diff --git a/.gitignore b/.gitignore
index f3436fe1fd3e8a7064887098b38e50dfda48b27d..f50e97646d664513f94d61a7d165e1a497cb8bab 100644
--- a/.gitignore
+++ b/.gitignore
@@ -1,9 +1,8 @@
-*.jpg
 .DS_Store
 
 # Data
 data/*
-transfer_learning/hymenoptera_data/*
+hymenoptera_data/*
 
 # Torch model
 *.pt
diff --git a/README.md b/README.md
index 2e65c03e17a8003f258aa4bfbc23e78017a5346b..fb48588d75d8c435169716b921b19ca89e91e637 100644
--- a/README.md
+++ b/README.md
@@ -1,9 +1,5 @@
 # Image classification - Zhengfei ZHANG
 
-This project consists of my solution for the image classification assignment.
-
-If you need to run the code, I suggest you doing it first (see [Usage](#usage)), then read the rest of this file for details and explanations while the program is running, as it is rather time consuming.
-
 ## Table of Contents
 
 - [Prerequisites](#prerequisites)
diff --git a/TD2 Deep Learning.ipynb b/TD2 Deep Learning.ipynb
index 5359381472463223442fb1e4391f870e87f84f25..b6b25f23927daaba2995a2a72c39bfc6a41f4d35 100644
--- a/TD2 Deep Learning.ipynb	
+++ b/TD2 Deep Learning.ipynb	
@@ -72,7 +72,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": null,
+   "execution_count": 2,
    "id": "26523cec",
    "metadata": {},
    "outputs": [],
@@ -87,7 +87,13 @@
     "import matplotlib.pyplot as plt\n",
     "import pandas as pd\n",
     "import torch.quantization\n",
-    "import os"
+    "import os\n",
+    "from torch.ao.quantization import QConfig, default_weight_observer\n",
+    "from torch.ao.quantization.observer import MinMaxObserver\n",
+    "import json\n",
+    "from PIL import Image\n",
+    "from torchvision.models import ResNet50_Weights\n",
+    "from torchvision.models import ConvNeXt_Tiny_Weights\n"
    ]
   },
   {
@@ -101,7 +107,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": null,
+   "execution_count": 3,
    "id": "b1950f0a",
    "metadata": {},
    "outputs": [
@@ -109,34 +115,34 @@
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "tensor([[-0.8420,  0.2845, -0.5074, -0.2304,  0.9752,  0.1160, -0.1176,  1.2489,\n",
-      "         -0.0740, -0.6623],\n",
-      "        [-0.7048, -0.7310,  0.0992,  0.5240,  1.4255, -0.4090, -1.1487, -0.4219,\n",
-      "          0.3874, -1.4008],\n",
-      "        [ 0.3871, -0.7297,  1.9117, -0.8532,  0.7785,  0.5915, -1.1458,  1.8627,\n",
-      "         -0.8876,  0.9125],\n",
-      "        [-1.0006, -0.6980, -1.7805,  0.6912, -1.4974, -0.2708, -0.4265,  1.0481,\n",
-      "          0.5749,  2.0555],\n",
-      "        [-1.1896,  0.8106, -1.8687,  0.4707,  0.1825,  1.6100, -0.0680, -0.7637,\n",
-      "         -0.1938, -1.6465],\n",
-      "        [ 0.9084,  0.8280, -0.0489, -1.1519,  0.6441, -1.2523, -0.2103,  1.4040,\n",
-      "          0.8581,  0.8607],\n",
-      "        [-1.6026, -1.9086, -1.3032, -0.8562,  0.2943, -0.6440, -0.8224,  0.4703,\n",
-      "         -0.8826,  0.2067],\n",
-      "        [ 2.0093,  0.5328,  0.6202, -0.4025, -0.2234,  1.4939, -1.6875,  0.2266,\n",
-      "          0.4975, -0.1584],\n",
-      "        [ 0.8489, -0.4357, -1.6452,  0.5448,  0.9157,  0.5466, -1.2052,  0.3536,\n",
-      "         -0.1666, -1.4067],\n",
-      "        [ 0.6193,  0.6475, -0.3227, -0.1045, -0.5125,  0.8096,  0.4754,  0.9074,\n",
-      "         -1.3701, -0.3242],\n",
-      "        [-0.9476,  1.2364, -3.0577, -0.5216, -0.7069, -0.6643,  1.2480,  0.2512,\n",
-      "          0.6646,  0.1489],\n",
-      "        [ 1.0305, -1.2793,  1.1895,  0.2710,  0.3480,  0.2181, -1.4330,  1.2334,\n",
-      "          0.3133, -0.5289],\n",
-      "        [ 0.1155, -1.2805,  0.4161, -1.3375, -0.1451,  0.3332, -0.1306, -0.2068,\n",
-      "          0.9061,  0.6682],\n",
-      "        [-0.8853,  0.2078,  0.4097, -1.8620,  0.9968, -0.6517,  1.5025,  1.1775,\n",
-      "         -1.8511, -2.0210]])\n",
+      "tensor([[ 4.1946e-01,  5.9725e-01, -1.4673e+00, -1.2549e+00,  2.1341e+00,\n",
+      "          1.4049e+00,  2.7962e-01, -3.8009e-01, -8.5179e-01,  2.5305e-01],\n",
+      "        [-1.2753e-03, -1.9215e+00, -1.4006e+00,  2.6579e-01,  3.7250e-01,\n",
+      "          9.4500e-01, -1.6121e+00,  5.5914e-02, -2.0862e-01,  8.5373e-01],\n",
+      "        [ 1.0509e-01,  7.0349e-01,  4.1523e-01, -2.3220e-01, -6.5935e-01,\n",
+      "          7.7277e-02,  2.2612e-01, -3.5223e-01,  2.0450e+00,  8.8183e-01],\n",
+      "        [-1.5364e-01, -1.1983e+00,  1.5166e+00,  1.0890e+00, -2.1162e-01,\n",
+      "          1.7259e-01, -7.7122e-01,  1.0476e+00,  1.3434e+00,  1.1047e+00],\n",
+      "        [-1.2166e-01, -8.2374e-01,  1.7921e+00, -3.9473e-01,  8.7033e-01,\n",
+      "         -4.8496e-01,  1.4589e+00, -5.5162e-01, -4.0023e-01, -1.1884e+00],\n",
+      "        [-4.9660e-01, -1.4023e-01, -2.7122e-02, -4.8280e-01, -1.0802e-01,\n",
+      "          8.6243e-01,  2.6292e+00, -1.0442e+00,  4.9448e-01, -1.1326e+00],\n",
+      "        [-5.4170e-01, -1.3118e-01,  1.4431e+00,  5.0660e-01, -2.3256e+00,\n",
+      "          1.7130e-02,  8.8171e-01,  3.4277e-01,  3.3848e-01,  4.7178e-01],\n",
+      "        [-8.4633e-01,  2.2323e-01,  1.2476e+00,  5.0526e-01, -9.1749e-01,\n",
+      "         -1.6531e+00,  4.1303e-01,  6.4286e-01,  1.1903e+00, -1.8325e+00],\n",
+      "        [-9.4865e-01, -1.8500e+00, -7.1828e-02,  7.3542e-02,  4.2884e-01,\n",
+      "          1.3198e+00,  7.1335e-01,  2.0110e-01, -9.7183e-01, -5.3261e-01],\n",
+      "        [ 9.2111e-01, -8.9227e-01, -1.1001e-01,  7.5715e-01, -9.8357e-01,\n",
+      "          1.3816e-01, -8.5766e-01,  2.2164e-01,  1.9961e+00,  6.3121e-01],\n",
+      "        [ 1.0979e+00,  1.2840e+00, -1.2254e+00, -2.0575e-03, -2.6566e-01,\n",
+      "          1.4393e+00,  1.0752e+00, -1.3780e+00, -1.8148e-01,  5.3869e-01],\n",
+      "        [ 1.7080e+00,  1.7873e-01, -8.3003e-01, -6.5089e-01,  5.3965e-03,\n",
+      "          6.2050e-01, -8.9723e-01,  3.4774e-01,  6.3044e-02,  1.4476e-01],\n",
+      "        [-3.0380e-01, -1.2354e+00,  1.2475e-01, -8.3514e-01,  2.1636e-01,\n",
+      "          1.4750e+00, -3.0404e-01,  1.6147e+00, -2.8958e-01,  3.6248e-01],\n",
+      "        [-1.2371e+00, -1.4293e+00,  9.4313e-01,  1.1091e+00, -9.2057e-01,\n",
+      "         -3.7234e-01,  1.0788e+00, -3.1039e-01, -4.5472e-02,  5.1776e-01]])\n",
       "AlexNet(\n",
       "  (features): Sequential(\n",
       "    (0): Conv2d(3, 64, kernel_size=(11, 11), stride=(4, 4), padding=(2, 2))\n",
@@ -202,7 +208,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": null,
+   "execution_count": 4,
    "id": "6e18f2fd",
    "metadata": {},
    "outputs": [
@@ -236,7 +242,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": null,
+   "execution_count": 5,
    "id": "462666a2",
    "metadata": {},
    "outputs": [
@@ -313,7 +319,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": null,
+   "execution_count": 6,
    "id": "317bf070",
    "metadata": {},
    "outputs": [
@@ -330,7 +336,7 @@
        ")"
       ]
      },
-     "execution_count": 7,
+     "execution_count": 6,
      "metadata": {},
      "output_type": "execute_result"
     }
@@ -376,7 +382,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": null,
+   "execution_count": 7,
    "id": "4b53f229",
    "metadata": {},
    "outputs": [
@@ -384,49 +390,33 @@
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Epoch: 0 \tTraining Loss: 44.473933 \tValidation Loss: 39.620629\n",
-      "Validation loss decreased (inf --> 39.620629).  Saving model ...\n",
-      "Epoch: 1 \tTraining Loss: 35.544782 \tValidation Loss: 32.533757\n",
-      "Validation loss decreased (39.620629 --> 32.533757).  Saving model ...\n",
-      "Epoch: 2 \tTraining Loss: 30.859100 \tValidation Loss: 29.284232\n",
-      "Validation loss decreased (32.533757 --> 29.284232).  Saving model ...\n",
-      "Epoch: 3 \tTraining Loss: 28.244149 \tValidation Loss: 28.139195\n",
-      "Validation loss decreased (29.284232 --> 28.139195).  Saving model ...\n",
-      "Epoch: 4 \tTraining Loss: 26.283759 \tValidation Loss: 25.799773\n",
-      "Validation loss decreased (28.139195 --> 25.799773).  Saving model ...\n",
-      "Epoch: 5 \tTraining Loss: 24.848492 \tValidation Loss: 24.929654\n",
-      "Validation loss decreased (25.799773 --> 24.929654).  Saving model ...\n",
-      "Epoch: 6 \tTraining Loss: 23.681632 \tValidation Loss: 23.586609\n",
-      "Validation loss decreased (24.929654 --> 23.586609).  Saving model ...\n",
-      "Epoch: 7 \tTraining Loss: 22.641888 \tValidation Loss: 23.032703\n",
-      "Validation loss decreased (23.586609 --> 23.032703).  Saving model ...\n",
-      "Epoch: 8 \tTraining Loss: 21.752826 \tValidation Loss: 22.664754\n",
-      "Validation loss decreased (23.032703 --> 22.664754).  Saving model ...\n",
-      "Epoch: 9 \tTraining Loss: 20.981409 \tValidation Loss: 22.301936\n",
-      "Validation loss decreased (22.664754 --> 22.301936).  Saving model ...\n",
-      "Epoch: 10 \tTraining Loss: 20.292528 \tValidation Loss: 22.741102\n",
-      "Epoch: 11 \tTraining Loss: 19.607159 \tValidation Loss: 21.533517\n",
-      "Validation loss decreased (22.301936 --> 21.533517).  Saving model ...\n",
-      "Epoch: 12 \tTraining Loss: 18.932060 \tValidation Loss: 21.467511\n",
-      "Validation loss decreased (21.533517 --> 21.467511).  Saving model ...\n",
-      "Epoch: 13 \tTraining Loss: 18.342876 \tValidation Loss: 21.668419\n",
-      "Epoch: 14 \tTraining Loss: 17.725712 \tValidation Loss: 21.420723\n",
