9566\n","Epoch [   18/  202] | d_loss: 0.0004 | g_loss: 13.6038\n","Epoch [   19/  202] | d_loss: 0.0004 | g_loss: 13.2582\n","Epoch [   20/  202] | d_loss: 0.0006 | g_loss: 12.4559\n","Epoch [   21/  202] | d_loss: 0.0007 | g_loss: 11.1595\n","Epoch [   22/  202] | d_loss: 0.0006 | g_loss: 11.5520\n","Epoch [   23/  202] | d_loss: 0.0004 | g_loss: 12.0203\n","Epoch [   24/  202] | d_loss: 0.0005 | g_loss: 10.9980\n","Epoch [   25/  202] | d_loss: 0.0005 | g_loss: 12.6401\n","Epoch [   26/  202] | d_loss: 0.0004 | g_loss: 12.5079\n","Epoch [   27/  202] | d_loss: 0.0003 | g_loss: 11.9361\n","Epoch [   28/  202] | d_loss: 0.0005 | g_loss: 10.5746\n","Epoch [   29/  202] | d_loss: 0.0011 | g_loss: 10.3349\n","Epoch [   30/  202] | d_loss: 0.0006 | g_loss: 11.1491\n","Epoch [   31/  202] | d_loss: 0.0004 | g_loss: 11.3383\n","Epoch [   32/  202] | d_loss: 0.0005 | g_loss: 10.2232\n","Epoch [   33/  202] | d_loss: 0.0007 | g_loss: 9.5892\n","Epoch [   34/  202] | d_loss: 0.0008 | g_loss: 11.1652\n","Epoch [   35/  202] | d_loss: 0.0003 | g_loss: 9.6886\n","Epoch [   36/  202] | d_loss: 0.0004 | g_loss: 10.3388\n","Epoch [   37/  202] | d_loss: 0.0003 | g_loss: 9.8882\n","Epoch [   38/  202] | d_loss: 0.0008 | g_loss: 9.7963\n","Epoch [   39/  202] | d_loss: 0.0007 | g_loss: 9.6773\n","Epoch [   40/  202] | d_loss: 0.0003 | g_loss: 9.3515\n","Epoch [   41/  202] | d_loss: 0.0001 | g_loss: 9.7615\n","Epoch [   42/  202] | d_loss: 0.0001 | g_loss: 9.5624\n","Epoch [   43/  202] | d_loss: 0.0001 | g_loss: 9.7710\n","Epoch [   44/  202] | d_loss: 0.0002 | g_loss: 9.1661\n","Epoch [   45/  202] | d_loss: 0.0007 | g_loss: 9.1755\n","Epoch [   46/  202] | d_loss: 0.0015 | g_loss: 10.5312\n","Epoch [   47/  202] | d_loss: 0.4572 | g_loss: 10.2165\n","Epoch [   48/  202] | d_loss: 0.3254 | g_loss: 8.2943\n","Epoch [   49/  202] | d_loss: 0.2732 | g_loss: 8.5910\n","Epoch [   50/  202] | d_loss: 0.2236 | g_loss: 8.3526\n","Epoch [   51/  202] | d_loss: 0.1959 | g_loss: 8.2557\n","Epoch [   52/  202] | d_loss: 0.1705 | g_loss: 8.5524\n","Epoch [   53/  202] | d_loss: 0.2730 | g_loss: 8.9803\n","Epoch [   54/  202] | d_loss: 0.0190 | g_loss: 8.8745\n","Epoch [   55/  202] | d_loss: 0.0221 | g_loss: 8.9625\n","Epoch [   56/  202] | d_loss: 0.2265 | g_loss: 8.4412\n","Epoch [   57/  202] | d_loss: 0.2608 | g_loss: 8.6531\n","Epoch [   58/  202] | d_loss: 0.2120 | g_loss: 8.8697\n","Epoch [   59/  202] | d_loss: 0.1906 | g_loss: 8.7316\n","Epoch [   60/  202] | d_loss: 0.1455 | g_loss: 8.6046\n","Epoch [   61/  202] | d_loss: 0.2950 | g_loss: 7.6516\n","Epoch [   62/  202] | d_loss: 0.1022 | g_loss: 8.3419\n","Epoch [   63/  202] | d_loss: 0.1975 | g_loss: 8.3909\n","Epoch [   64/  202] | d_loss: 0.4089 | g_loss: 8.7912\n","Epoch [   65/  202] | d_loss: 0.0786 | g_loss: 8.1860\n","Epoch [   66/  202] | d_loss: 0.0711 | g_loss: 7.6758\n","Epoch [   67/  202] | d_loss: 0.2469 | g_loss: 8.3732\n","Epoch [   68/  202] | d_loss: 0.1449 | g_loss: 8.3077\n","Epoch [   69/  202] | d_loss: 0.1978 | g_loss: 8.1288\n","Epoch [   70/  202] | d_loss: 0.1955 | g_loss: 8.4189\n","Epoch [   71/  202] | d_loss: 0.2055 | g_loss: 8.0902\n","Epoch [   72/  202] | d_loss: 0.0330 | g_loss: 9.6669\n","Epoch [   73/  202] | d_loss: 0.1018 | g_loss: 7.6819\n","Epoch [   74/  202] | d_loss: 0.2513 | g_loss: 7.8982\n","Epoch [   75/  202] | d_loss: 0.1544 | g_loss: 7.2885\n","Epoch [   76/  202] | d_loss: 0.1692 | g_loss: 7.9533\n","Epoch [   77/  202] | d_loss: 0.2323 | g_loss: 8.4676\n","Epoch [   78/  202] | d_loss: 0.2285 | g_loss: 7.9449\n","Epoch [   79/  202] | d_loss: 0.1096 | g_loss: 7.5099\n","Epoch [   80/  202] | d_loss: 0.2167 | g_loss: 7.2681\n","Epoch [   81/  202] | d_loss: 0.1122 | g_loss: 7.2315\n","Epoch [   82/  202] | d_loss: 0.0987 | g_loss: 7.7702\n","Epoch [   83/  202] | d_loss: 0.1293 | g_loss: 7.1094\n","Epoch [   84/  202] | d_loss: 0.1046 | g_loss: 7.8048\n","Epoch [   85/  202] | d_loss: 0.1826 | g_loss: 7.9497\n","Epoch [   86/  202] | d_loss: 0.3739 | g_loss: 8.3167\n","Epoch [   87/  202] | d_loss: 0.1866 | g_loss: 7.6729\n","Epoch [   88/  202] | d_loss: 0.1324 | g_loss: 8.1433\n","Epoch [   89/  202] | d_loss: 0.0850 | g_loss: 7.1107\n","Epoch [   90/  202] | d_loss: 0.0621 | g_loss: 7.3855\n","Epoch [   91/  202] | d_loss: 0.2741 | g_loss: 7.6923\n","Epoch [   92/  202] | d_loss: 0.1309 | g_loss: 7.1541\n","Epoch [   93/  202] | d_loss: 0.2897 | g_loss: 7.2513\n","Epoch [   94/  202] | d_loss: 0.0954 | g_loss: 7.0316\n","Epoch [   95/  202] | d_loss: 0.2104 | g_loss: 6.5448\n","Epoch [   96/  202] | d_loss: 0.1599 | g_loss: 6.9487\n","Epoch [   97/  202] | d_loss: 0.0947 | g_loss: 7.2901\n","Epoch [   98/  202] | d_loss: 0.1450 | g_loss: 7.1248\n","Epoch [   99/  202] | d_loss: 0.1661 | g_loss: 7.7717\n","Epoch [  100/  202] | d_loss: 0.1873 | g_loss: 7.1095\n","Epoch [  101/  202] | d_loss: 0.1317 | g_loss: 7.1736\n","Saving model...\n","Epoch [  102/  202] | d_loss: 0.0760 | g_loss: 7.0948\n","Epoch [  103/  202] | d_loss: 0.1296 | g_loss: 6.8852\n","Epoch [  104/  202] | d_loss: 0.1811 | g_loss: 6.8167\n","Epoch [  105/  202] | d_loss: 0.2720 | g_loss: 6.9437\n","Epoch [  106/  202] | d_loss: 0.2467 | g_loss: 6.6204\n","Epoch [  107/  202] | d_loss: 0.1393 | g_loss: 6.9277\n","Epoch [  108/  202] | d_loss: 0.1420 | g_loss: 6.9078\n","Epoch [  109/  202] | d_loss: 0.2076 | g_loss: 6.6674\n","Epoch [  110/  202] | d_loss: 0.1292 | g_loss: 6.3261\n","Epoch [  111/  202] | d_loss: 0.0898 | g_loss: 7.2109\n","Epoch [  112/  202] | d_loss: 0.0759 | g_loss: 6.7167\n","Epoch [  113/  202] | d_loss: 0.1056 | g_loss: 6.8629\n","Epoch [  114/  202] | d_loss: 0.0921 | g_loss: 7.1561\n","Epoch [  115/  202] | d_loss: 0.1396 | g_loss: 6.8571\n","Epoch [  116/  202] | d_loss: 0.1183 | g_loss: 7.0625\n","Epoch [  117/  202] | d_loss: 0.2752 | g_loss: 6.5805\n","Epoch [  118/  202] | d_loss: 0.1329 | g_loss: 6.3832\n","Epoch [  119/  202] | d_loss: 0.3588 | g_loss: 5.6905\n","Epoch [  120/  202] | d_loss: 0.1347 | g_loss: 5.9866\n","Epoch [  121/  202] | d_loss: 0.1970 | g_loss: 7.1444\n","Epoch [  122/  202] | d_loss: 0.0613 | g_loss: 6.0734\n","Epoch [  123/  202] | d_loss: 0.1086 | g_loss: 6.7619\n","Epoch [  124/  202] | d_loss: 0.1036 | g_loss: 6.5330\n","Epoch [  125/  202] | d_loss: 0.1868 | g_loss: 6.4032\n","Epoch [  126/  202] | d_loss: 0.1964 | g_loss: 5.7656\n","Epoch [  127/  202] | d_loss: 0.2366 | g_loss: 5.9363\n","Epoch [  128/  202] | d_loss: 0.1466 | g_loss: 6.0160\n","Epoch [  129/  202] | d_loss: 0.0598 | g_loss: 6.5015\n","Epoch [  130/  202] | d_loss: 0.1185 | g_loss: 6.1371\n","Epoch [  131/  202] | d_loss: 0.2374 | g_loss: 6.4592\n","Epoch [  132/  202] | d_loss: 0.2247 | g_loss: 6.3625\n","Epoch [  133/  202] | d_loss: 0.1161 | g_loss: 6.3370\n","Epoch [  134/  202] | d_loss: 0.1583 | g_loss: 5.6795\n","Epoch [  135/  202] | d_loss: 0.1568 | g_loss: 6.6407\n","Epoch [  136/  202] | d_loss: 0.0846 | g_loss: 5.7535\n","Epoch [  137/  202] | d_loss: 0.1737 | g_loss: 5.6021\n","Epoch [  138/  202] | d_loss: 0.1356 | g_loss: 6.2431\n","Epoch [  139/  202] | d_loss: 0.1634 | g_loss: 6.1374\n","Epoch [  140/  202] | d_loss: 0.1810 | g_loss: 5.6265\n","Epoch [  141/  202] | d_loss: 0.1734 | g_loss: 5.8362\n","Epoch [  142/  202] | d_loss: 0.2606 | g_loss: 6.0263\n","Epoch [  143/  202] | d_loss: 0.0902 | g_loss: 6.0130\n","Epoch [  144/  202] | d_loss: 0.1811 | g_loss: 6.2937\n","Epoch [  145/  202] | d_loss: 0.1149 | g_loss: 5.7332\n","Epoch [  146/  202] | d_loss: 0.2255 | g_loss: 6.1247\n","Epoch [  147/  202] | d_loss: 0.1691 | g_loss: 5.7257\n","Epoch [  148/  202] | d_loss: 0.1236 | g_loss: 5.6946\n","Epoch [  149/  202] | d_loss: 0.0690 | g_loss: 5.7202\n","Epoch [  150/  202] | d_loss: 0.1270 | g_loss: 5.7152\n","Epoch [  151/  202] | d_loss: 0.3081 | g_loss: 5.1222\n","Epoch [  152/  202] | d_loss: 0.1005 | g_loss: 6.1739\n","Epoch [  153/  202] | d_loss: 0.1264 | g_loss: 5.6047\n","Epoch [  154/  202] | d_loss: 