-      "Validation loss decreased (21.467511 --> 21.420723).  Saving model ...\n",
-      "Epoch: 15 \tTraining Loss: 17.228202 \tValidation Loss: 21.657052\n",
-      "Epoch: 16 \tTraining Loss: 16.635705 \tValidation Loss: 22.080738\n",
-      "Epoch: 17 \tTraining Loss: 16.082365 \tValidation Loss: 21.646796\n",
-      "Epoch: 18 \tTraining Loss: 15.567858 \tValidation Loss: 22.053860\n",
-      "Epoch: 19 \tTraining Loss: 15.077309 \tValidation Loss: 22.270342\n",
-      "Epoch: 20 \tTraining Loss: 14.603599 \tValidation Loss: 22.214336\n",
-      "Epoch: 21 \tTraining Loss: 14.093810 \tValidation Loss: 22.724239\n",
-      "Epoch: 22 \tTraining Loss: 13.643105 \tValidation Loss: 22.612203\n",
-      "Epoch: 23 \tTraining Loss: 13.193473 \tValidation Loss: 23.833128\n",
-      "Epoch: 24 \tTraining Loss: 12.774464 \tValidation Loss: 24.365881\n",
-      "Epoch: 25 \tTraining Loss: 12.335211 \tValidation Loss: 24.674567\n",
-      "Epoch: 26 \tTraining Loss: 11.861359 \tValidation Loss: 24.542632\n",
-      "Epoch: 27 \tTraining Loss: 11.523480 \tValidation Loss: 25.236285\n",
-      "Epoch: 28 \tTraining Loss: 11.013934 \tValidation Loss: 26.543926\n",
-      "Epoch: 29 \tTraining Loss: 10.694415 \tValidation Loss: 26.362344\n"
+      "Epoch: 0 \tTraining Loss: 42.519634 \tValidation Loss: 36.655749\n",
+      "Validation loss decreased (inf --> 36.655749).  Saving model ...\n",
+      "Epoch: 1 \tTraining Loss: 33.525474 \tValidation Loss: 32.488665\n",
+      "Validation loss decreased (36.655749 --> 32.488665).  Saving model ...\n",
+      "Epoch: 2 \tTraining Loss: 30.212554 \tValidation Loss: 29.202218\n",
+      "Validation loss decreased (32.488665 --> 29.202218).  Saving model ...\n",
+      "Epoch: 3 \tTraining Loss: 28.229093 \tValidation Loss: 27.670834\n",
+      "Validation loss decreased (29.202218 --> 27.670834).  Saving model ...\n",
+      "Epoch: 4 \tTraining Loss: 26.704960 \tValidation Loss: 26.590415\n",
+      "Validation loss decreased (27.670834 --> 26.590415).  Saving model ...\n",
+      "Epoch: 5 \tTraining Loss: 25.400147 \tValidation Loss: 25.525508\n",
+      "Validation loss decreased (26.590415 --> 25.525508).  Saving model ...\n",
+      "Epoch: 6 \tTraining Loss: 24.347397 \tValidation Loss: 24.916307\n",
+      "Validation loss decreased (25.525508 --> 24.916307).  Saving model ...\n",
+      "Epoch: 7 \tTraining Loss: 23.344014 \tValidation Loss: 24.675999\n",
+      "Validation loss decreased (24.916307 --> 24.675999).  Saving model ...\n",
+      "Epoch: 8 \tTraining Loss: 22.443937 \tValidation Loss: 23.829740\n",
+      "Validation loss decreased (24.675999 --> 23.829740).  Saving model ...\n",
+      "Epoch: 9 \tTraining Loss: 21.620854 \tValidation Loss: 24.359353\n",
+      "Epoch: 10 \tTraining Loss: 20.750674 \tValidation Loss: 23.321183\n",
+      "Validation loss decreased (23.829740 --> 23.321183).  Saving model ...\n",
+      "Epoch: 11 \tTraining Loss: 20.063842 \tValidation Loss: 22.095903\n",
+      "Validation loss decreased (23.321183 --> 22.095903).  Saving model ...\n",
+      "Epoch: 12 \tTraining Loss: 19.389771 \tValidation Loss: 22.387120\n",
+      "Epoch: 13 \tTraining Loss: 18.747496 \tValidation Loss: 23.242739\n",
+      "Epoch: 14 \tTraining Loss: 18.107062 \tValidation Loss: 22.644315\n",
+      "Stopped early\n"
      ]
     }
    ],
@@ -522,13 +512,13 @@
   },
   {
    "cell_type": "code",
-   "execution_count": null,
+   "execution_count": 9,
    "id": "d39df818",
    "metadata": {},
    "outputs": [
     {
      "data": {
-      "image/png": "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",
+      "image/png": "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",
       "text/plain": [
        "<Figure size 640x480 with 1 Axes>"
       ]
@@ -538,7 +528,7 @@
     }
    ],
    "source": [
-    "plt.plot(range(n_epochs), train_loss_list)\n",
+    "plt.plot(range(len(train_loss_list)), train_loss_list)\n",
     "plt.xlabel(\"Epoch\")\n",
     "plt.ylabel(\"Loss\")\n",
     "plt.title(\"Performance of Model 1\")\n",
@@ -555,7 +545,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 31,
+   "execution_count": 10,
    "id": "e93efdfc",
    "metadata": {},
    "outputs": [
@@ -563,20 +553,20 @@
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Test Loss: 21.418785\n",
+      "Test Loss: 21.920984\n",
       "\n",
-      "Test Accuracy of airplane: 67% (677/1000)\n",
-      "Test Accuracy of automobile: 77% (770/1000)\n",
-      "Test Accuracy of  bird: 50% (503/1000)\n",
-      "Test Accuracy of   cat: 35% (354/1000)\n",
-      "Test Accuracy of  deer: 62% (623/1000)\n",
-      "Test Accuracy of   dog: 52% (525/1000)\n",
-      "Test Accuracy of  frog: 69% (696/1000)\n",
-      "Test Accuracy of horse: 68% (686/1000)\n",
-      "Test Accuracy of  ship: 80% (803/1000)\n",
-      "Test Accuracy of truck: 69% (698/1000)\n",
+      "Test Accuracy of airplane: 60% (605/1000)\n",
+      "Test Accuracy of automobile: 79% (796/1000)\n",
+      "Test Accuracy of  bird: 45% (451/1000)\n",
+      "Test Accuracy of   cat: 44% (440/1000)\n",
+      "Test Accuracy of  deer: 55% (556/1000)\n",
+      "Test Accuracy of   dog: 51% (512/1000)\n",
+      "Test Accuracy of  frog: 72% (726/1000)\n",
+      "Test Accuracy of horse: 68% (688/1000)\n",
+      "Test Accuracy of  ship: 74% (742/1000)\n",
+      "Test Accuracy of truck: 64% (641/1000)\n",
       "\n",
-      "Test Accuracy (Overall): 63% (6335/10000)\n"
+      "Test Accuracy (Overall): 61% (6157/10000)\n"
      ]
     }
    ],
@@ -661,7 +651,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": null,
+   "execution_count": 11,
    "id": "28da770d",
    "metadata": {},
    "outputs": [
@@ -680,7 +670,7 @@
        ")"
       ]
      },
-     "execution_count": 8,
+     "execution_count": 11,
      "metadata": {},
      "output_type": "execute_result"
     }
@@ -730,7 +720,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": null,
+   "execution_count": 12,
    "id": "210b2852",
    "metadata": {},
    "outputs": [
@@ -738,46 +728,50 @@
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Epoch: 0 \tTraining Loss: 44.427319 \tValidation Loss: 40.379719\n",
-      "Validation loss decreased (inf --> 40.379719).  Saving model ...\n",
-      "Epoch: 1 \tTraining Loss: 38.668627 \tValidation Loss: 35.563413\n",
-      "Validation loss decreased (40.379719 --> 35.563413).  Saving model ...\n",
-      "Epoch: 2 \tTraining Loss: 34.096305 \tValidation Loss: 31.245042\n",
-      "Validation loss decreased (35.563413 --> 31.245042).  Saving model ...\n",
-      "Epoch: 3 \tTraining Loss: 31.116184 \tValidation Loss: 29.127113\n",
-      "Validation loss decreased (31.245042 --> 29.127113).  Saving model ...\n",
-      "Epoch: 4 \tTraining Loss: 28.863355 \tValidation Loss: 27.261098\n",
-      "Validation loss decreased (29.127113 --> 27.261098).  Saving model ...\n",
-      "Epoch: 5 \tTraining Loss: 26.840526 \tValidation Loss: 24.582053\n",
-      "Validation loss decreased (27.261098 --> 24.582053).  Saving model ...\n",
-      "Epoch: 6 \tTraining Loss: 25.091524 \tValidation Loss: 23.448411\n",
-      "Validation loss decreased (24.582053 --> 23.448411).  Saving model ...\n",
-      "Epoch: 7 \tTraining Loss: 23.575481 \tValidation Loss: 22.002271\n",
-      "Validation loss decreased (23.448411 --> 22.002271).  Saving model ...\n",
-      "Epoch: 8 \tTraining Loss: 22.132604 \tValidation Loss: 21.072783\n",
-      "Validation loss decreased (22.002271 --> 21.072783).  Saving model ...\n",
-      "Epoch: 9 \tTraining Loss: 20.872915 \tValidation Loss: 19.869785\n",
-      "Validation loss decreased (21.072783 --> 19.869785).  Saving model ...\n",
-      "Epoch: 10 \tTraining Loss: 19.703448 \tValidation Loss: 18.738881\n",
-      "Validation loss decreased (19.869785 --> 18.738881).  Saving model ...\n",
-      "Epoch: 11 \tTraining Loss: 18.590030 \tValidation Loss: 17.896260\n",
-      "Validation loss decreased (18.738881 --> 17.896260).  Saving model ...\n",
-      "Epoch: 12 \tTraining Loss: 17.555201 \tValidation Loss: 17.599109\n",
-      "Validation loss decreased (17.896260 --> 17.599109).  Saving model ...\n",
-      "Epoch: 13 \tTraining Loss: 16.532635 \tValidation Loss: 17.089988\n",
-      "Validation loss decreased (17.599109 --> 17.089988).  Saving model ...\n",
-      "Epoch: 14 \tTraining Loss: 15.708936 \tValidation Loss: 16.946565\n",
-      "Validation loss decreased (17.089988 --> 16.946565).  Saving model ...\n",
-      "Epoch: 15 \tTraining Loss: 14.713673 \tValidation Loss: 16.396082\n",
-      "Validation loss decreased (16.946565 --> 16.396082).  Saving model ...\n",
-      "Epoch: 16 \tTraining Loss: 13.923363 \tValidation Loss: 16.574588\n",
-      "Epoch: 17 \tTraining Loss: 13.109490 \tValidation Loss: 16.013181\n",
-      "Validation loss decreased (16.396082 --> 16.013181).  Saving model ...\n",
-      "Epoch: 18 \tTraining Loss: 12.363001 \tValidation Loss: 15.954380\n",
-      "Validation loss decreased (16.013181 --> 15.954380).  Saving model ...\n",
-      "Epoch: 19 \tTraining Loss: 11.658812 \tValidation Loss: 16.106396\n",
-      "Epoch: 20 \tTraining Loss: 10.857707 \tValidation Loss: 16.401605\n",
-      "Epoch: 21 \tTraining Loss: 10.176664 \tValidation Loss: 16.437715\n"
+      "Epoch: 0 \tTraining Loss: 45.950050 \tValidation Loss: 45.313403\n",
+      "Validation loss decreased (inf --> 45.313403).  Saving model ...\n",
+      "Epoch: 1 \tTraining Loss: 40.787581 \tValidation Loss: 36.139096\n",
+      "Validation loss decreased (45.313403 --> 36.139096).  Saving model ...\n",
+      "Epoch: 2 \tTraining Loss: 34.447005 \tValidation Loss: 32.414839\n",
+      "Validation loss decreased (36.139096 --> 32.414839).  Saving model ...\n",
+      "Epoch: 3 \tTraining Loss: 31.198155 \tValidation Loss: 28.597152\n",
+      "Validation loss decreased (32.414839 --> 28.597152).  Saving model ...\n",
+      "Epoch: 4 \tTraining Loss: 28.935899 \tValidation Loss: 27.656532\n",
+      "Validation loss decreased (28.597152 --> 27.656532).  Saving model ...\n",
+      "Epoch: 5 \tTraining Loss: 27.173148 \tValidation Loss: 26.000456\n",
+      "Validation loss decreased (27.656532 --> 26.000456).  Saving model ...\n",
+      "Epoch: 6 \tTraining Loss: 25.591705 \tValidation Loss: 23.975792\n",
+      "Validation loss decreased (26.000456 --> 23.975792).  Saving model ...\n",
+      "Epoch: 7 \tTraining Loss: 24.003946 \tValidation Loss: 22.047517\n",
+      "Validation loss decreased (23.975792 --> 22.047517).  Saving model ...\n",
+      "Epoch: 8 \tTraining Loss: 22.563493 \tValidation Loss: 21.478709\n",
+      "Validation loss decreased (22.047517 --> 21.478709).  Saving model ...\n",
+      "Epoch: 9 \tTraining Loss: 21.276739 \tValidation Loss: 20.395124\n",
+      "Validation loss decreased (21.478709 --> 20.395124).  Saving model ...\n",
+      "Epoch: 10 \tTraining Loss: 19.976689 \tValidation Loss: 19.261183\n",
+      "Validation loss decreased (20.395124 --> 19.261183).  Saving model ...\n",
+      "Epoch: 11 \tTraining Loss: 18.898193 \tValidation Loss: 19.134879\n",
+      "Validation loss decreased (19.261183 --> 19.134879).  Saving model ...\n",
+      "Epoch: 12 \tTraining Loss: 17.755759 \tValidation Loss: 18.175134\n",
+      "Validation loss decreased (19.134879 --> 18.175134).  Saving model ...\n",
+      "Epoch: 13 \tTraining Loss: 16.911120 \tValidation Loss: 18.412602\n",
+      "Epoch: 14 \tTraining Loss: 15.897645 \tValidation Loss: 17.411980\n",
+      "Validation loss decreased (18.175134 --> 17.411980).  Saving model ...\n",
+      "Epoch: 15 \tTraining Loss: 15.045171 \tValidation Loss: 17.193695\n",
+      "Validation loss decreased (17.411980 --> 17.193695).  Saving model ...\n",
+      "Epoch: 16 \tTraining Loss: 14.215693 \tValidation Loss: 17.198453\n",
+      "Epoch: 17 \tTraining Loss: 13.413932 \tValidation Loss: 17.039673\n",
+      "Validation loss decreased (17.193695 --> 17.039673).  Saving model ...\n",
+      "Epoch: 18 \tTraining Loss: 12.662231 \tValidation Loss: 17.201798\n",
+      "Epoch: 19 \tTraining Loss: 11.924725 \tValidation Loss: 17.324246\n",
+      "Epoch: 20 \tTraining Loss: 11.173872 \tValidation Loss: 16.782957\n",
+      "Validation loss decreased (17.039673 --> 16.782957).  Saving model ...\n",
+      "Epoch: 21 \tTraining Loss: 10.370130 \tValidation Loss: 16.526257\n",
+      "Validation loss decreased (16.782957 --> 16.526257).  Saving model ...\n",
+      "Epoch: 22 \tTraining Loss: 9.688294 \tValidation Loss: 17.352934\n",
+      "Epoch: 23 \tTraining Loss: 9.047468 \tValidation Loss: 17.994093\n",
+      "Epoch: 24 \tTraining Loss: 8.550826 \tValidation Loss: 18.633177\n",
+      "Stopped early\n"
      ]
     }
    ],
@@ -857,13 +851,13 @@
   },
   {
    "cell_type": "code",
-   "execution_count": null,
+   "execution_count": 13,
    "id": "557508e9",
    "metadata": {},
    "outputs": [
     {
      "data": {
-      "image/png": "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",
+      "image/png": "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",
       "text/plain": [
        "<Figure size 640x480 with 1 Axes>"
       ]
@@ -882,7 +876,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 68,
+   "execution_count": 14,
    "id": "9f0a4c3f",
    "metadata": {},
    "outputs": [
@@ -890,20 +884,20 @@
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Test Loss: 16.079455\n",
+      "Test Loss: 16.602481\n",
       "\n",
-      "Test Accuracy of airplane: 79% (793/1000)\n",
-      "Test Accuracy of automobile: 80% (800/1000)\n",
-      "Test Accuracy of  bird: 60% (601/1000)\n",
-      "Test Accuracy of   cat: 53% (530/1000)\n",
-      "Test Accuracy of  deer: 59% (591/1000)\n",
-      "Test Accuracy of   dog: 61% (619/1000)\n",
-      "Test Accuracy of  frog: 85% (851/1000)\n",
-      "Test Accuracy of horse: 78% (783/1000)\n",
-      "Test Accuracy of  ship: 85% (855/1000)\n",
-      "Test Accuracy of truck: 85% (854/1000)\n",
+      "Test Accuracy of airplane: 81% (816/1000)\n",
+      "Test Accuracy of automobile: 87% (873/1000)\n",
+      "Test Accuracy of  bird: 63% (636/1000)\n",
+      "Test Accuracy of   cat: 51% (517/1000)\n",
+      "Test Accuracy of  deer: 70% (702/1000)\n",
+      "Test Accuracy of   dog: 59% (590/1000)\n",
+      "Test Accuracy of  frog: 76% (769/1000)\n",
+      "Test Accuracy of horse: 72% (723/1000)\n",
+      "Test Accuracy of  ship: 86% (865/1000)\n",
+      "Test Accuracy of truck: 77% (772/1000)\n",
       "\n",
-      "Test Accuracy (Overall): 72% (7277/10000)\n"
+      "Test Accuracy (Overall): 72% (7263/10000)\n"
      ]
     }
    ],
@@ -995,7 +989,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": null,
+   "execution_count": 15,
    "id": "ef623c26",
    "metadata": {},
    "outputs": [
@@ -1012,7 +1006,7 @@
        "2330946"
       ]
      },
-     "execution_count": 62,
+     "execution_count": 15,
      "metadata": {},
      "output_type": "execute_result"
     }
@@ -1039,7 +1033,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": null,
+   "execution_count": 16,
    "id": "c4c65d4b",
    "metadata": {},
    "outputs": [
@@ -1056,7 +1050,7 @@
        "659742"
       ]
      },
-     "execution_count": 66,
+     "execution_count": 16,
      "metadata": {},
      "output_type": "execute_result"
     }
@@ -1094,10 +1088,17 @@
   },
   {
    "cell_type": "code",
-   "execution_count": null,
+   "execution_count": 17,
    "id": "b0aed3cc",
    "metadata": {},
    "outputs": [
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "[W1204 14:41:35.780678000 qlinear_dynamic.cpp:251] Warning: Currently, qnnpack incorrectly ignores reduce_range when it is set to true; this may change in a future release. (function operator())\n"
+     ]
+    },
     {
      "data": {
       "text/html": [
@@ -1128,68 +1129,68 @@
        "    <tr>\n",
        "      <th>0</th>\n",
        "      <td>airplane</td>\n",
-       "      <td>79.3% (793/1000)</td>\n",
        "      <td>79.1% (791/1000)</td>\n",
+       "      <td>81.4% (814/1000)</td>\n",
        "    </tr>\n",
        "    <tr>\n",
        "      <th>1</th>\n",
        "      <td>automobile</td>\n",
-       "      <td>80.0% (800/1000)</td>\n",
-       "      <td>79.9% (799/1000)</td>\n",
+       "      <td>84.1% (841/1000)</td>\n",
+       "      <td>87.5% (875/1000)</td>\n",
        "    </tr>\n",
        "    <tr>\n",
        "      <th>2</th>\n",
        "      <td>bird</td>\n",
-       "      <td>60.1% (601/1000)</td>\n",
-       "      <td>60.1% (601/1000)</td>\n",
+       "      <td>59.9% (599/1000)</td>\n",
+       "      <td>63.4% (634/1000)</td>\n",
        "    </tr>\n",
        "    <tr>\n",
        "      <th>3</th>\n",
        "      <td>cat</td>\n",
-       "      <td>53.0% (530/1000)</td>\n",
-       "      <td>52.9% (529/1000)</td>\n",
+       "      <td>49.4% (494/1000)</td>\n",
+       "      <td>51.7% (517/1000)</td>\n",
        "    </tr>\n",
        "    <tr>\n",
        "      <th>4</th>\n",
        "      <td>deer</td>\n",
-       "      <td>59.1% (591/1000)</td>\n",
-       "      <td>59.0% (590/1000)</td>\n",
+       "      <td>67.1% (671/1000)</td>\n",
+       "      <td>70.0% (700/1000)</td>\n",
        "    </tr>\n",
        "    <tr>\n",
        "      <th>5</th>\n",
        "      <td>dog</td>\n",
-       "      <td>61.9% (619/1000)</td>\n",
-       "      <td>61.2% (612/1000)</td>\n",
+       "      <td>56.7% (567/1000)</td>\n",
+       "      <td>59.1% (591/1000)</td>\n",
        "    </tr>\n",
        "    <tr>\n",
        "      <th>6</th>\n",
        "      <td>frog</td>\n",
-       "      <td>85.1% (851/1000)</td>\n",
-       "      <td>85.1% (851/1000)</td>\n",
+       "      <td>72.4% (724/1000)</td>\n",
+       "      <td>77.0% (770/1000)</td>\n",
        "    </tr>\n",
        "    <tr>\n",
        "      <th>7</th>\n",
        "      <td>horse</td>\n",
-       "      <td>78.3% (783/1000)</td>\n",
-       "      <td>78.1% (781/1000)</td>\n",
+       "      <td>68.0% (680/1000)</td>\n",
+       "      <td>72.6% (726/1000)</td>\n",
        "    </tr>\n",
        "    <tr>\n",
        "      <th>8</th>\n",
        "      <td>ship</td>\n",
-       "      <td>85.5% (855/1000)</td>\n",
-       "      <td>85.5% (855/1000)</td>\n",
+       "      <td>84.9% (849/1000)</td>\n",
+       "      <td>86.4% (864/1000)</td>\n",
        "    </tr>\n",
        "    <tr>\n",
        "      <th>9</th>\n",
        "      <td>truck</td>\n",
-       "      <td>85.4% (854/1000)</td>\n",
-       "      <td>85.5% (855/1000)</td>\n",
+       "      <td>74.7% (747/1000)</td>\n",
+       "      <td>77.2% (772/1000)</td>\n",
        "    </tr>\n",
        "    <tr>\n",
        "      <th>10</th>\n",
        "      <td>total</td>\n",
-       "      <td>72.77% (7277/10000)</td>\n",