0.1062 | g_loss: 5.7394\n","Epoch [  155/  202] | d_loss: 0.1170 | g_loss: 5.6154\n","Epoch [  156/  202] | d_loss: 0.1356 | g_loss: 6.0157\n","Epoch [  157/  202] | d_loss: 0.2296 | g_loss: 5.2568\n","Epoch [  158/  202] | d_loss: 0.1240 | g_loss: 5.1784\n","Epoch [  159/  202] | d_loss: 0.1045 | g_loss: 5.5988\n","Epoch [  160/  202] | d_loss: 0.1566 | g_loss: 6.5493\n","Epoch [  161/  202] | d_loss: 0.1006 | g_loss: 6.2415\n","Epoch [  162/  202] | d_loss: 0.2095 | g_loss: 5.2902\n","Epoch [  163/  202] | d_loss: 0.1146 | g_loss: 5.5889\n","Epoch [  164/  202] | d_loss: 0.1497 | g_loss: 5.4557\n","Epoch [  165/  202] | d_loss: 0.0928 | g_loss: 5.4063\n","Epoch [  166/  202] | d_loss: 0.1258 | g_loss: 5.5056\n","Epoch [  167/  202] | d_loss: 0.0931 | g_loss: 5.7698\n","Epoch [  168/  202] | d_loss: 0.1056 | g_loss: 5.5393\n","Epoch [  169/  202] | d_loss: 0.1349 | g_loss: 5.4794\n","Epoch [  170/  202] | d_loss: 0.3442 | g_loss: 5.9072\n","Epoch [  171/  202] | d_loss: 0.1455 | g_loss: 5.0630\n","Epoch [  172/  202] | d_loss: 0.1491 | g_loss: 5.2885\n","Epoch [  173/  202] | d_loss: 0.1099 | g_loss: 5.2052\n","Epoch [  174/  202] | d_loss: 0.1269 | g_loss: 5.4819\n","Epoch [  175/  202] | d_loss: 0.1479 | g_loss: 5.5595\n","Epoch [  176/  202] | d_loss: 0.2191 | g_loss: 5.8972\n","Epoch [  177/  202] | d_loss: 0.1785 | g_loss: 5.5326\n","Epoch [  178/  202] | d_loss: 0.1188 | g_loss: 5.1260\n","Epoch [  179/  202] | d_loss: 0.1408 | g_loss: 5.4061\n","Epoch [  180/  202] | d_loss: 0.1080 | g_loss: 5.0986\n","Epoch [  181/  202] | d_loss: 0.1694 | g_loss: 5.0604\n","Epoch [  182/  202] | d_loss: 0.1023 | g_loss: 5.3019\n","Epoch [  183/  202] | d_loss: 0.1613 | g_loss: 4.9088\n","Epoch [  184/  202] | d_loss: 0.1305 | g_loss: 5.1234\n","Epoch [  185/  202] | d_loss: 0.1038 | g_loss: 5.1419\n","Epoch [  186/  202] | d_loss: 0.1668 | g_loss: 5.5852\n","Epoch [  187/  202] | d_loss: 0.2754 | g_loss: 4.8090\n","Epoch [  188/  202] | d_loss: 0.1298 | g_loss: 4.9350\n","Epoch [  189/  202] | d_loss: 0.1641 | g_loss: 4.5115\n","Epoch [  190/  202] | d_loss: 0.1411 | g_loss: 4.8528\n","Epoch [  191/  202] | d_loss: 0.1496 | g_loss: 4.9074\n","Epoch [  192/  202] | d_loss: 0.1217 | g_loss: 5.1605\n","Epoch [  193/  202] | d_loss: 0.1828 | g_loss: 5.1303\n","Epoch [  194/  202] | d_loss: 0.1688 | g_loss: 4.6766\n","Epoch [  195/  202] | d_loss: 0.1043 | g_loss: 4.9256\n","Epoch [  196/  202] | d_loss: 0.1144 | g_loss: 5.2230\n","Epoch [  197/  202] | d_loss: 0.1542 | g_loss: 4.9872\n","Epoch [  198/  202] | d_loss: 0.1418 | g_loss: 4.9805\n","Epoch [  199/  202] | d_loss: 0.1210 | g_loss: 4.9512\n","Epoch [  200/  202] | d_loss: 0.1754 | g_loss: 4.7807\n","Epoch [  201/  202] | d_loss: 0.1528 | g_loss: 4.9668\n","Saving model...\n","Epoch [  202/  202] | d_loss: 0.1663 | g_loss: 5.2881\n"]}],"source":["# ----------\n","#  Training\n","# ----------\n","\n","losses = []\n","num_epochs = 202\n","\n","# Initialize weights\n","generator.apply(weights_init_normal)\n","discriminator.apply(weights_init_normal)\n","epoch_D = 0\n","epoch_G = 0\n","\n","# train the network\n","discriminator.train()\n","generator.train()\n","print_every = 400\n","\n","for epoch in range(epoch_G, num_epochs):\n","    for i, batch in enumerate(dataloader):\n","\n","        # Model inputs\n","        real_A = Variable(batch[0].type(Tensor))\n","        real_B = Variable(batch[1].type(Tensor))\n","\n","        # Adversarial ground truths\n","        valid = Variable(Tensor(np.ones((real_B.size(0), *patch))), requires_grad=False)\n","        fake = Variable(Tensor(np.zeros((real_B.size(0), *patch))), requires_grad=False)\n","\n","        # ------------------\n","        #  Train Generators\n","        # ------------------\n","\n","        optimizer_G.zero_grad()\n","\n","        # GAN loss\n","        # TO DO: Put here your GAN loss\n","        fake_A = generator(real_B)\n","        pred_fake = discriminator(fake_A, real_B)\n","        loss_GAN = criterion_GAN(pred_fake, valid)\n","\n","        # Pixel-wise loss\n","        # TO DO: Put here your pixel loss\n","        loss_pixel = criterion_pixelwise(fake_A,real_A) * lambda_pixel\n","\n","        # Total loss\n","        # TO DO: Put here your total loss\n","        loss_G = loss_GAN + loss_pixel\n","\n","        loss_G.backward()\n","\n","        optimizer_G.step()\n","\n","        # ---------------------\n","        #  Train Discriminator\n","        # ---------------------\n","\n","        optimizer_D.zero_grad()\n","\n","        # Real loss\n","        pred_real = discriminator(real_A, real_B)\n","        loss_real = criterion_GAN(pred_real, valid)\n","\n","        # Fake loss\n","        pred_fake = discriminator(fake_A.detach(), real_B)\n","        loss_fake = criterion_GAN(pred_fake, fake)\n","\n","        # Total loss\n","        loss_D = 0.5 * (loss_real + loss_fake)\n","\n","        loss_D.backward()\n","        optimizer_D.step()\n","        \n","        # Print some loss stats\n","        if i % print_every == 0:\n","            # print discriminator and generator loss\n","            print('Epoch [{:5d}/{:5d}] | d_loss: {:6.4f} | g_loss: {:6.4f}'.format(\n","                    epoch+1, num_epochs, loss_D.item(), loss_G.item()))\n","    ## AFTER EACH EPOCH##\n","    # append discriminator loss and generator loss\n","    losses.append((loss_D.item(), loss_G.item()))\n","    if epoch % 100 == 0:\n","        print('Saving model...')\n","        save_model(epoch)\n"]},{"cell_type":"markdown","metadata":{"id":"Ed-ZbuVWBUgu"},"source":["Observation of the loss along the training"]},{"cell_type":"code","execution_count":38,"metadata":{"id":"nOLW054DTLpg","colab":{"base_uri":"https://localhost:8080/","height":298},"executionInfo":{"status":"ok","timestamp":1679068189618,"user_tz":-60,"elapsed":530,"user":{"displayName":"Florian Gaudry","userId":"04425733722793549516"}},"outputId":"c353e178-8fba-4e8c-c659-8ec137516409"},"outputs":[{"output_type":"execute_result","data":{"text/plain":["<matplotlib.legend.Legend at 0x7fed684fcbb0>"]},"metadata":{},"execution_count":38},{"output_type":"display_data","data":{"text/plain":["<Figure size 432x288 with 1 Axes>"],"image/png":"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\n"},"metadata":{"needs_background":"light"}}],"source":["fig, ax = plt.subplots()\n","losses = np.array(losses)\n","plt.plot(losses.T[0], label='Discriminator')\n","plt.plot(losses.T[1], label='Generator')\n","plt.title(\"Training Losses\")\n","plt.legend()\n"]},{"cell_type":"markdown","metadata":{"id":"S58kJj9HBUgV"},"source":["If the training takes too much time, you can use a pretrained model in the meantime, to evaluate its performance.\n","\n","It is available at : https://partage.liris.cnrs.fr/index.php/s/xwEFmxn9ANeq4zY"]},{"cell_type":"markdown","metadata":{"id":"i0TC5qK3BUg4"},"source":["### Evaluate your cGAN"]},{"cell_type":"code","execution_count":39,"metadata":{"id":"fYBRR6NYBUg6","executionInfo":{"status":"ok","timestamp":1679068198819,"user_tz":-60,"elapsed":245,"user":{"displayName":"Florian Gaudry","userId":"04425733722793549516"}}},"outputs":[],"source":["def load_model(epoch=200):\n","    if 'generator_'+str(epoch)+'.pth' in os.listdir() and 'discriminator_'+str(epoch)+'.pth' in os.listdir():\n","        if cuda:\n","            checkpoint_generator = torch.load('generator_'+str(epoch)+'.pth')\n","        else:\n","            checkpoint_generator = torch.load('generator_'+str(epoch)+'.pth', map_location='cpu')\n","        generator.load_state_dict(checkpoint_generator['model_state_dict'])\n","        optimizer_G.load_state_dict(checkpoint_generator['optimizer_state_dict'])\n","        epoch_G = checkpoint_generator['epoch']\n","        loss_G = checkpoint_generator['loss']\n","\n","        if cuda:\n","            checkpoint_discriminator = torch.load('discriminator_'+str(epoch)+'.pth')\n","        else:\n","            checkpoint_discriminator = torch.load('discriminator_'+str(epoch)+'.pth', map_location='cpu')\n","        discriminator.load_state_dict(checkpoint_discriminator['model_state_dict'])\n","        optimizer_D.load_state_dict(checkpoint_discriminator['optimizer_state_dict'])\n","        epoch_D = checkpoint_discriminator['epoch']\n","        loss_D = checkpoint_discriminator['loss']\n","    else:\n","        print('There isn\\'t a training available with this number of epochs')"]},{"cell_type":"code","source":["loss_G"],"metadata":{"colab":{"base_uri":"https://localhost:8080/"},"id":"8pyuHs4cCeIO","executionInfo":{"status":"ok","timestamp":1679068209510,"user_tz":-60,"elapsed":274,"user":{"displayName":"Florian Gaudry","userId":"04425733722793549516"}},"outputId":"22e76b81-9fb8-4a72-935c-63f2e6537620"},"execution_count":40,"outputs":[{"output_type":"execute_result","data":{"text/plain":["tensor(5.2694, device='cuda:0', grad_fn=<AddBackward0>)"]},"metadata":{},"execution_count":40}]},{"cell_type":"code","execution_count":41,"metadata":{"id":"4V0DwQomBUg9","colab":{"base_uri":"https://localhost:8080/"},"executionInfo":{"status":"ok","timestamp":1679068219403,"user_tz":-60,"elapsed":1425,"user":{"displayName":"Florian Gaudry","userId":"04425733722793549516"}},"outputId":"cbffd35f-5811-4e9e-9f62-0d3a95eeb13f"},"outputs":[{"output_type":"execute_result","data":{"text/plain":["U_Net(\n","  (inc): inconv(\n","    (conv): Sequential(\n","      (0): Conv2d(3, 64, kernel_size=(4, 4), stride=(2, 2), padding=(1, 1))\n","      (1): LeakyReLU(negative_slope=0.2, inplace=True)\n","    )\n","  )\n","  (down1): down(\n","    (conv): Sequential(\n","      (0): Conv2d(64, 128, kernel_size=(4, 4), stride=(2, 2), padding=(1, 1))\n","      (1): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n","      (2): LeakyReLU(negative_slope=0.2, inplace=True)\n","    )\n","  )\n","  (down2): down(\n","    (conv): Sequential(\n","      (0): Conv2d(128, 256, kernel_size=(4, 4), stride=(2, 2), padding=(1, 1))\n","      (1): BatchNorm2d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n","      (2): LeakyReLU(negative_slope=0.2, inplace=True)\n","    )\n","  )\n","  (down3): down(\n","    (conv): Sequential(\n","      (0): Conv2d(256, 512, kernel_size=(4, 4), stride=(2, 2), padding=(1, 1))\n","      (1): BatchNorm2d(512, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n","      (2): LeakyReLU(negative_slope=0.2, inplace=True)\n","    )\n","  )\n","  (down4): down(\n","    (conv): Sequential(\n","      (0): Conv2d(512, 512, kernel_size=(4, 4), stride=(2, 2), padding=(1, 1))\n","      (1): BatchNorm2d(512, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n","      (2): LeakyReLU(negative_slope=0.2, inplace=True)\n","    )\n","  )\n","  (down5): down(\n","    (conv): Sequential(\n","      (0): Conv2d(512, 512, kernel_size=(4, 4), stride=(2, 2), padding=(1, 1))\n","      (1): BatchNorm2d(512, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n","      (2): LeakyReLU(negative_slope=0.2, inplace=True)\n","    )\n","  )\n","  (down6): down(\n","    (conv): Sequential(\n","      (0): Conv2d(512, 512, kernel_size=(4, 4), stride=(2, 2), padding=(1, 1))\n","      (1): BatchNorm2d(512, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n","      (2): LeakyReLU(negative_slope=0.2, inplace=True)\n","    )\n","  )\n","  (down7): down(\n","    (conv): Sequential(\n","      (0): Conv2d(512, 512, kernel_size=(4, 4), stride=(2, 2), padding=(1, 1))\n","      (1): BatchNorm2d(512, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n","      (2): LeakyReLU(negative_slope=0.2, inplace=True)\n","    )\n","  )\n","  (up7): up(\n","    (conv): Sequential(\n","      (0): ConvTranspose2d(512, 512, kernel_size=(4, 4), stride=(2, 2), padding=(1, 1))\n","      (1): BatchNorm2d(512, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n","      (2): Dropout(p=0.5, inplace=True)\n","      (3): ReLU(inplace=True)\n","    )\n","  )\n","  (up6): up(\n","    (conv): Sequential(\n","      (0): ConvTranspose2d(1024, 512, kernel_size=(4, 4), stride=(2, 2), padding=(1, 1))\n","      (1): BatchNorm2d(512, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n","      (2): Dropout(p=0.5, inplace=True)\n","      (3): ReLU(inplace=True)\n","    )\n","  )\n","  (up5): up(\n","    (conv): Sequential(\n","      (0): ConvTranspose2d(1024, 512, kernel_size=(4, 4), stride=(2, 2), padding=(1, 1))\n","      (1): BatchNorm2d(512, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n","      (2): Dropout(p=0.5, inplace=True)\n","      (3): ReLU(inplace=True)\n","    )\n","  )\n","  (up4): up(\n","    (conv): Sequential(\n","      (0): ConvTranspose2d(1024, 512, kernel_size=(4, 4), stride=(2, 2), padding=(1, 1))\n","      (1): BatchNorm2d(512, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n","      (2): ReLU(inplace=True)\n","    )\n","  )\n","  (up3): up(\n","    (conv): Sequential(\n","      (0): ConvTranspose2d(1024, 256, kernel_size=(4, 4), stride=(2, 2), padding=(1, 1))\n","      (1): BatchNorm2d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n","      (2): ReLU(inplace=True)\n","    )\n","  )\n","  (up2): up(\n","    (conv): Sequential(\n","      (0): ConvTranspose2d(512, 128, kernel_size=(4, 4), stride=(2, 2), padding=(1, 1))\n","      (1): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n","      (2): ReLU(inplace=True)\n","    )\n","  )\n","  (up1): up(\n","    (conv): Sequential(\n","      (0): ConvTranspose2d(256, 64, kernel_size=(4, 4), stride=(2, 2), padding=(1, 1))\n","      (1): BatchNorm2d(64, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n","      (2): ReLU(inplace=True)\n","    )\n","  )\n","  (outc): outconv(\n","    (conv): Sequential(\n","      (0): ConvTranspose2d(128, 3, kernel_size=(4, 4), stride=(2, 2), padding=(1, 1))\n","      (1): Tanh()\n","    )\n","  )\n",")"]},"metadata":{},"execution_count":41}],"source":["load_model(epoch=200)\n","\n","# switching mode\n","generator.eval()"]},{"cell_type":"code","execution_count":42,"metadata":{"id":"gyvmvkIvBUhB","colab":{"base_uri":"https://localhost:8080/","height":1000,"output_embedded_package_id":"15nT9SOvmiXdPMR4gHxLwSIevo0tKVvuF"},"executionInfo":{"status":"ok","timestamp":1679068230613,"user_tz":-60,"elapsed":7723,"user":{"displayName":"Florian Gaudry","userId":"04425733722793549516"}},"outputId":"5a259a50-915a-4819-c7d1-395ccaa9b8f4"},"outputs":[{"output_type":"display_data","data":{"text/plain":"Output hidden; open in https://colab.research.google.com to view."},"metadata":{}}],"source":["# show a sample evaluation image on the training base\n","image, mask = next(iter(dataloader))\n","output = generator(mask.type(Tensor))\n","output = output.view(16, 3, 256, 256)\n","output = output.cpu().detach()\n","for i in range(8):\n","    image_plot = reverse_transform(image[i])\n","    output_plot = reverse_transform(output[i])\n","    mask_plot = reverse_transform(mask[i])\n","    plot2x3Array(mask_plot,image_plot,output_plot)"]},{"cell_type":"code","execution_count":43,"metadata":{"id":"nqvrxBoGBUhD","colab":{"base_uri":"https://localhost:8080/","height":1000,"output_embedded_package_id":"1PUqYyZ6h8AA5297sV78XmL7XmvmsO4eo"},"executionInfo":{"status":"ok","timestamp":1679068252696,"user_tz":-60,"elapsed":7739,"user":{"displayName":"Florian Gaudry","userId":"04425733722793549516"}},"outputId":"faa09786-4eaf-4bd9-c6f1-84a40f066dc1"},"outputs":[{"output_type":"display_data","data":{"text/plain":"Output hidden; open in https://colab.research.google.com to view."