-       "      <td>72.64% (7264/10000)</td>\n",
+       "      <td>69.63% (6963/10000)</td>\n",
+       "      <td>72.63% (7263/10000)</td>\n",
        "    </tr>\n",
        "  </tbody>\n",
        "</table>\n",
@@ -1197,20 +1198,20 @@
       ],
       "text/plain": [
        "         Class Accuracy (Initial Model) Accuracy (Quantized Model)\n",
-       "0     airplane         79.3% (793/1000)           79.1% (791/1000)\n",
-       "1   automobile         80.0% (800/1000)           79.9% (799/1000)\n",
-       "2         bird         60.1% (601/1000)           60.1% (601/1000)\n",
-       "3          cat         53.0% (530/1000)           52.9% (529/1000)\n",
-       "4         deer         59.1% (591/1000)           59.0% (590/1000)\n",
-       "5          dog         61.9% (619/1000)           61.2% (612/1000)\n",
-       "6         frog         85.1% (851/1000)           85.1% (851/1000)\n",
-       "7        horse         78.3% (783/1000)           78.1% (781/1000)\n",
-       "8         ship         85.5% (855/1000)           85.5% (855/1000)\n",
-       "9        truck         85.4% (854/1000)           85.5% (855/1000)\n",
-       "10       total      72.77% (7277/10000)        72.64% (7264/10000)"
+       "0     airplane         79.1% (791/1000)           81.4% (814/1000)\n",
+       "1   automobile         84.1% (841/1000)           87.5% (875/1000)\n",
+       "2         bird         59.9% (599/1000)           63.4% (634/1000)\n",
+       "3          cat         49.4% (494/1000)           51.7% (517/1000)\n",
+       "4         deer         67.1% (671/1000)           70.0% (700/1000)\n",
+       "5          dog         56.7% (567/1000)           59.1% (591/1000)\n",
+       "6         frog         72.4% (724/1000)           77.0% (770/1000)\n",
+       "7        horse         68.0% (680/1000)           72.6% (726/1000)\n",
+       "8         ship         84.9% (849/1000)           86.4% (864/1000)\n",
+       "9        truck         74.7% (747/1000)           77.2% (772/1000)\n",
+       "10       total      69.63% (6963/10000)        72.63% (7263/10000)"
       ]
      },
-     "execution_count": 87,
+     "execution_count": 17,
      "metadata": {},
      "output_type": "execute_result"
     }
@@ -1286,7 +1287,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 16,
+   "execution_count": 18,
    "id": "a0adb89c",
    "metadata": {},
    "outputs": [
@@ -1295,22 +1296,50 @@
      "output_type": "stream",
      "text": [
       "Starting QAT training...\n",
-      "Epoch: 1/30 \tTraining Loss: 1.832520 \tValidation Loss: 0.441452\n",
-      "Validation loss decreased (inf --> 0.441452). Saving model...\n"
-     ]
-    },
-    {
-     "ename": "KeyboardInterrupt",
-     "evalue": "",
-     "output_type": "error",
-     "traceback": [
-      "\u001b[0;31m---------------------------------------------------------------------------\u001b[0m",
-      "\u001b[0;31mKeyboardInterrupt\u001b[0m                         Traceback (most recent call last)",
-      "Cell \u001b[0;32mIn[16], line 47\u001b[0m\n\u001b[1;32m     45\u001b[0m output \u001b[38;5;241m=\u001b[39m model(data)\n\u001b[1;32m     46\u001b[0m loss \u001b[38;5;241m=\u001b[39m criterion(output, target)\n\u001b[0;32m---> 47\u001b[0m \u001b[43mloss\u001b[49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mbackward\u001b[49m\u001b[43m(\u001b[49m\u001b[43m)\u001b[49m\n\u001b[1;32m     48\u001b[0m optimizer\u001b[38;5;241m.\u001b[39mstep()\n\u001b[1;32m     50\u001b[0m \u001b[38;5;66;03m# Update training loss\u001b[39;00m\n",
-      "File \u001b[0;32m~/miniconda3/lib/python3.12/site-packages/torch/_tensor.py:581\u001b[0m, in \u001b[0;36mTensor.backward\u001b[0;34m(self, gradient, retain_graph, create_graph, inputs)\u001b[0m\n\u001b[1;32m    571\u001b[0m \u001b[38;5;28;01mif\u001b[39;00m has_torch_function_unary(\u001b[38;5;28mself\u001b[39m):\n\u001b[1;32m    572\u001b[0m     \u001b[38;5;28;01mreturn\u001b[39;00m handle_torch_function(\n\u001b[1;32m    573\u001b[0m         Tensor\u001b[38;5;241m.\u001b[39mbackward,\n\u001b[1;32m    574\u001b[0m         (\u001b[38;5;28mself\u001b[39m,),\n\u001b[0;32m   (...)\u001b[0m\n\u001b[1;32m    579\u001b[0m         inputs\u001b[38;5;241m=\u001b[39minputs,\n\u001b[1;32m    580\u001b[0m     )\n\u001b[0;32m--> 581\u001b[0m \u001b[43mtorch\u001b[49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mautograd\u001b[49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mbackward\u001b[49m\u001b[43m(\u001b[49m\n\u001b[1;32m    582\u001b[0m \u001b[43m    \u001b[49m\u001b[38;5;28;43mself\u001b[39;49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[43mgradient\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[43mretain_graph\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[43mcreate_graph\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[43minputs\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43minputs\u001b[49m\n\u001b[1;32m    583\u001b[0m \u001b[43m\u001b[49m\u001b[43m)\u001b[49m\n",
-      "File \u001b[0;32m~/miniconda3/lib/python3.12/site-packages/torch/autograd/__init__.py:347\u001b[0m, in \u001b[0;36mbackward\u001b[0;34m(tensors, grad_tensors, retain_graph, create_graph, grad_variables, inputs)\u001b[0m\n\u001b[1;32m    342\u001b[0m     retain_graph \u001b[38;5;241m=\u001b[39m create_graph\n\u001b[1;32m    344\u001b[0m \u001b[38;5;66;03m# The reason we repeat the same comment below is that\u001b[39;00m\n\u001b[1;32m    345\u001b[0m \u001b[38;5;66;03m# some Python versions print out the first line of a multi-line function\u001b[39;00m\n\u001b[1;32m    346\u001b[0m \u001b[38;5;66;03m# calls in the traceback and some print out the last line\u001b[39;00m\n\u001b[0;32m--> 347\u001b[0m \u001b[43m_engine_run_backward\u001b[49m\u001b[43m(\u001b[49m\n\u001b[1;32m    348\u001b[0m \u001b[43m    \u001b[49m\u001b[43mtensors\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m    349\u001b[0m \u001b[43m    \u001b[49m\u001b[43mgrad_tensors_\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m    350\u001b[0m \u001b[43m    \u001b[49m\u001b[43mretain_graph\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m    351\u001b[0m \u001b[43m    \u001b[49m\u001b[43mcreate_graph\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m    352\u001b[0m \u001b[43m    \u001b[49m\u001b[43minputs\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m    353\u001b[0m \u001b[43m    \u001b[49m\u001b[43mallow_unreachable\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[38;5;28;43;01mTrue\u001b[39;49;00m\u001b[43m,\u001b[49m\n\u001b[1;32m    354\u001b[0m \u001b[43m    \u001b[49m\u001b[43maccumulate_grad\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[38;5;28;43;01mTrue\u001b[39;49;00m\u001b[43m,\u001b[49m\n\u001b[1;32m    355\u001b[0m \u001b[43m\u001b[49m\u001b[43m)\u001b[49m\n",
-      "File \u001b[0;32m~/miniconda3/lib/python3.12/site-packages/torch/autograd/graph.py:825\u001b[0m, in \u001b[0;36m_engine_run_backward\u001b[0;34m(t_outputs, *args, **kwargs)\u001b[0m\n\u001b[1;32m    823\u001b[0m     unregister_hooks \u001b[38;5;241m=\u001b[39m _register_logging_hooks_on_whole_graph(t_outputs)\n\u001b[1;32m    824\u001b[0m \u001b[38;5;28;01mtry\u001b[39;00m:\n\u001b[0;32m--> 825\u001b[0m     \u001b[38;5;28;01mreturn\u001b[39;00m \u001b[43mVariable\u001b[49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43m_execution_engine\u001b[49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mrun_backward\u001b[49m\u001b[43m(\u001b[49m\u001b[43m  \u001b[49m\u001b[38;5;66;43;03m# Calls into the C++ engine to run the backward pass\u001b[39;49;00m\n\u001b[1;32m    826\u001b[0m \u001b[43m        \u001b[49m\u001b[43mt_outputs\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[38;5;241;43m*\u001b[39;49m\u001b[43margs\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[38;5;241;43m*\u001b[39;49m\u001b[38;5;241;43m*\u001b[39;49m\u001b[43mkwargs\u001b[49m\n\u001b[1;32m    827\u001b[0m \u001b[43m    \u001b[49m\u001b[43m)\u001b[49m  \u001b[38;5;66;03m# Calls into the C++ engine to run the backward pass\u001b[39;00m\n\u001b[1;32m    828\u001b[0m \u001b[38;5;28;01mfinally\u001b[39;00m:\n\u001b[1;32m    829\u001b[0m     \u001b[38;5;28;01mif\u001b[39;00m attach_logging_hooks:\n",
-      "\u001b[0;31mKeyboardInterrupt\u001b[0m: "
+      "Epoch: 1/30 \tTraining Loss: 1.824183 \tValidation Loss: 0.429200\n",
+      "Validation loss decreased (inf --> 0.429200). Saving model...\n",
+      "Epoch: 2/30 \tTraining Loss: 1.580260 \tValidation Loss: 0.356223\n",
+      "Validation loss decreased (0.429200 --> 0.356223). Saving model...\n",
+      "Epoch: 3/30 \tTraining Loss: 1.337864 \tValidation Loss: 0.305624\n",
+      "Validation loss decreased (0.356223 --> 0.305624). Saving model...\n",
+      "Epoch: 4/30 \tTraining Loss: 1.209521 \tValidation Loss: 0.279522\n",
+      "Validation loss decreased (0.305624 --> 0.279522). Saving model...\n",
+      "Epoch: 5/30 \tTraining Loss: 1.122750 \tValidation Loss: 0.259735\n",
+      "Validation loss decreased (0.279522 --> 0.259735). Saving model...\n",
+      "Epoch: 6/30 \tTraining Loss: 1.051047 \tValidation Loss: 0.244680\n",
+      "Validation loss decreased (0.259735 --> 0.244680). Saving model...\n",
+      "Epoch: 7/30 \tTraining Loss: 0.989193 \tValidation Loss: 0.228631\n",
+      "Validation loss decreased (0.244680 --> 0.228631). Saving model...\n",
+      "Epoch: 8/30 \tTraining Loss: 0.927654 \tValidation Loss: 0.217336\n",
+      "Validation loss decreased (0.228631 --> 0.217336). Saving model...\n",
+      "Epoch: 9/30 \tTraining Loss: 0.873108 \tValidation Loss: 0.205978\n",
+      "Validation loss decreased (0.217336 --> 0.205978). Saving model...\n",
+      "Epoch: 10/30 \tTraining Loss: 0.824872 \tValidation Loss: 0.200104\n",
+      "Validation loss decreased (0.205978 --> 0.200104). Saving model...\n",
+      "Epoch: 11/30 \tTraining Loss: 0.773477 \tValidation Loss: 0.187483\n",
+      "Validation loss decreased (0.200104 --> 0.187483). Saving model...\n",
+      "Epoch: 12/30 \tTraining Loss: 0.728516 \tValidation Loss: 0.184176\n",
+      "Validation loss decreased (0.187483 --> 0.184176). Saving model...\n",
+      "Epoch: 13/30 \tTraining Loss: 0.688895 \tValidation Loss: 0.176157\n",
+      "Validation loss decreased (0.184176 --> 0.176157). Saving model...\n",
+      "Epoch: 14/30 \tTraining Loss: 0.649141 \tValidation Loss: 0.170638\n",
+      "Validation loss decreased (0.176157 --> 0.170638). Saving model...\n",
+      "Epoch: 15/30 \tTraining Loss: 0.612924 \tValidation Loss: 0.172746\n",
+      "Epoch: 16/30 \tTraining Loss: 0.576014 \tValidation Loss: 0.168787\n",
+      "Validation loss decreased (0.170638 --> 0.168787). Saving model...\n",
+      "Epoch: 17/30 \tTraining Loss: 0.544572 \tValidation Loss: 0.165967\n",
+      "Validation loss decreased (0.168787 --> 0.165967). Saving model...\n",
+      "Epoch: 18/30 \tTraining Loss: 0.513845 \tValidation Loss: 0.164744\n",
+      "Validation loss decreased (0.165967 --> 0.164744). Saving model...\n",
+      "Epoch: 19/30 \tTraining Loss: 0.482465 \tValidation Loss: 0.168818\n",
+      "Epoch: 20/30 \tTraining Loss: 0.450607 \tValidation Loss: 0.163888\n",
+      "Validation loss decreased (0.164744 --> 0.163888). Saving model...\n",
+      "Epoch: 21/30 \tTraining Loss: 0.425899 \tValidation Loss: 0.161512\n",
+      "Validation loss decreased (0.163888 --> 0.161512). Saving model...\n",
+      "Epoch: 22/30 \tTraining Loss: 0.396296 \tValidation Loss: 0.164949\n",
+      "Epoch: 23/30 \tTraining Loss: 0.368426 \tValidation Loss: 0.171558\n",
+      "Epoch: 24/30 \tTraining Loss: 0.347285 \tValidation Loss: 0.170112\n",
+      "Early stopping triggered.\n"
      ]
     }
    ],
@@ -1331,8 +1360,6 @@
     "model.train()\n",
     "\n",
     "# Define custom QAT configuration\n",
-    "from torch.ao.quantization import QConfig, default_weight_observer\n",
-    "from torch.ao.quantization.observer import MinMaxObserver\n",
     "\n",
     "qat_config = QConfig(\n",
     "    activation=MinMaxObserver.with_args(quant_min=0, quant_max=127),\n",
@@ -1419,15 +1446,17 @@
      "text": [
       "Converting the model to a quantized version...\n",
       "Evaluating models...\n",
-      "Original Model Accuracy: 21.57%\n",
-      "Quantized Model Accuracy: 21.57%\n",
+      "Original Model Accuracy: 73.62%\n",
+      "Quantized Model Accuracy: 73.62%\n",
       "Quantized QAT model saved to 'quantized_qat_model.pt'.\n"
      ]
     }
    ],
    "source": [
     "print(\"Converting the model to a quantized version...\")\n",
-    "quantized_model = torch.quantization.convert(model, inplace=False)\n",
+    "torch.backends.quantized.engine = 'qnnpack' # or 'fbgemm' for x86 architectures\n",
+    "#quantized_model = torch.quantization.convert(model, inplace=False)\n",
+    "quantized_model = torch.quantization.quantize_dynamic(model, dtype=torch.qint8)\n",
     "\n",
     "# Evaluate both the original and quantized models\n",
     "def evaluate_model(model, loader):\n",
@@ -1475,18 +1504,10 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 22,
+   "execution_count": 21,
    "id": "b4d13080",
    "metadata": {},
    "outputs": [
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "Downloading: \"https://download.pytorch.org/models/resnet50-11ad3fa6.pth\" to /Users/zhangzhengfei/.cache/torch/hub/checkpoints/resnet50-11ad3fa6.pth\n",
-      "100%|██████████| 97.8M/97.8M [00:12<00:00, 8.48MB/s]\n"
-     ]
-    },
     {
      "name": "stdout",
      "output_type": "stream",
@@ -1506,13 +1527,8 @@
     }
    ],
    "source": [
-    "import json\n",
-    "from PIL import Image\n",
-    "from torchvision.models import ResNet50_Weights\n",
-    "import matplotlib.pyplot as plt\n",
-    "\n",
     "# Choose an image to pass through the model\n",
-    "test_image = \"dog.png\"\n",
+    "test_image = \"dog.jpg\"\n",
     "\n",
     "# Configure matplotlib for pretty inline plots\n",
     "#%matplotlib inline\n",
@@ -1568,6 +1584,1401 @@
     "    \n"
    ]
   },
+  {
+   "cell_type": "markdown",
+   "id": "1bc18aac",
+   "metadata": {},
+   "source": [
+    "Normal version"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 22,
+   "id": "8baf6e1c",
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "Predicted class for ./dog.png is: Golden Retriever\n",
+      "Predicted class for ./gaspump.jpg is: gas pump\n",
+      "Predicted class for ./dog.jpg is: Golden Retriever\n",
+      "Predicted class for ./golf-cart.jpg is: golf cart\n",
+      "Predicted class for ./gondola.jpg is: gondola\n",
+      "Predicted class for ./eel.jpg is: eel\n",
+      "Predicted class for ./hymenoptera_data/train/bees/2638074627_6b3ae746a0.jpg is: bee\n",
+      "Predicted class for ./hymenoptera_data/train/bees/507288830_f46e8d4cb2.jpg is: bee\n",
+      "Predicted class for ./hymenoptera_data/train/bees/2405441001_b06c36fa72.jpg is: bee\n",
+      "Predicted class for ./hymenoptera_data/train/bees/2962405283_22718d9617.jpg is: bee\n",
+      "Predicted class for ./hymenoptera_data/train/bees/446296270_d9e8b93ecf.jpg is: bee\n",
+      "Predicted class for ./hymenoptera_data/train/bees/1092977343_cb42b38d62.jpg is: bee\n",
+      "Predicted class for ./hymenoptera_data/train/bees/2704348794_eb5d5178c2.jpg is: bee\n",
+      "Predicted class for ./hymenoptera_data/train/bees/2358061370_9daabbd9ac.jpg is: bee\n",
+      "Predicted class for ./hymenoptera_data/train/bees/2861002136_52c7c6f708.jpg is: bee\n",
+      "Predicted class for ./hymenoptera_data/train/bees/266644509_d30bb16a1b.jpg is: bee\n",
+      "Predicted class for ./hymenoptera_data/train/bees/2470492904_837e97800d.jpg is: bee\n",
+      "Predicted class for ./hymenoptera_data/train/bees/2053200300_8911ef438a.jpg is: bee\n",
+      "Predicted class for ./hymenoptera_data/train/bees/2601176055_8464e6aa71.jpg is: bee\n",
+      "Predicted class for ./hymenoptera_data/train/bees/473618094_8ffdcab215.jpg is: bee\n",
+      "Predicted class for ./hymenoptera_data/train/bees/150013791_969d9a968b.jpg is: bee\n",
+      "Predicted class for ./hymenoptera_data/train/bees/2486746709_c43cec0e42.jpg is: bee\n",
+      "Predicted class for ./hymenoptera_data/train/bees/452462677_7be43af8ff.jpg is: bee\n",
+      "Predicted class for ./hymenoptera_data/train/bees/2397446847_04ef3cd3e1.jpg is: bee\n",
+      "Predicted class for ./hymenoptera_data/train/bees/92663402_37f379e57a.jpg is: bee\n",
+      "Predicted class for ./hymenoptera_data/train/bees/2486729079_62df0920be.jpg is: bee\n",
+      "Predicted class for ./hymenoptera_data/train/bees/2551813042_8a070aeb2b.jpg is: bee\n",
+      "Predicted class for ./hymenoptera_data/train/bees/2792000093_e8ae0718cf.jpg is: bee\n",
+      "Predicted class for ./hymenoptera_data/train/bees/2477324698_3d4b1b1cab.jpg is: bee\n",
+      "Predicted class for ./hymenoptera_data/train/bees/2959730355_416a18c63c.jpg is: bee\n",
+      "Predicted class for ./hymenoptera_data/train/bees/774440991_63a4aa0cbe.jpg is: bee\n",
+      "Predicted class for ./hymenoptera_data/train/bees/2652877533_a564830cbf.jpg is: bee\n",
+      "Predicted class for ./hymenoptera_data/train/bees/21399619_3e61e5bb6f.jpg is: sea urchin\n",
+      "Predicted class for ./hymenoptera_data/train/bees/586041248_3032e277a9.jpg is: fly\n",
+      "Predicted class for ./hymenoptera_data/train/bees/39672681_1302d204d1.jpg is: bee\n",
+      "Predicted class for ./hymenoptera_data/train/bees/2345177635_caf07159b3.jpg is: bee\n",
+      "Predicted class for ./hymenoptera_data/train/bees/2321139806_d73d899e66.jpg is: bee\n",
+      "Predicted class for ./hymenoptera_data/train/bees/2528444139_fa728b0f5b.jpg is: bee\n",
+      "Predicted class for ./hymenoptera_data/train/bees/3044402684_3853071a87.jpg is: bee\n",
+      "Predicted class for ./hymenoptera_data/train/bees/2683605182_9d2a0c66cf.jpg is: honeycomb\n",
+      "Predicted class for ./hymenoptera_data/train/bees/2728759455_ce9bb8cd7a.jpg is: bee\n",
+      "Predicted class for ./hymenoptera_data/train/bees/522104315_5d3cb2758e.jpg is: bee\n",
+      "Predicted class for ./hymenoptera_data/train/bees/2493379287_4100e1dacc.jpg is: corn\n",
+      "Predicted class for ./hymenoptera_data/train/bees/478701318_bbd5e557b8.jpg is: bee\n",
+      "Predicted class for ./hymenoptera_data/train/bees/2610833167_79bf0bcae5.jpg is: bee\n",
+      "Predicted class for ./hymenoptera_data/train/bees/2710368626_cb42882dc8.jpg is: bee\n",
+      "Predicted class for ./hymenoptera_data/train/bees/1691282715_0addfdf5e8.jpg is: bee\n",
+      "Predicted class for ./hymenoptera_data/train/bees/2756397428_1d82a08807.jpg is: bee\n",
+      "Predicted class for ./hymenoptera_data/train/bees/1799726602_8580867f71.jpg is: bee\n",
+      "Predicted class for ./hymenoptera_data/train/bees/2477349551_e75c97cf4d.jpg is: bee\n",
+      "Predicted class for ./hymenoptera_data/train/bees/2031225713_50ed499635.jpg is: bee\n",