},"metadata":{}}],"source":["# show a sample evaluation image on the validation dataset\n","image, mask = next(iter(val_dataloader))\n","output = generator(mask.type(Tensor))\n","output = output.view(8, 3, 256, 256)\n","output = output.cpu().detach()\n","for i in range(8):\n","    image_plot = reverse_transform(image[i])\n","    output_plot = reverse_transform(output[i])\n","    mask_plot = reverse_transform(mask[i])\n","    plot2x3Array(mask_plot,image_plot,output_plot)"]},{"cell_type":"markdown","metadata":{"id":"qkFVjRsOBUhG"},"source":["<font color='red'>**Question 4**</font>                                                                  \n","Compare results for 100 and 200 epochs"]},{"cell_type":"code","execution_count":44,"metadata":{"id":"k85Cl5_UDWyv","colab":{"base_uri":"https://localhost:8080/"},"executionInfo":{"status":"ok","timestamp":1679068277046,"user_tz":-60,"elapsed":614,"user":{"displayName":"Florian Gaudry","userId":"04425733722793549516"}},"outputId":"4607e6f1-fa58-494d-b73f-f4190ad0ff03"},"outputs":[{"output_type":"execute_result","data":{"text/plain":["U_Net(\n","  (inc): inconv(\n","    (conv): Sequential(\n","      (0): Conv2d(3, 64, kernel_size=(4, 4), stride=(2, 2), padding=(1, 1))\n","      (1): LeakyReLU(negative_slope=0.2, inplace=True)\n","    )\n","  )\n","  (down1): down(\n","    (conv): Sequential(\n","      (0): Conv2d(64, 128, kernel_size=(4, 4), stride=(2, 2), padding=(1, 1))\n","      (1): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n","      (2): LeakyReLU(negative_slope=0.2, inplace=True)\n","    )\n","  )\n","  (down2): down(\n","    (conv): Sequential(\n","      (0): Conv2d(128, 256, kernel_size=(4, 4), stride=(2, 2), padding=(1, 1))\n","      (1): BatchNorm2d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n","      (2): LeakyReLU(negative_slope=0.2, inplace=True)\n","    )\n","  )\n","  (down3): down(\n","    (conv): Sequential(\n","      (0): Conv2d(256, 512, kernel_size=(4, 4), stride=(2, 2), padding=(1, 1))\n","      (1): BatchNorm2d(512, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n","      (2): LeakyReLU(negative_slope=0.2, inplace=True)\n","    )\n","  )\n","  (down4): down(\n","    (conv): Sequential(\n","      (0): Conv2d(512, 512, kernel_size=(4, 4), stride=(2, 2), padding=(1, 1))\n","      (1): BatchNorm2d(512, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n","      (2): LeakyReLU(negative_slope=0.2, inplace=True)\n","    )\n","  )\n","  (down5): down(\n","    (conv): Sequential(\n","      (0): Conv2d(512, 512, kernel_size=(4, 4), stride=(2, 2), padding=(1, 1))\n","      (1): BatchNorm2d(512, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n","      (2): LeakyReLU(negative_slope=0.2, inplace=True)\n","    )\n","  )\n","  (down6): down(\n","    (conv): Sequential(\n","      (0): Conv2d(512, 512, kernel_size=(4, 4), stride=(2, 2), padding=(1, 1))\n","      (1): BatchNorm2d(512, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n","      (2): LeakyReLU(negative_slope=0.2, inplace=True)\n","    )\n","  )\n","  (down7): down(\n","    (conv): Sequential(\n","      (0): Conv2d(512, 512, kernel_size=(4, 4), stride=(2, 2), padding=(1, 1))\n","      (1): BatchNorm2d(512, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n","      (2): LeakyReLU(negative_slope=0.2, inplace=True)\n","    )\n","  )\n","  (up7): up(\n","    (conv): Sequential(\n","      (0): ConvTranspose2d(512, 512, kernel_size=(4, 4), stride=(2, 2), padding=(1, 1))\n","      (1): BatchNorm2d(512, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n","      (2): Dropout(p=0.5, inplace=True)\n","      (3): ReLU(inplace=True)\n","    )\n","  )\n","  (up6): up(\n","    (conv): Sequential(\n","      (0): ConvTranspose2d(1024, 512, kernel_size=(4, 4), stride=(2, 2), padding=(1, 1))\n","      (1): BatchNorm2d(512, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n","      (2): Dropout(p=0.5, inplace=True)\n","      (3): ReLU(inplace=True)\n","    )\n","  )\n","  (up5): up(\n","    (conv): Sequential(\n","      (0): ConvTranspose2d(1024, 512, kernel_size=(4, 4), stride=(2, 2), padding=(1, 1))\n","      (1): BatchNorm2d(512, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n","      (2): Dropout(p=0.5, inplace=True)\n","      (3): ReLU(inplace=True)\n","    )\n","  )\n","  (up4): up(\n","    (conv): Sequential(\n","      (0): ConvTranspose2d(1024, 512, kernel_size=(4, 4), stride=(2, 2), padding=(1, 1))\n","      (1): BatchNorm2d(512, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n","      (2): ReLU(inplace=True)\n","    )\n","  )\n","  (up3): up(\n","    (conv): Sequential(\n","      (0): ConvTranspose2d(1024, 256, kernel_size=(4, 4), stride=(2, 2), padding=(1, 1))\n","      (1): BatchNorm2d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n","      (2): ReLU(inplace=True)\n","    )\n","  )\n","  (up2): up(\n","    (conv): Sequential(\n","      (0): ConvTranspose2d(512, 128, kernel_size=(4, 4), stride=(2, 2), padding=(1, 1))\n","      (1): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n","      (2): ReLU(inplace=True)\n","    )\n","  )\n","  (up1): up(\n","    (conv): Sequential(\n","      (0): ConvTranspose2d(256, 64, kernel_size=(4, 4), stride=(2, 2), padding=(1, 1))\n","      (1): BatchNorm2d(64, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n","      (2): ReLU(inplace=True)\n","    )\n","  )\n","  (outc): outconv(\n","    (conv): Sequential(\n","      (0): ConvTranspose2d(128, 3, kernel_size=(4, 4), stride=(2, 2), padding=(1, 1))\n","      (1): Tanh()\n","    )\n","  )\n",")"]},"metadata":{},"execution_count":44}],"source":["# TO DO : Your code here to load and evaluate with a few samples\n","#         a model after 100 epochs\n","\n","load_model(epoch=100)\n","\n","# switching mode\n","generator.eval()"]},{"cell_type":"code","source":["# show a sample evaluation image on the training base\n","image, mask = next(iter(dataloader))\n","output = generator(mask.type(Tensor))\n","output = output.view(16, 3, 256, 256)\n","output = output.cpu().detach()\n","for i in range(8):\n","    image_plot = reverse_transform(image[i])\n","    output_plot = reverse_transform(output[i])\n","    mask_plot = reverse_transform(mask[i])\n","    plot2x3Array(mask_plot,image_plot,output_plot)"],"metadata":{"id":"hSAgn_240a4Z","colab":{"base_uri":"https://localhost:8080/","height":1000,"output_embedded_package_id":"10gXikV-LBVxbiqZldVK7Avu-Q0toaZzI"},"executionInfo":{"status":"ok","timestamp":1679068287640,"user_tz":-60,"elapsed":7235,"user":{"displayName":"Florian Gaudry","userId":"04425733722793549516"}},"outputId":"b2ae8060-e6f2-4101-dc4e-a05c8f57fa0c"},"execution_count":45,"outputs":[{"output_type":"display_data","data":{"text/plain":"Output hidden; open in https://colab.research.google.com to view."},"metadata":{}}]},{"cell_type":"code","source":["# show a sample evaluation image on the validation dataset\n","image, mask = next(iter(val_dataloader))\n","output = generator(mask.type(Tensor))\n","output = output.view(8, 3, 256, 256)\n","output = output.cpu().detach()\n","for i in range(8):\n","    image_plot = reverse_transform(image[i])\n","    output_plot = reverse_transform(output[i])\n","    mask_plot = reverse_transform(mask[i])\n","    plot2x3Array(mask_plot,image_plot,output_plot)"],"metadata":{"id":"P9pOWtVx0glJ","colab":{"base_uri":"https://localhost:8080/","height":1000,"output_embedded_package_id":"1gm0jpy7OPXD_ROJPP_ejVcCfj0e57NsE"},"executionInfo":{"status":"ok","timestamp":1679068303081,"user_tz":-60,"elapsed":6934,"user":{"displayName":"Florian Gaudry","userId":"04425733722793549516"}},"outputId":"91bff7b4-40b4-442f-dcbb-ceda0f5d5912"},"execution_count":46,"outputs":[{"output_type":"display_data","data":{"text/plain":"Output hidden; open in https://colab.research.google.com to view."},"metadata":{}}]},{"cell_type":"code","execution_count":47,"metadata":{"id":"_GbMIfRXBUhH","executionInfo":{"status":"ok","timestamp":1679068313180,"user_tz":-60,"elapsed":232,"user":{"displayName":"Florian Gaudry","userId":"04425733722793549516"}}},"outputs":[],"source":["# And finally :\n","if cuda:\n","    torch.cuda.empty_cache()"]},{"cell_type":"markdown","metadata":{"id":"rVxSSPJgK60P"},"source":["# How to submit your Work ?\n","\n","This work must be done individually. The expected output is a repository named gan-cgan on https://gitlab.ec-lyon.fr. It must contain your notebook (or python files) and a README.md file that explains briefly the successive steps of the project. The last commit is due before 11:59 pm on Wednesday, March 29, 2023. Subsequent commits will not be considered."]