+      "Predicted class for ./hymenoptera_data/train/bees/2610838525_fe8e3cae47.jpg is: bee\n",
+      "Predicted class for ./hymenoptera_data/train/bees/3074585407_9854eb3153.jpg is: bee\n",
+      "Predicted class for ./hymenoptera_data/train/bees/2330918208_8074770c20.jpg is: bee\n",
+      "Predicted class for ./hymenoptera_data/train/bees/465133211_80e0c27f60.jpg is: bee\n",
+      "Predicted class for ./hymenoptera_data/train/bees/3079610310_ac2d0ae7bc.jpg is: bee\n",
+      "Predicted class for ./hymenoptera_data/train/bees/2495722465_879acf9d85.jpg is: bee\n",
+      "Predicted class for ./hymenoptera_data/train/bees/444532809_9e931e2279.jpg is: bee\n",
+      "Predicted class for ./hymenoptera_data/train/bees/1807583459_4fe92b3133.jpg is: bee\n",
+      "Predicted class for ./hymenoptera_data/train/bees/359928878_b3b418c728.jpg is: bee\n",
+      "Predicted class for ./hymenoptera_data/train/bees/2037437624_2d7bce461f.jpg is: bee\n",
+      "Predicted class for ./hymenoptera_data/train/bees/509247772_2db2d01374.jpg is: bee\n",
+      "Predicted class for ./hymenoptera_data/train/bees/90179376_abc234e5f4.jpg is: bee\n",
+      "Predicted class for ./hymenoptera_data/train/bees/3030772428_8578335616.jpg is: bee\n",
+      "Predicted class for ./hymenoptera_data/train/bees/873076652_eb098dab2d.jpg is: bee\n",
+      "Predicted class for ./hymenoptera_data/train/bees/17209602_fe5a5a746f.jpg is: bee\n",
+      "Predicted class for ./hymenoptera_data/train/bees/421515404_e87569fd8b.jpg is: bee\n",
+      "Predicted class for ./hymenoptera_data/train/bees/1097045929_1753d1c765.jpg is: honeycomb\n",
+      "Predicted class for ./hymenoptera_data/train/bees/2781170484_5d61835d63.jpg is: bee\n",
+      "Predicted class for ./hymenoptera_data/train/bees/3100226504_c0d4f1e3f1.jpg is: bee\n",
+      "Predicted class for ./hymenoptera_data/train/bees/2617161745_fa3ebe85b4.jpg is: bee\n",
+      "Predicted class for ./hymenoptera_data/train/bees/2580598377_a4caecdb54.jpg is: bee\n",
+      "Predicted class for ./hymenoptera_data/train/bees/208702903_42fb4d9748.jpg is: daisy\n",
+      "Predicted class for ./hymenoptera_data/train/bees/537309131_532bfa59ea.jpg is: bee\n",
+      "Predicted class for ./hymenoptera_data/train/bees/969455125_58c797ef17.jpg is: sulphur butterfly\n",
+      "Predicted class for ./hymenoptera_data/train/bees/365759866_b15700c59b.jpg is: cardoon\n",
+      "Predicted class for ./hymenoptera_data/train/bees/196430254_46bd129ae7.jpg is: bee\n",
+      "Predicted class for ./hymenoptera_data/train/bees/1232245714_f862fbe385.jpg is: bee\n",
+      "Predicted class for ./hymenoptera_data/train/bees/2445215254_51698ff797.jpg is: bee\n",
+      "Predicted class for ./hymenoptera_data/train/bees/760526046_547e8b381f.jpg is: bee\n",
+      "Predicted class for ./hymenoptera_data/train/bees/513545352_fd3e7c7c5d.jpg is: bee\n",
+      "Predicted class for ./hymenoptera_data/train/bees/2634617358_f32fd16bea.jpg is: bee\n",
+      "Predicted class for ./hymenoptera_data/train/bees/39747887_42df2855ee.jpg is: bee\n",
+      "Predicted class for ./hymenoptera_data/train/bees/354167719_22dca13752.jpg is: bee\n",
+      "Predicted class for ./hymenoptera_data/train/bees/2384149906_2cd8b0b699.jpg is: bee\n",
+      "Predicted class for ./hymenoptera_data/train/bees/2625499656_e3415e374d.jpg is: bee\n",
+      "Predicted class for ./hymenoptera_data/train/bees/2645107662_b73a8595cc.jpg is: bee\n",
+      "Predicted class for ./hymenoptera_data/train/bees/154600396_53e1252e52.jpg is: bee\n",
+      "Predicted class for ./hymenoptera_data/train/bees/279113587_b4843db199.jpg is: bee\n",
+      "Predicted class for ./hymenoptera_data/train/bees/98391118_bdb1e80cce.jpg is: fly\n",
+      "Predicted class for ./hymenoptera_data/train/bees/132511197_0b86ad0fff.jpg is: bee\n",
+      "Predicted class for ./hymenoptera_data/train/bees/2707440199_cd170bd512.jpg is: cardoon\n",
+      "Predicted class for ./hymenoptera_data/train/bees/342758693_c56b89b6b6.jpg is: bee\n",
+      "Predicted class for ./hymenoptera_data/train/bees/36900412_92b81831ad.jpg is: bee\n",
+      "Predicted class for ./hymenoptera_data/train/bees/2364597044_3c3e3fc391.jpg is: bee\n",
+      "Predicted class for ./hymenoptera_data/train/bees/1295655112_7813f37d21.jpg is: bee\n",
+      "Predicted class for ./hymenoptera_data/train/bees/2227611847_ec72d40403.jpg is: bee\n",
+      "Predicted class for ./hymenoptera_data/train/bees/205835650_e6f2614bee.jpg is: bee\n",
+      "Predicted class for ./hymenoptera_data/train/bees/1093831624_fb5fbe2308.jpg is: bee\n",
+      "Predicted class for ./hymenoptera_data/train/bees/129236073_0985e91c7d.jpg is: bee\n",
+      "Predicted class for ./hymenoptera_data/train/bees/198508668_97d818b6c4.jpg is: bee\n",
+      "Predicted class for ./hymenoptera_data/train/bees/1508176360_2972117c9d.jpg is: bee\n",
+      "Predicted class for ./hymenoptera_data/train/bees/457457145_5f86eb7e9c.jpg is: bee\n",
+      "Predicted class for ./hymenoptera_data/train/bees/2722592222_258d473e17.jpg is: bee\n",
+      "Predicted class for ./hymenoptera_data/train/bees/2822388965_f6dca2a275.jpg is: bee\n",
+      "Predicted class for ./hymenoptera_data/train/bees/2651621464_a2fa8722eb.jpg is: bee\n",
+      "Predicted class for ./hymenoptera_data/train/bees/132826773_dbbcb117b9.jpg is: bee\n",
+      "Predicted class for ./hymenoptera_data/train/bees/476347960_52edd72b06.jpg is: bee\n",
+      "Predicted class for ./hymenoptera_data/train/bees/3006264892_30e9cced70.jpg is: bee\n",
+      "Predicted class for ./hymenoptera_data/train/bees/760568592_45a52c847f.jpg is: bee\n",
+      "Predicted class for ./hymenoptera_data/train/bees/2452236943_255bfd9e58.jpg is: bee\n",
+      "Predicted class for ./hymenoptera_data/train/bees/472288710_2abee16fa0.jpg is: fly\n",
+      "Predicted class for ./hymenoptera_data/train/bees/2908916142_a7ac8b57a8.jpg is: bee\n",
+      "Predicted class for ./hymenoptera_data/train/bees/95238259_98470c5b10.jpg is: bee\n",
+      "Predicted class for ./hymenoptera_data/train/bees/85112639_6e860b0469.jpg is: bee\n",
+      "Predicted class for ./hymenoptera_data/train/bees/2801728106_833798c909.jpg is: bee\n",
+      "Predicted class for ./hymenoptera_data/train/bees/174142798_e5ad6d76e0.jpg is: bee\n",
+      "Predicted class for ./hymenoptera_data/train/bees/2467959963_a7831e9ff0.jpg is: bee\n",
+      "Predicted class for ./hymenoptera_data/train/bees/2538361678_9da84b77e3.jpg is: bee\n",
+      "Predicted class for ./hymenoptera_data/train/bees/196658222_3fffd79c67.jpg is: daisy\n",
+      "Predicted class for ./hymenoptera_data/train/bees/29494643_e3410f0d37.jpg is: bee\n",
+      "Predicted class for ./hymenoptera_data/train/bees/16838648_415acd9e3f.jpg is: bee\n",
+      "Predicted class for ./hymenoptera_data/train/bees/3030189811_01d095b793.jpg is: bee\n",
+      "Predicted class for ./hymenoptera_data/train/bees/469333327_358ba8fe8a.jpg is: bee\n",
+      "Predicted class for ./hymenoptera_data/train/bees/452462695_40a4e5b559.jpg is: bee\n",
+      "Predicted class for ./hymenoptera_data/train/bees/3090975720_71f12e6de4.jpg is: bee\n",
+      "Predicted class for ./hymenoptera_data/train/bees/2765347790_da6cf6cb40.jpg is: bee\n",
+      "Predicted class for ./hymenoptera_data/train/ants/957233405_25c1d1187b.jpg is: ant\n",
+      "Predicted class for ./hymenoptera_data/train/ants/2288481644_83ff7e4572.jpg is: ant\n",
+      "Predicted class for ./hymenoptera_data/train/ants/67270775_e9fdf77e9d.jpg is: ant\n",
+      "Predicted class for ./hymenoptera_data/train/ants/1808777855_2a895621d7.jpg is: ant\n",
+      "Predicted class for ./hymenoptera_data/train/ants/VietnameseAntMimicSpider.jpg is: southern black widow\n",
+      "Predicted class for ./hymenoptera_data/train/ants/swiss-army-ant.jpg is: ant\n",
+      "Predicted class for ./hymenoptera_data/train/ants/termite-vs-ant.jpg is: ant\n",
+      "Predicted class for ./hymenoptera_data/train/ants/245647475_9523dfd13e.jpg is: ant\n",
+      "Predicted class for ./hymenoptera_data/train/ants/384191229_5779cf591b.jpg is: ant\n",
+      "Predicted class for ./hymenoptera_data/train/ants/hormiga_co_por.jpg is: ant\n",
+      "Predicted class for ./hymenoptera_data/train/ants/531979952_bde12b3bc0.jpg is: ant\n",
+      "Predicted class for ./hymenoptera_data/train/ants/224655713_3956f7d39a.jpg is: ant\n",
+      "Predicted class for ./hymenoptera_data/train/ants/132478121_2a430adea2.jpg is: ant\n",
+      "Predicted class for ./hymenoptera_data/train/ants/512863248_43c8ce579b.jpg is: ant\n",
+      "Predicted class for ./hymenoptera_data/train/ants/533848102_70a85ad6dd.jpg is: ant\n",
+      "Predicted class for ./hymenoptera_data/train/ants/201558278_fe4caecc76.jpg is: ant\n",
+      "Predicted class for ./hymenoptera_data/train/ants/army-ants-red-picture.jpg is: ant\n",
+      "Predicted class for ./hymenoptera_data/train/ants/MehdiabadiAnt2_600.jpg is: ant\n",
+      "Predicted class for ./hymenoptera_data/train/ants/334167043_cbd1adaeb9.jpg is: ant\n",
+      "Predicted class for ./hymenoptera_data/train/ants/20935278_9190345f6b.jpg is: ant\n",
+      "Predicted class for ./hymenoptera_data/train/ants/540889389_48bb588b21.jpg is: ant\n",
+      "Predicted class for ./hymenoptera_data/train/ants/466430434_4000737de9.jpg is: ant\n",
+      "Predicted class for ./hymenoptera_data/train/ants/649026570_e58656104b.jpg is: ant\n",