}],"metadata":{"colab":{"provenance":[]},"kernelspec":{"display_name":"Python 3","language":"python","name":"python3"},"language_info":{"codemirror_mode":{"name":"ipython","version":3},"file_extension":".py","mimetype":"text/x-python","name":"python","nbconvert_exporter":"python","pygments_lexer":"ipython3","version":"3.8.8"},"accelerator":"GPU","gpuClass":"standard","widgets":{"application/vnd.jupyter.widget-state+json":{"1e36689c6e3b4540af78f20862d04898":{"model_module":"@jupyter-widgets/controls","model_name":"HBoxModel","model_module_version":"1.5.0","state":{"_dom_classes":[],"_model_module":"@jupyter-widgets/controls","_model_module_version":"1.5.0","_model_name":"HBoxModel","_view_count":null,"_view_module":"@jupyter-widgets/controls","_view_module_version":"1.5.0","_view_name":"HBoxView","box_style":"","children":["IPY_MODEL_3a07c521ad8f44e7ba6ef57c182c01e0","IPY_MODEL_e8c931c1361b41a395f9c257e77bba9c","IPY_MODEL_c9681befe58c4bd992c1c93c193b9f6f"],"layout":"IPY_MODEL_8c67d3b695994062a7161f56eaa99530"}},"3a07c521ad8f44e7ba6ef57c182c01e0":{"model_module":"@jupyter-widgets/controls","model_name":"HTMLModel","model_module_version":"1.5.0","state":{"_dom_classes":[],"_model_module":"@jupyter-widgets/controls","_model_module_version":"1.5.0","_model_name":"HTMLModel","_view_count":null,"_view_module":"@jupyter-widgets/controls","_view_module_version":"1.5.0","_view_name":"HTMLView","description":"","description_tooltip":null,"layout":"IPY_MODEL_a1a14cdea09342c1ad80273469cec5a0","placeholder":"​","style":"IPY_MODEL_f49a0430fcc448ad980ebbfd0ec9b58e","value":"100%"}},"e8c931c1361b41a395f9c257e77bba9c":{"model_module":"@jupyter-widgets/controls","model_name":"FloatProgressModel","model_module_version":"1.5.0","state":{"_dom_classes":[],"_model_module":"@jupyter-widgets/controls","_model_module_version":"1.5.0","_model_name":"FloatProgressModel","_view_count":null,"_view_module":"@jupyter-widgets/controls","_view_module_version":"1.5.0","_view_name":"ProgressView","bar_style":"success","description":"","description_tooltip":null,"layout":"IPY_MODEL_9d8022f8bf7a44218e482b83f46fd947","max":9912422,"min":0,"orientation":"horizontal","style":"IPY_MODEL_c706ba9682dd4384997a6059aca253cb","value":9912422}},"c9681befe58c4bd992c1c93c193b9f6f":{"model_module":"@jupyter-widgets/controls","model_name":"HTMLModel","model_module_version":"1.5.0","state":{"_dom_classes":[],"_model_module":"@jupyter-widgets/controls","_model_module_version":"1.5.0","_model_name":"HTMLModel","_view_count":null,"_view_module":"@jupyter-widgets/controls","_view_module_version":"1.5.0","_view_name":"HTMLView","description":"","description_tooltip":null,"layout":"IPY_MODEL_eac304c981804cd9b5f29803acfc7efd","placeholder":"​","style":"IPY_MODEL_ca37bab93af74dae87f01916dc49ee24","value":" 9912422/9912422 [00:00&lt;00:00, 69787919.96it/s]"}},"8c67d3b695994062a7161f56eaa99530":{"model_module":"@jupyter-widgets/base","model_name":"LayoutModel","model_module_version":"1.2.0","state":{"_model_module":"@jupyter-widgets/base","_model_module_version":"1.2.0","_model_name":"LayoutModel","_view_count":null,"_view_module":"@jupyter-widgets/base","_view_module_version":"1.2.0","_view_name":"LayoutView","align_content":null,"align_items":null,"align_self":null,"border":null,"bottom":null,"display":null,"flex":null,"flex_flow":null,"grid_area":null,"grid_auto_columns":null,"grid_auto_flow":null,"grid_auto_rows":null,"grid_column":null,"grid_gap":null,"grid_row":null,"grid_template_areas":null,"grid_template_columns":null,"grid_template_rows":null,"height":null,"justify_content":null,"justify_items":null,"left":null,"margin":null,"max_height":null,"max_width":null,"min_height":null,"min_width":null,"object_fit":null,"object_position":null,"order":null,"overflow":null,"overflow_x":null,"overflow_y":null,"padding":null,"right":null,"top":null,"visibility":null,"width":null}},"a1a14cdea09342c1ad80273469cec5a0":{"model_module":"@jupyter-widgets/base","model_name":"LayoutModel","model_module_version":"1.2.0","state":{"_model_module":"@jupyter-widgets/base","_model_module_version":"1.2.0","_model_name":"LayoutModel","_view_count":null,"_view_module":"@jupyter-widgets/base","_view_module_version":"1.2.0","_view_name":"LayoutView","align_content":null,"align_items":null,"align_self":null,"border":null,"bottom":null,"display":null,"flex":null,"flex_flow":null,"grid_area":null,"grid_auto_columns":null,"grid_auto_flow":null,"grid_auto_rows":null,"grid_column":null,"grid_gap":null,"grid_row":null,"grid_template_areas":null,"grid_template_columns":null,"grid_template_rows":null,"height":null,"justify_content":null,"justify_items":null,"left":null,"margin":null,"max_height":null,"max_width":null,"min_height":null,"min_width":null,"object_fit":null,"object_position":null,"order":null,"overflow":null,"overflow_x":null,"overflow_y":null,"padding":null,"right":null,"top":null,"visibility":null,"width":null}},"f49a0430fcc448ad980ebbfd0ec9b58e":{"model_module":"@jupyter-widgets/controls","model_name":"DescriptionStyleModel","model_module_version":"1.5.0","state":{"_model_module":"@jupyter-widgets/controls","_model_module_version":"1.5.0","_model_name":"DescriptionStyleModel","_view_count":null,"_view_module":"@jupyter-widgets/base","_view_module_version":"1.2.0","_view_name":"StyleView","description_width":""}},"9d8022f8bf7a44218e482b83f46fd947":{"model_module":"@jupyter-widgets/base","model_name":"LayoutModel","model_module_version":"1.2.0","state":{"_model_module":"@jupyter-widgets/base","_model_module_version":"1.2.0","_model_name":"LayoutModel","_view_count":null,"_view_module":"@jupyter-widgets/base","_view_module_version":"1.2.0","_view_name":"LayoutView","align_content":null,"align_items":null,"align_self":null,"border":null,"bottom":null,"display":null,"flex":null,"flex_flow":null,"grid_area":null,"grid_auto_columns":null,"grid_auto_flow":null,"grid_auto_rows":null,"grid_column":null,"grid_gap":null,"grid_row":null,"grid_template_areas":null,"grid_template_columns":null,"grid_template_rows":null,"height":null,"justify_content":null,"justify_items":null,"left":null,"margin":null,"max_height":null,"max_width":null,"min_height":null,"min_width":null,"object_fit":null,"object_position":null,"order":null,"overflow":null,"overflow_x":null,"overflow_y":null,"padding":null,"right":null,"top":null,"visibility":null,"width":null}},"c706ba9682dd4384997a6059aca253cb":{"model_module":"@jupyter-widgets/controls","model_name":"ProgressStyleModel","model_module_version":"1.5.0","state":{"_model_module":"@jupyter-widgets/controls","_model_module_version":"1.5.0","_model_name":"ProgressStyleModel","_view_count":null,"_view_module":"@jupyter-widgets/base","_view_module_version":"1.2.0","_view_name":"StyleView","bar_color":null,"description_width":""}},"eac304c981804cd9b5f29803acfc7efd":{"model_module":"@jupyter-widgets/base","model_name":"LayoutModel","model_module_version":"1.2.0","state":{"_model_module":"@jupyter-widgets/base","_model_module_version":"1.2.0","_model_name":"LayoutModel","_view_count":null,"_view_module":"@jupyter-widgets/base","_view_module_version":"1.2.0","_view_name":"LayoutView","align_content":null,"align_items":null,"align_self":null,"border":null,"bottom":null,"display":null,"flex":null,"flex_flow":null,"grid_area":null,"grid_auto_columns":null,"grid_auto_flow":null,"grid_auto_rows":null,"grid_column":null,"grid_gap":null,"grid_row":null,"grid_template_areas":null,"grid_template_columns":null,"grid_template_rows":null,"height":null,"justify_content":null,"justify_items":null,"left":null,"margin":null,"max_height":null,"max_width":null,"min_height":null,"min_width":null,"object_fit":null,"object_position":null,"order":null,"overflow":null,"overflow_x":null,"overflow_y":null,"padding":null,"right":null,"top":null,"visibility":null,"width":null}},"ca37bab93af74dae87f01916dc49ee24":{"model_module":"@jupyter-widgets/controls","model_name":"DescriptionStyleModel","model_module_version":"1.5.0","state":{"_model_module":"@jupyter-widgets/controls","_model_module_version":"1.5.0","_model_name":"DescriptionStyleModel","_view_count":null,"_view_module":"@jupyter-widgets/base","_view_module_version":"1.2.0","_view_name":"StyleView","description_width":""}},"e2867e04986a42e3944412d1c7129656":{"model_module":"@jupyter-widgets/controls","model_name":"HBoxModel","model_module_version":"1.5.0","state":{"_dom_classes":[],"_model_module":"@jupyter-widgets/controls","_model_module_version":"1.5.0","_model_name":"HBoxModel","_view_count":null,"_view_module":"@jupyter-widgets/controls","_view_module_version":"1.5.0","_view_name":"HBoxView","box_style":"","children":["IPY_MODEL_31fa538191fc4e67ab2fea1cb7e4ea04","IPY_MODEL_dbe3af00397c4f408dedc9543c7fbcac","IPY_MODEL_c40a461f12644f2c8c1ea80190d90bd2"],"layout":"IPY_MODEL_637143360d734d7398e64c003da291c1"}},"31fa538191fc4e67ab2fea1cb7e4ea04":{"model_module":"@jupyter-widgets/controls","model_name":"HTMLModel","model_module_version":"1.5.0","state":{"_dom_classes":[],"_model_module":"@jupyter-widgets/controls","_model_module_version":"1.5.0","_model_name":"HTMLModel","_view_count":null,"_view_module":"@jupyter-widgets/controls","_view_module_version":"1.5.0","_view_name":"HTMLView","description":"","description_tooltip":null,"layout":"IPY_MODEL_4e09360f2a7d4a6cbf94798fbe5105cb","placeholder":"​","style":"IPY_MODEL_d2555ebdd173497a9f49054f2ca82793","value":"100%"}},"dbe3af00397c4f408dedc9543c7fbcac":{"model_module":"@jupyter-widgets/controls","model_name":"FloatProgressModel","model_module_version":"1.5.0","state":{"_dom_classes":[],"_model_module":"@jupyter-widgets/controls","_model_module_version":"1.5.0","_model_name":"FloatProgressModel","_view_count":null,"_view_module":"@jupyter-widgets/controls","_view_module_version":"1.5.0","_view_name":"ProgressView","bar_style":"success","description":"","description_tooltip":null,"layout":"IPY_MODEL_b3ffa36739ec4c5c9d0f0690e9920d19","max":28881,"min":0,"orientation":"horizontal","style":"IPY_MODEL_b0bd56c6c26d49adac84eaaaeac75e9c","value":28881}},"c40a461f12644f2c8c1ea80190d90bd2":{"model_module":"@jupyter-widgets/controls","model_name":"HTMLModel","model_module_version":"1.5.0","state":{"_dom_classes":[],"_model_module":"@jupyter-widgets/controls","_model_module_version":"1.5.0","_model_name":"HTMLModel","_view_count":null,"_view_module":"@jupyter-widgets/controls","_view_module_version":"1.5.0","_view_name":"HTMLView","description":"","description_tooltip":null,"layout":"IPY_MODEL_8a84f6f970ee41ebb69f82aa2a006f8a","placeholder":"​","style":"IPY_MODEL_ce1790d859da42fe8dfe59dbe7c9d232","value":" 28881/28881 [00:00&lt;00:00, 1708398.36it/s]"}},"637143360d734d7398e64c003da291c1":{"model_module":"@jupyter-widgets/base","model_name":"LayoutModel","model_module_version":"1.2.0","state":{"_model_module":"@jupyter-widgets/base","_model_module_version":"1.2.0","_model_name":"LayoutModel","_view_count":null,"_view_module":"@jupyter-widgets/base","_view_module_version":"1.2.0","_view_name":"LayoutView","align_content":null,"align_items":null,"align_self":null,"border":null,"bottom":null,"display":null,"flex":null,"flex_flow":null,"grid_area":null,"grid_auto_columns":null,"grid_auto_flow":null,"grid_auto_rows":null,"grid_column":null,"grid_gap":null,"grid_row":null,"grid_template_areas":null,"grid_template_columns":null,"grid_template_rows":null,"height":null,"justify_content":null,"justify_items":null,"left":null,"margin":null,"max_height":null,"max_width":null,"min_height":null,"min_width":null,"object_fit":null,"object_position":null,"order":null,"overflow":null,"overflow_x":null,"overflow_y":null,"padding":null,"right":null,"top":null,"visibility":null,"width":null}},"4e09360f2a7d4a6cbf94798fbe5105cb":{"model_module":"@jupyter-widgets/base","model_name":"LayoutModel","model_module_version":"1.2.0","state":{"_model_module":"@jupyter-widgets/base","_model_module_version":"1.2.0","_model_name":"LayoutModel","_view_count":null,"_view_module":"@jupyter-widgets/base","_view_module_version":"1.2.0","_view_name":"LayoutView","align_content":null,"align_items":null,"align_self":null,"border":null,"bottom":null,"display":null,"flex":null,"flex_flow":null,"grid_area":null,"grid_auto_columns":null,"grid_auto_flow":null,"grid_auto_rows":null,"grid_column":null,"grid_gap":null,"grid_row":null,"grid_template_areas":null,"grid_template_columns":null,"grid_template_rows":null,"height":null,"justify_content":null,"justify_items":null,"left":null,"margin":null,"max_height":null,"max_width":null,"min_height":null,"min_width":null,"object_fit":null,"object_position":null,"order":null,"overflow":null,"overflow_x":null,"overflow_y":null,"padding":null,"right":null,"top":null,"visibility":null,"width":null}},"d2555ebdd173497a9f49054f2ca82793":{"model_module":"@jupyter-widgets/controls","model_name":"DescriptionStyleModel","model_module_version":"1.5.0","state":{"_model_module":"@jupyter-widgets/controls","_model_module_version":"1.5.0","_model_name":"DescriptionStyleModel","_view_count":null,"_view_module":"@jupyter-widgets/base","_view_module_version":"1.2.0","_view_name":"StyleView","description_width":""}},"b3ffa36739ec4c5c9d0f0690e9920d19":{"model_module":"@jupyter-widgets/base","model_name":"LayoutModel","model_module_version":"1.2.0","state":{"_model_module":"@jupyter-widgets/base","_model_module_version":"1.2.0","_model_name":"LayoutModel","_view_count":null,"_view_module":"@jupyter-widgets/base","_view_module_version":"1.2.0","_view_name":"LayoutView","align_content":null,"align_items":null,"align_self":null,"border":null,"bottom":null,"display":null,"flex":null,"flex_flow":null,"grid_area":null,"grid_auto_columns":null,"grid_auto_flow":null,"grid_auto_rows":null,"grid_column":null,"grid_gap":null,"grid_row":null,"grid_template_areas":null,"grid_template_columns":null,"grid_template_rows":null,"height":null,"justify_content":null,"justify_items":null,"left":null,"margin":null,"max_height":null,"max_width":null,"min_height":null,"min_width":null,"object_fit":null,"object_position":null,"order":null,"overflow":null,"overflow_x":null,"overflow_y":null,"padding":null,"right":null,"top":null,"visibility":null,"width":null}},"b0bd56c6c26d49adac84eaaaeac75e9c":{"model_module":"@jupyter-widgets/controls","model_name":"ProgressStyleModel","model_module_version":"1.5.0","state":{"_model_module":"@jupyter-widgets/controls","_model_module_version":"1.5.0","_model_name":"ProgressStyleModel","_view_count":null,"_view_module":"@jupyter-widgets/base","_view_module_version":"1.2.0","_view_name":"StyleView","bar_color":null,"description_width":""}},"8a84f6f970ee41ebb69f82aa2a006f8a":{"model_module":"@jupyter-widgets/base","model_name":"LayoutModel","model_module_version":"1.2.0","state":{"_model_module":"@jupyter-widgets/base","_model_module_version":"1.2.0","_model_name":"LayoutModel","_view_count":null,"_view_module":"@jupyter-widgets/base","_view_module_version":"1.2.0","_view_name":"LayoutView","align_content":null,"align_items":null,"align_self":null,"border":null,"bottom":null,"display":null,"flex":null,"flex_flow":null,"grid_area":null,"grid_auto_columns":null,"grid_auto_flow":null,"grid_auto_rows":null,"grid_column":null,"grid_gap":null,"grid_row":null,"grid_template_areas":null,"grid_template_columns":null,"grid_template_rows":null,"height":null,"justify_content":null,"justify_items":null,"left":null,"margin":null,"max_height":null,"max_width":null,"min_height":null,"min_width":null,"object_fit":null,"object_position":null,"order":null,"overflow":null,"overflow_x":null,"overflow_y":null,"padding":null,"right":null,"top":null,"visibility":null,"width":null}},"ce1790d859da42fe8dfe59dbe7c9d232":{"model_module":"@jupyter-widgets/controls","model_name":"DescriptionStyleModel","model_module_version":"1.5.0","state":{"_