+      "Predicted class for ./hymenoptera_data/train/ants/196057951_63bf063b92.jpg is: ant\n",
+      "Predicted class for ./hymenoptera_data/train/ants/1660097129_384bf54490.jpg is: ant\n",
+      "Predicted class for ./hymenoptera_data/train/ants/1286984635_5119e80de1.jpg is: ant\n",
+      "Predicted class for ./hymenoptera_data/train/ants/6240329_72c01e663e.jpg is: ant\n",
+      "Predicted class for ./hymenoptera_data/train/ants/Ant_1.jpg is: ant\n",
+      "Predicted class for ./hymenoptera_data/train/ants/522163566_fec115ca66.jpg is: ant\n",
+      "Predicted class for ./hymenoptera_data/train/ants/0013035.jpg is: ant\n",
+      "Predicted class for ./hymenoptera_data/train/ants/24335309_c5ea483bb8.jpg is: ant\n",
+      "Predicted class for ./hymenoptera_data/train/ants/150801171_cd86f17ed8.jpg is: ant\n",
+      "Predicted class for ./hymenoptera_data/train/ants/403746349_71384f5b58.jpg is: ant\n",
+      "Predicted class for ./hymenoptera_data/train/ants/460372577_f2f6a8c9fc.jpg is: ant\n",
+      "Predicted class for ./hymenoptera_data/train/ants/386190770_672743c9a7.jpg is: ant\n",
+      "Predicted class for ./hymenoptera_data/train/ants/886401651_f878e888cd.jpg is: ant\n",
+      "Predicted class for ./hymenoptera_data/train/ants/506249802_207cd979b4.jpg is: ant\n",
+      "Predicted class for ./hymenoptera_data/train/ants/841049277_b28e58ad05.jpg is: shoji\n",
+      "Predicted class for ./hymenoptera_data/train/ants/707895295_009cf23188.jpg is: ant\n",
+      "Predicted class for ./hymenoptera_data/train/ants/Nepenthes_rafflesiana_ant.jpg is: ant\n",
+      "Predicted class for ./hymenoptera_data/train/ants/518773929_734dbc5ff4.jpg is: ant\n",
+      "Predicted class for ./hymenoptera_data/train/ants/342438950_a3da61deab.jpg is: ant\n",
+      "Predicted class for ./hymenoptera_data/train/ants/1368913450_e146e2fb6d.jpg is: ant\n",
+      "Predicted class for ./hymenoptera_data/train/ants/49375974_e28ba6f17e.jpg is: ant\n",
+      "Predicted class for ./hymenoptera_data/train/ants/822537660_caf4ba5514.jpg is: ant\n",
+      "Predicted class for ./hymenoptera_data/train/ants/36439863_0bec9f554f.jpg is: ant\n",
+      "Predicted class for ./hymenoptera_data/train/ants/175998972.jpg is: ant\n",
+      "Predicted class for ./hymenoptera_data/train/ants/382971067_0bfd33afe0.jpg is: ant\n",
+      "Predicted class for ./hymenoptera_data/train/ants/1804095607_0341701e1c.jpg is: ant\n",
+      "Predicted class for ./hymenoptera_data/train/ants/188552436_605cc9b36b.jpg is: ant\n",
+      "Predicted class for ./hymenoptera_data/train/ants/339670531_94b75ae47a.jpg is: ant\n",
+      "Predicted class for ./hymenoptera_data/train/ants/374435068_7eee412ec4.jpg is: ant\n",
+      "Predicted class for ./hymenoptera_data/train/ants/1473187633_63ccaacea6.jpg is: cicada\n",
+      "Predicted class for ./hymenoptera_data/train/ants/258217966_d9d90d18d3.jpg is: ant\n",
+      "Predicted class for ./hymenoptera_data/train/ants/150801003_3390b73135.jpg is: ant\n",
+      "Predicted class for ./hymenoptera_data/train/ants/1030023514_aad5c608f9.jpg is: ant\n",
+      "Predicted class for ./hymenoptera_data/train/ants/2288450226_a6e96e8fdf.jpg is: ant\n",
+      "Predicted class for ./hymenoptera_data/train/ants/541630764_dbd285d63c.jpg is: ant\n",
+      "Predicted class for ./hymenoptera_data/train/ants/275429470_b2d7d9290b.jpg is: ant\n",
+      "Predicted class for ./hymenoptera_data/train/ants/6240338_93729615ec.jpg is: ant\n",
+      "Predicted class for ./hymenoptera_data/train/ants/424873399_47658a91fb.jpg is: ant\n",
+      "Predicted class for ./hymenoptera_data/train/ants/543417860_b14237f569.jpg is: ant\n",
+      "Predicted class for ./hymenoptera_data/train/ants/318052216_84dff3f98a.jpg is: ant\n",
+      "Predicted class for ./hymenoptera_data/train/ants/149244013_c529578289.jpg is: ant\n",
+      "Predicted class for ./hymenoptera_data/train/ants/1262877379_64fcada201.jpg is: ant\n",
+      "Predicted class for ./hymenoptera_data/train/ants/450057712_771b3bfc91.jpg is: ant\n",
+      "Predicted class for ./hymenoptera_data/train/ants/662541407_ff8db781e7.jpg is: ant\n",
+      "Predicted class for ./hymenoptera_data/train/ants/154124431_65460430f2.jpg is: ant\n",
+      "Predicted class for ./hymenoptera_data/train/ants/2019439677_2db655d361.jpg is: ant\n",
+      "Predicted class for ./hymenoptera_data/train/ants/1489674356_09d48dde0a.jpg is: ant\n",
+      "Predicted class for ./hymenoptera_data/train/ants/892108839_f1aad4ca46.jpg is: ant\n",
+      "Predicted class for ./hymenoptera_data/train/ants/522415432_2218f34bf8.jpg is: ant\n",
+      "Predicted class for ./hymenoptera_data/train/ants/178538489_bec7649292.jpg is: ant\n",
+      "Predicted class for ./hymenoptera_data/train/ants/ant photos.jpg is: ant\n",
+      "Predicted class for ./hymenoptera_data/train/ants/474806473_ca6caab245.jpg is: ladybug\n",
+      "Predicted class for ./hymenoptera_data/train/ants/408393566_b5b694119b.jpg is: ant\n",
+      "Predicted class for ./hymenoptera_data/train/ants/2278278459_6b99605e50.jpg is: ant\n",
+      "Predicted class for ./hymenoptera_data/train/ants/formica.jpeg is: ant\n",
+      "Predicted class for ./hymenoptera_data/train/ants/1269756697_0bce92cdab.jpg is: ant\n",
+      "Predicted class for ./hymenoptera_data/train/ants/2292213964_ca51ce4bef.jpg is: apiary\n",
+      "Predicted class for ./hymenoptera_data/train/ants/226951206_d6bf946504.jpg is: ant\n",
+      "Predicted class for ./hymenoptera_data/train/ants/938946700_ca1c669085.jpg is: ant\n",
+      "Predicted class for ./hymenoptera_data/train/ants/2265824718_2c96f485da.jpg is: ant\n",
+      "Predicted class for ./hymenoptera_data/train/ants/392382602_1b7bed32fa.jpg is: screwdriver\n",
+      "Predicted class for ./hymenoptera_data/train/ants/69639610_95e0de17aa.jpg is: ant\n",
+      "Predicted class for ./hymenoptera_data/train/ants/7759525_1363d24e88.jpg is: ant\n",
+      "Predicted class for ./hymenoptera_data/train/ants/424119020_6d57481dab.jpg is: ant\n",
+      "Predicted class for ./hymenoptera_data/train/ants/162603798_40b51f1654.jpg is: ant\n",
+      "Predicted class for ./hymenoptera_data/train/ants/28847243_e79fe052cd.jpg is: ant\n",
+      "Predicted class for ./hymenoptera_data/train/ants/998118368_6ac1d91f81.jpg is: ant\n",
+      "Predicted class for ./hymenoptera_data/train/ants/6743948_2b8c096dda.jpg is: ant\n",
+      "Predicted class for ./hymenoptera_data/train/ants/484293231_e53cfc0c89.jpg is: ant\n",
+      "Predicted class for ./hymenoptera_data/train/ants/512164029_c0a66b8498.jpg is: ant\n",
+      "Predicted class for ./hymenoptera_data/train/ants/2265825502_fff99cfd2d.jpg is: ant\n",
+      "Predicted class for ./hymenoptera_data/train/ants/459694881_ac657d3187.jpg is: ant\n",
+      "Predicted class for ./hymenoptera_data/train/ants/1099452230_d1949d3250.jpg is: bee\n",
+      "Predicted class for ./hymenoptera_data/train/ants/kurokusa.jpg is: ant\n",
+      "Predicted class for ./hymenoptera_data/train/ants/116570827_e9c126745d.jpg is: ant\n",
+      "Predicted class for ./hymenoptera_data/train/ants/167890289_dd5ba923f3.jpg is: ant\n",
+      "Predicted class for ./hymenoptera_data/train/ants/1360291657_dc248c5eea.jpg is: ant\n",
+      "Predicted class for ./hymenoptera_data/train/ants/460874319_0a45ab4d05.jpg is: ant\n",
+      "Predicted class for ./hymenoptera_data/train/ants/45472593_bfd624f8dc.jpg is: ant\n",
+      "Predicted class for ./hymenoptera_data/train/ants/207947948_3ab29d7207.jpg is: ant\n",
+      "Predicted class for ./hymenoptera_data/train/ants/535522953_308353a07c.jpg is: ant\n",
+      "Predicted class for ./hymenoptera_data/train/ants/255434217_1b2b3fe0a4.jpg is: ant\n",
+      "Predicted class for ./hymenoptera_data/train/ants/560966032_988f4d7bc4.jpg is: ant\n",
+      "Predicted class for ./hymenoptera_data/train/ants/148715752_302c84f5a4.jpg is: harvestman\n",
+      "Predicted class for ./hymenoptera_data/train/ants/470127037_513711fd21.jpg is: ant\n",
+      "Predicted class for ./hymenoptera_data/train/ants/9715481_b3cb4114ff.jpg is: ant\n",
+      "Predicted class for ./hymenoptera_data/train/ants/684133190_35b62c0c1d.jpg is: ant\n",
+      "Predicted class for ./hymenoptera_data/train/ants/trap-jaw-ant-insect-bg.jpg is: ant\n",
+      "Predicted class for ./hymenoptera_data/train/ants/196757565_326437f5fe.jpg is: ant\n",
+      "Predicted class for ./hymenoptera_data/train/ants/5650366_e22b7e1065.jpg is: ant\n",
+      "Predicted class for ./hymenoptera_data/train/ants/1095476100_3906d8afde.jpg is: ant\n",
+      "Predicted class for ./hymenoptera_data/train/ants/1225872729_6f0856588f.jpg is: ant\n",
+      "Predicted class for ./hymenoptera_data/train/ants/795000156_a9900a4a71.jpg is: ant\n",
+      "Predicted class for ./hymenoptera_data/train/ants/1924473702_daa9aacdbe.jpg is: ant\n",
+      "Predicted class for ./hymenoptera_data/train/ants/82852639_52b7f7f5e3.jpg is: ant\n",
+      "Predicted class for ./hymenoptera_data/train/ants/1693954099_46d4c20605.jpg is: ant\n",
+      "Predicted class for ./hymenoptera_data/train/ants/201790779_527f4c0168.jpg is: ant\n",
+      "Predicted class for ./hymenoptera_data/train/ants/475961153_b8c13fd405.jpg is: ant\n",
+      "Predicted class for ./hymenoptera_data/train/ants/506249836_717b73f540.jpg is: ant\n",