model_module":"@jupyter-widgets/controls","_model_module_version":"1.5.0","_model_name":"DescriptionStyleModel","_view_count":null,"_view_module":"@jupyter-widgets/base","_view_module_version":"1.2.0","_view_name":"StyleView","description_width":""}},"3cb8c9bc538e47108f56a375a61843dc":{"model_module":"@jupyter-widgets/controls","model_name":"HBoxModel","model_module_version":"1.5.0","state":{"_dom_classes":[],"_model_module":"@jupyter-widgets/controls","_model_module_version":"1.5.0","_model_name":"HBoxModel","_view_count":null,"_view_module":"@jupyter-widgets/controls","_view_module_version":"1.5.0","_view_name":"HBoxView","box_style":"","children":["IPY_MODEL_de5b309afba74b2994887b655a785740","IPY_MODEL_d8f1a2b25b9e4aa38bb9b360e635a0e1","IPY_MODEL_c76733e8e9444e05aeb16f749d22e101"],"layout":"IPY_MODEL_a424e4dc9ff444ee9e91e18f3811a0ba"}},"de5b309afba74b2994887b655a785740":{"model_module":"@jupyter-widgets/controls","model_name":"HTMLModel","model_module_version":"1.5.0","state":{"_dom_classes":[],"_model_module":"@jupyter-widgets/controls","_model_module_version":"1.5.0","_model_name":"HTMLModel","_view_count":null,"_view_module":"@jupyter-widgets/controls","_view_module_version":"1.5.0","_view_name":"HTMLView","description":"","description_tooltip":null,"layout":"IPY_MODEL_02631df0e525476198fab343808cf032","placeholder":"​","style":"IPY_MODEL_7e491dbf2a9d4dbeb0b456bb489ce642","value":"100%"}},"d8f1a2b25b9e4aa38bb9b360e635a0e1":{"model_module":"@jupyter-widgets/controls","model_name":"FloatProgressModel","model_module_version":"1.5.0","state":{"_dom_classes":[],"_model_module":"@jupyter-widgets/controls","_model_module_version":"1.5.0","_model_name":"FloatProgressModel","_view_count":null,"_view_module":"@jupyter-widgets/controls","_view_module_version":"1.5.0","_view_name":"ProgressView","bar_style":"success","description":"","description_tooltip":null,"layout":"IPY_MODEL_d7cb13eae183456685915195cfc39672","max":1648877,"min":0,"orientation":"horizontal","style":"IPY_MODEL_d8df861c33d44b2fbd9d96d42c797025","value":1648877}},"c76733e8e9444e05aeb16f749d22e101":{"model_module":"@jupyter-widgets/controls","model_name":"HTMLModel","model_module_version":"1.5.0","state":{"_dom_classes":[],"_model_module":"@jupyter-widgets/controls","_model_module_version":"1.5.0","_model_name":"HTMLModel","_view_count":null,"_view_module":"@jupyter-widgets/controls","_view_module_version":"1.5.0","_view_name":"HTMLView","description":"","description_tooltip":null,"layout":"IPY_MODEL_0320ce9f267f450692259fa6e985e848","placeholder":"​","style":"IPY_MODEL_8c5be51ac95f40a5aeb7bab19b1b7ee9","value":" 1648877/1648877 [00:00&lt;00:00, 20564037.34it/s]"}},"a424e4dc9ff444ee9e91e18f3811a0ba":{"model_module":"@jupyter-widgets/base","model_name":"LayoutModel","model_module_version":"1.2.0","state":{"_model_module":"@jupyter-widgets/base","_model_module_version":"1.2.0","_model_name":"LayoutModel","_view_count":null,"_view_module":"@jupyter-widgets/base","_view_module_version":"1.2.0","_view_name":"LayoutView","align_content":null,"align_items":null,"align_self":null,"border":null,"bottom":null,"display":null,"flex":null,"flex_flow":null,"grid_area":null,"grid_auto_columns":null,"grid_auto_flow":null,"grid_auto_rows":null,"grid_column":null,"grid_gap":null,"grid_row":null,"grid_template_areas":null,"grid_template_columns":null,"grid_template_rows":null,"height":null,"justify_content":null,"justify_items":null,"left":null,"margin":null,"max_height":null,"max_width":null,"min_height":null,"min_width":null,"object_fit":null,"object_position":null,"order":null,"overflow":null,"overflow_x":null,"overflow_y":null,"padding":null,"right":null,"top":null,"visibility":null,"width":null}},"02631df0e525476198fab343808cf032":{"model_module":"@jupyter-widgets/base","model_name":"LayoutModel","model_module_version":"1.2.0","state":{"_model_module":"@jupyter-widgets/base","_model_module_version":"1.2.0","_model_name":"LayoutModel","_view_count":null,"_view_module":"@jupyter-widgets/base","_view_module_version":"1.2.0","_view_name":"LayoutView","align_content":null,"align_items":null,"align_self":null,"border":null,"bottom":null,"display":null,"flex":null,"flex_flow":null,"grid_area":null,"grid_auto_columns":null,"grid_auto_flow":null,"grid_auto_rows":null,"grid_column":null,"grid_gap":null,"grid_row":null,"grid_template_areas":null,"grid_template_columns":null,"grid_template_rows":null,"height":null,"justify_content":null,"justify_items":null,"left":null,"margin":null,"max_height":null,"max_width":null,"min_height":null,"min_width":null,"object_fit":null,"object_position":null,"order":null,"overflow":null,"overflow_x":null,"overflow_y":null,"padding":null,"right":null,"top":null,"visibility":null,"width":null}},"7e491dbf2a9d4dbeb0b456bb489ce642":{"model_module":"@jupyter-widgets/controls","model_name":"DescriptionStyleModel","model_module_version":"1.5.0","state":{"_model_module":"@jupyter-widgets/controls","_model_module_version":"1.5.0","_model_name":"DescriptionStyleModel","_view_count":null,"_view_module":"@jupyter-widgets/base","_view_module_version":"1.2.0","_view_name":"StyleView","description_width":""}},"d7cb13eae183456685915195cfc39672":{"model_module":"@jupyter-widgets/base","model_name":"LayoutModel","model_module_version":"1.2.0","state":{"_model_module":"@jupyter-widgets/base","_model_module_version":"1.2.0","_model_name":"LayoutModel","_view_count":null,"_view_module":"@jupyter-widgets/base","_view_module_version":"1.2.0","_view_name":"LayoutView","align_content":null,"align_items":null,"align_self":null,"border":null,"bottom":null,"display":null,"flex":null,"flex_flow":null,"grid_area":null,"grid_auto_columns":null,"grid_auto_flow":null,"grid_auto_rows":null,"grid_column":null,"grid_gap":null,"grid_row":null,"grid_template_areas":null,"grid_template_columns":null,"grid_template_rows":null,"height":null,"justify_content":null,"justify_items":null,"left":null,"margin":null,"max_height":null,"max_width":null,"min_height":null,"min_width":null,"object_fit":null,"object_position":null,"order":null,"overflow":null,"overflow_x":null,"overflow_y":null,"padding":null,"right":null,"top":null,"visibility":null,"width":null}},"d8df861c33d44b2fbd9d96d42c797025":{"model_module":"@jupyter-widgets/controls","model_name":"ProgressStyleModel","model_module_version":"1.5.0","state":{"_model_module":"@jupyter-widgets/controls","_model_module_version":"1.5.0","_model_name":"ProgressStyleModel","_view_count":null,"_view_module":"@jupyter-widgets/base","_view_module_version":"1.2.0","_view_name":"StyleView","bar_color":null,"description_width":""}},"0320ce9f267f450692259fa6e985e848":{"model_module":"@jupyter-widgets/base","model_name":"LayoutModel","model_module_version":"1.2.0","state":{"_model_module":"@jupyter-widgets/base","_model_module_version":"1.2.0","_model_name":"LayoutModel","_view_count":null,"_view_module":"@jupyter-widgets/base","_view_module_version":"1.2.0","_view_name":"LayoutView","align_content":null,"align_items":null,"align_self":null,"border":null,"bottom":null,"display":null,"flex":null,"flex_flow":null,"grid_area":null,"grid_auto_columns":null,"grid_auto_flow":null,"grid_auto_rows":null,"grid_column":null,"grid_gap":null,"grid_row":null,"grid_template_areas":null,"grid_template_columns":null,"grid_template_rows":null,"height":null,"justify_content":null,"justify_items":null,"left":null,"margin":null,"max_height":null,"max_width":null,"min_height":null,"min_width":null,"object_fit":null,"object_position":null,"order":null,"overflow":null,"overflow_x":null,"overflow_y":null,"padding":null,"right":null,"top":null,"visibility":null,"width":null}},"8c5be51ac95f40a5aeb7bab19b1b7ee9":{"model_module":"@jupyter-widgets/controls","model_name":"DescriptionStyleModel","model_module_version":"1.5.0","state":{"_model_module":"@jupyter-widgets/controls","_model_module_version":"1.5.0","_model_name":"DescriptionStyleModel","_view_count":null,"_view_module":"@jupyter-widgets/base","_view_module_version":"1.2.0","_view_name":"StyleView","description_width":""}},"82bbfe059d2443e6aecefe547f675843":{"model_module":"@jupyter-widgets/controls","model_name":"HBoxModel","model_module_version":"1.5.0","state":{"_dom_classes":[],"_model_module":"@jupyter-widgets/controls","_model_module_version":"1.5.0","_model_name":"HBoxModel","_view_count":null,"_view_module":"@jupyter-widgets/controls","_view_module_version":"1.5.0","_view_name":"HBoxView","box_style":"","children":["IPY_MODEL_c254657012b84acf9326e55d7e842d09","IPY_MODEL_56351b86306d402984d6ec489f12cdb1","IPY_MODEL_13422fcd179a4792b9b94c173667958e"],"layout":"IPY_MODEL_57a5d6d615a847c19eec394b14db6b2d"}},"c254657012b84acf9326e55d7e842d09":{"model_module":"@jupyter-widgets/controls","model_name":"HTMLModel","model_module_version":"1.5.0","state":{"_dom_classes":[],"_model_module":"@jupyter-widgets/controls","_model_module_version":"1.5.0","_model_name":"HTMLModel","_view_count":null,"_view_module":"@jupyter-widgets/controls","_view_module_version":"1.5.0","_view_name":"HTMLView","description":"","description_tooltip":null,"layout":"IPY_MODEL_2ea85461d5654243b12e1c088dbeb036","placeholder":"​","style":"IPY_MODEL_b692a33348a24c74a201325b8b0699c5","value":"100%"}},"56351b86306d402984d6ec489f12cdb1":{"model_module":"@jupyter-widgets/controls","model_name":"FloatProgressModel","model_module_version":"1.5.0","state":{"_dom_classes":[],"_model_module":"@jupyter-widgets/controls","_model_module_version":"1.5.0","_model_name":"FloatProgressModel","_view_count":null,"_view_module":"@jupyter-widgets/controls","_view_module_version":"1.5.0","_view_name":"ProgressView","bar_style":"success","description":"","description_tooltip":null,"layout":"IPY_MODEL_8111287f856643548d03e1670a82065f","max":4542,"min":0,"orientation":"horizontal","style":"IPY_MODEL_a5808ce132484f5da81fabf5a2bc335c","value":4542}},"13422fcd179a4792b9b94c173667958e":{"model_module":"@jupyter-widgets/controls","model_name":"HTMLModel","model_module_version":"1.5.0","state":{"_dom_classes":[],"_model_module":"@jupyter-widgets/controls","_model_module_version":"1.5.0","_model_name":"HTMLModel","_view_count":null,"_view_module":"@jupyter-widgets/controls","_view_module_version":"1.5.0","_view_name":"HTMLView","description":"","description_tooltip":null,"layout":"IPY_MODEL_5ecc7186a0874145bce0655c99a51c44","placeholder":"​","style":"IPY_MODEL_6071a8fa5dc64f8fbfa05d1096134610","value":" 4542/4542 [00:00&lt;00:00, 380417.12it/s]"}},"57a5d6d615a847c19eec394b14db6b2d":{"model_module":"@jupyter-widgets/base","model_name":"LayoutModel","model_module_version":"1.2.0","state":{"_model_module":"@jupyter-widgets/base","_model_module_version":"1.2.0","_model_name":"LayoutModel","_view_count":null,"_view_module":"@jupyter-widgets/base","_view_module_version":"1.2.0","_view_name":"LayoutView","align_content":null,"align_items":null,"align_self":null,"border":null,"bottom":null,"display":null,"flex":null,"flex_flow":null,"grid_area":null,"grid_auto_columns":null,"grid_auto_flow":null,"grid_auto_rows":null,"grid_column":null,"grid_gap":null,"grid_row":null,"grid_template_areas":null,"grid_template_columns":null,"grid_template_rows":null,"height":null,"justify_content":null,"justify_items":null,"left":null,"margin":null,"max_height":null,"max_width":null,"min_height":null,"min_width":null,"object_fit":null,"object_position":null,"order":null,"overflow":null,"overflow_x":null,"overflow_y":null,"padding":null,"right":null,"top":null,"visibility":null,"width":null}},"2ea85461d5654243b12e1c088dbeb036":{"model_module":"@jupyter-widgets/base","model_name":"LayoutModel","model_module_version":"1.2.0","state":{"_model_module":"@jupyter-widgets/base","_model_module_version":"1.2.0","_model_name":"LayoutModel","_view_count":null,"_view_module":"@jupyter-widgets/base","_view_module_version":"1.2.0","_view_name":"LayoutView","align_content":null,"align_items":null,"align_self":null,"border":null,"bottom":null,"display":null,"flex":null,"flex_flow":null,"grid_area":null,"grid_auto_columns":null,"grid_auto_flow":null,"grid_auto_rows":null,"grid_column":null,"grid_gap":null,"grid_row":null,"grid_template_areas":null,"grid_template_columns":null,"grid_template_rows":null,"height":null,"justify_content":null,"justify_items":null,"left":null,"margin":null,"max_height":null,"max_width":null,"min_height":null,"min_width":null,"object_fit":null,"object_position":null,"order":null,"overflow":null,"overflow_x":null,"overflow_y":null,"padding":null,"right":null,"top":null,"visibility":null,"width":null}},"b692a33348a24c74a201325b8b0699c5":{"model_module":"@jupyter-widgets/controls","model_name":"DescriptionStyleModel","model_module_version":"1.5.0","state":{"_model_module":"@jupyter-widgets/controls","_model_module_version":"1.5.0","_model_name":"DescriptionStyleModel","_view_count":null,"_view_module":"@jupyter-widgets/base","_view_module_version":"1.2.0","_view_name":"StyleView","description_width":""}},"8111287f856643548d03e1670a82065f":{"model_module":"@jupyter-widgets/base","model_name":"LayoutModel","model_module_version":"1.2.0","state":{"_model_module":"@jupyter-widgets/base","_model_module_version":"1.2.0","_model_name":"LayoutModel","_view_count":null,"_view_module":"@jupyter-widgets/base","_view_module_version":"1.2.0","_view_name":"LayoutView","align_content":null,"align_items":null,"align_self":null,"border":null,"bottom":null,"display":null,"flex":null,"flex_flow":null,"grid_area":null,"grid_auto_columns":null,"grid_auto_flow":null,"grid_auto_rows":null,"grid_column":null,"grid_gap":null,"grid_row":null,"grid_template_areas":null,"grid_template_columns":null,"grid_template_rows":null,"height":null,"justify_content":null,"justify_items":null,"left":null,"margin":null,"max_height":null,"max_width":null,"min_height":null,"min_width":null,"object_fit":null,"object_position":null,"order":null,"overflow":null,"overflow_x":null,"overflow_y":null,"padding":null,"right":null,"top":null,"visibility":null,"width":null}},"a5808ce132484f5da81fabf5a2bc335c":{"model_module":"@jupyter-widgets/controls","model_name":"ProgressStyleModel","model_module_version":"1.5.0","state":{"_model_module":"@jupyter-widgets/controls","_model_module_version":"1.5.0","_model_name":"ProgressStyleModel","_view_count":null,"_view_module":"@jupyter-widgets/base","_view_module_version":"1.2.0","_view_name":"StyleView","bar_color":null,"description_width":""}},"5ecc7186a0874145bce0655c99a51c44":{"model_module":"@jupyter-widgets/base","model_name":"LayoutModel","model_module_version":"1.2.0","state":{"_model_module":"@jupyter-widgets/base","_model_module_version":"1.2.0","_model_name":"LayoutModel","_view_count":null,"_view_module":"@jupyter-widgets/base","_view_module_version":"1.2.0","_view_name":"LayoutView","align_content":null,"align_items":null,"align_self":null,"border":null,"bottom":null,"display":null,"flex":null,"flex_flow":null,"grid_area":null,"grid_auto_columns":null,"grid_auto_flow":null,"grid_auto_rows":null,"grid_column":null,"grid_gap":null,"grid_row":null,"grid_template_areas":null,"grid_template_columns":null,"grid_template_rows":null,"height":null,"justify_content":null,"justify_items":null,"left":null,"margin":null,"max_height":null,"max_width":null,"min_height":null,"min_width":null,"object_fit":null,"object_position":null,"order":null,"overflow":null,"overflow_x":null,"overflow_y":null,"padding":null,"right":null,"top":null,"visibility":null,"width":null}},"6071a8fa5dc64f8fbfa05d1096134610":{"model_module":"@jupyter-widgets/controls","model_name":"DescriptionStyleModel","model_module_version":"1.5.0","state":{"_model_module":"@jupyter-widgets/controls","_model_module_version":"1.5.0","_model_name":"DescriptionStyleModel","_view_count":null,"_view_module":"@jupyter-widgets/base","_view_module_version":"1.2.0","_view_name":"StyleView","description_width":""}}}}},"nbformat":4,"nbformat_minor":0}
\ No newline at end of file