+      "Predicted class for ./hymenoptera_data/train/ants/1917341202_d00a7f9af5.jpg is: ant\n",
+      "Predicted class for ./hymenoptera_data/val/bees/2717418782_bd83307d9f.jpg is: bee\n",
+      "Predicted class for ./hymenoptera_data/val/bees/2173503984_9c6aaaa7e2.jpg is: bee\n",
+      "Predicted class for ./hymenoptera_data/val/bees/54736755_c057723f64.jpg is: bee\n",
+      "Predicted class for ./hymenoptera_data/val/bees/2103637821_8d26ee6b90.jpg is: bee\n",
+      "Predicted class for ./hymenoptera_data/val/bees/603711658_4c8cd2201e.jpg is: bee\n",
+      "Predicted class for ./hymenoptera_data/val/bees/238161922_55fa9a76ae.jpg is: bee\n",
+      "Predicted class for ./hymenoptera_data/val/bees/2457841282_7867f16639.jpg is: bee\n",
+      "Predicted class for ./hymenoptera_data/val/bees/6a00d8341c630a53ef00e553d0beb18834-800wi.jpg is: bee\n",
+      "Predicted class for ./hymenoptera_data/val/bees/177677657_a38c97e572.jpg is: bee\n",
+      "Predicted class for ./hymenoptera_data/val/bees/348291597_ee836fbb1a.jpg is: bee\n",
+      "Predicted class for ./hymenoptera_data/val/bees/152789693_220b003452.jpg is: bee\n",
+      "Predicted class for ./hymenoptera_data/val/bees/2782079948_8d4e94a826.jpg is: bee\n",
+      "Predicted class for ./hymenoptera_data/val/bees/576452297_897023f002.jpg is: bee\n",
+      "Predicted class for ./hymenoptera_data/val/bees/1181173278_23c36fac71.jpg is: bee\n",
+      "Predicted class for ./hymenoptera_data/val/bees/3077452620_548c79fda0.jpg is: bee\n",
+      "Predicted class for ./hymenoptera_data/val/bees/586474709_ae436da045.jpg is: bee\n",
+      "Predicted class for ./hymenoptera_data/val/bees/26589803_5ba7000313.jpg is: bee\n",
+      "Predicted class for ./hymenoptera_data/val/bees/2478216347_535c8fe6d7.jpg is: bee\n",
+      "Predicted class for ./hymenoptera_data/val/bees/2668391343_45e272cd07.jpg is: bee\n",
+      "Predicted class for ./hymenoptera_data/val/bees/540976476_844950623f.jpg is: bee\n",
+      "Predicted class for ./hymenoptera_data/val/bees/144098310_a4176fd54d.jpg is: bee\n",
+      "Predicted class for ./hymenoptera_data/val/bees/1486120850_490388f84b.jpg is: bee\n",
+      "Predicted class for ./hymenoptera_data/val/bees/2670536155_c170f49cd0.jpg is: bee\n",
+      "Predicted class for ./hymenoptera_data/val/bees/1519368889_4270261ee3.jpg is: mushroom\n",
+      "Predicted class for ./hymenoptera_data/val/bees/2506114833_90a41c5267.jpg is: daisy\n",
+      "Predicted class for ./hymenoptera_data/val/bees/2438480600_40a1249879.jpg is: bee\n",
+      "Predicted class for ./hymenoptera_data/val/bees/187130242_4593a4c610.jpg is: bee\n",
+      "Predicted class for ./hymenoptera_data/val/bees/224841383_d050f5f510.jpg is: bee\n",
+      "Predicted class for ./hymenoptera_data/val/bees/59798110_2b6a3c8031.jpg is: bee\n",
+      "Predicted class for ./hymenoptera_data/val/bees/2883093452_7e3a1eb53f.jpg is: bee\n",
+      "Predicted class for ./hymenoptera_data/val/bees/2321144482_f3785ba7b2.jpg is: bee\n",
+      "Predicted class for ./hymenoptera_data/val/bees/abeja.jpg is: bee\n",
+      "Predicted class for ./hymenoptera_data/val/bees/203868383_0fcbb48278.jpg is: bee\n",
+      "Predicted class for ./hymenoptera_data/val/bees/44105569_16720a960c.jpg is: bee\n",
+      "Predicted class for ./hymenoptera_data/val/bees/272986700_d4d4bf8c4b.jpg is: bee\n",
+      "Predicted class for ./hymenoptera_data/val/bees/464594019_1b24a28bb1.jpg is: bee\n",
+      "Predicted class for ./hymenoptera_data/val/bees/485743562_d8cc6b8f73.jpg is: bee\n",
+      "Predicted class for ./hymenoptera_data/val/bees/2815838190_0a9889d995.jpg is: bee\n",
+      "Predicted class for ./hymenoptera_data/val/bees/603709866_a97c7cfc72.jpg is: bee\n",
+      "Predicted class for ./hymenoptera_data/val/bees/2086294791_6f3789d8a6.jpg is: bee\n",
+      "Predicted class for ./hymenoptera_data/val/bees/1328423762_f7a88a8451.jpg is: bee\n",
+      "Predicted class for ./hymenoptera_data/val/bees/416144384_961c326481.jpg is: dung beetle\n",
+      "Predicted class for ./hymenoptera_data/val/bees/2709775832_85b4b50a57.jpg is: apiary\n",
+      "Predicted class for ./hymenoptera_data/val/bees/1297972485_33266a18d9.jpg is: bee\n",
+      "Predicted class for ./hymenoptera_data/val/bees/2415414155_1916f03b42.jpg is: bee\n",
+      "Predicted class for ./hymenoptera_data/val/bees/149973093_da3c446268.jpg is: bee\n",
+      "Predicted class for ./hymenoptera_data/val/bees/2741763055_9a7bb00802.jpg is: bee\n",
+      "Predicted class for ./hymenoptera_data/val/bees/936182217_c4caa5222d.jpg is: bee\n",
+      "Predicted class for ./hymenoptera_data/val/bees/1799729694_0c40101071.jpg is: bee\n",
+      "Predicted class for ./hymenoptera_data/val/bees/2841437312_789699c740.jpg is: bee\n",
+      "Predicted class for ./hymenoptera_data/val/bees/2509402554_31821cb0b6.jpg is: bee\n",
+      "Predicted class for ./hymenoptera_data/val/bees/372228424_16da1f8884.jpg is: bee\n",
+      "Predicted class for ./hymenoptera_data/val/bees/456097971_860949c4fc.jpg is: bee\n",
+      "Predicted class for ./hymenoptera_data/val/bees/2525379273_dcb26a516d.jpg is: bee\n",
+      "Predicted class for ./hymenoptera_data/val/bees/2809496124_5f25b5946a.jpg is: bee\n",
+      "Predicted class for ./hymenoptera_data/val/bees/2060668999_e11edb10d0.jpg is: bee\n",
+      "Predicted class for ./hymenoptera_data/val/bees/1355974687_1341c1face.jpg is: bee\n",
+      "Predicted class for ./hymenoptera_data/val/bees/2751836205_6f7b5eff30.jpg is: bee\n",
+      "Predicted class for ./hymenoptera_data/val/bees/2702408468_d9ed795f4f.jpg is: bee\n",
+      "Predicted class for ./hymenoptera_data/val/bees/2444778727_4b781ac424.jpg is: bee\n",
+      "Predicted class for ./hymenoptera_data/val/bees/1032546534_06907fe3b3.jpg is: apiary\n",
+      "Predicted class for ./hymenoptera_data/val/bees/215512424_687e1e0821.jpg is: monarch butterfly\n",
+      "Predicted class for ./hymenoptera_data/val/bees/2745389517_250a397f31.jpg is: bee\n",
+      "Predicted class for ./hymenoptera_data/val/bees/590318879_68cf112861.jpg is: bee\n",
+      "Predicted class for ./hymenoptera_data/val/bees/2685605303_9eed79d59d.jpg is: cardoon\n",
+      "Predicted class for ./hymenoptera_data/val/bees/296565463_d07a7bed96.jpg is: bee\n",
+      "Predicted class for ./hymenoptera_data/val/bees/350436573_41f4ecb6c8.jpg is: bee\n",
+      "Predicted class for ./hymenoptera_data/val/bees/290082189_f66cb80bfc.jpg is: bee\n",
+      "Predicted class for ./hymenoptera_data/val/bees/10870992_eebeeb3a12.jpg is: bee\n",
+      "Predicted class for ./hymenoptera_data/val/bees/151603988_2c6f7d14c7.jpg is: bee\n",
+      "Predicted class for ./hymenoptera_data/val/bees/759745145_e8bc776ec8.jpg is: bee\n",
+      "Predicted class for ./hymenoptera_data/val/bees/181171681_c5a1a82ded.jpg is: bee\n",
+      "Predicted class for ./hymenoptera_data/val/bees/2104135106_a65eede1de.jpg is: bee\n",
+      "Predicted class for ./hymenoptera_data/val/bees/2470492902_3572c90f75.jpg is: bee\n",
+      "Predicted class for ./hymenoptera_data/val/bees/353266603_d3eac7e9a0.jpg is: bee\n",
+      "Predicted class for ./hymenoptera_data/val/bees/57459255_752774f1b2.jpg is: bee\n",
+      "Predicted class for ./hymenoptera_data/val/bees/2501530886_e20952b97d.jpg is: bee\n",
+      "Predicted class for ./hymenoptera_data/val/bees/65038344_52a45d090d.jpg is: bee\n",
+      "Predicted class for ./hymenoptera_data/val/bees/220376539_20567395d8.jpg is: bee\n",
+      "Predicted class for ./hymenoptera_data/val/bees/151594775_ee7dc17b60.jpg is: bee\n",
+      "Predicted class for ./hymenoptera_data/val/bees/400262091_701c00031c.jpg is: bee\n",
+      "Predicted class for ./hymenoptera_data/val/bees/72100438_73de9f17af.jpg is: bee\n",
+      "Predicted class for ./hymenoptera_data/val/bees/2407809945_fb525ef54d.jpg is: bee\n",
+      "Predicted class for ./hymenoptera_data/val/ants/459442412_412fecf3fe.jpg is: ant\n",
+      "Predicted class for ./hymenoptera_data/val/ants/800px-Meat_eater_ant_qeen_excavating_hole.jpg is: ant\n",
+      "Predicted class for ./hymenoptera_data/val/ants/892676922_4ab37dce07.jpg is: ant\n",
+      "Predicted class for ./hymenoptera_data/val/ants/F.pergan.28(f).jpg is: ant\n",
+      "Predicted class for ./hymenoptera_data/val/ants/1247887232_edcb61246c.jpg is: leafhopper\n",
+      "Predicted class for ./hymenoptera_data/val/ants/181942028_961261ef48.jpg is: ant\n",
+      "Predicted class for ./hymenoptera_data/val/ants/1073564163_225a64f170.jpg is: mantis\n",
+      "Predicted class for ./hymenoptera_data/val/ants/2238242353_52c82441df.jpg is: ant\n",
+      "Predicted class for ./hymenoptera_data/val/ants/205398178_c395c5e460.jpg is: ant\n",
+      "Predicted class for ./hymenoptera_data/val/ants/263615709_cfb28f6b8e.jpg is: ant\n",
+      "Predicted class for ./hymenoptera_data/val/ants/94999827_36895faade.jpg is: ant\n",
+      "Predicted class for ./hymenoptera_data/val/ants/436944325_d4925a38c7.jpg is: ant\n",
+      "Predicted class for ./hymenoptera_data/val/ants/161076144_124db762d6.jpg is: centipede\n",
+      "Predicted class for ./hymenoptera_data/val/ants/147542264_79506478c2.jpg is: ant\n",
+      "Predicted class for ./hymenoptera_data/val/ants/239161491_86ac23b0a3.jpg is: ant\n",
+      "Predicted class for ./hymenoptera_data/val/ants/1053149811_f62a3410d3.jpg is: ant\n",
+      "Predicted class for ./hymenoptera_data/val/ants/1124525276_816a07c17f.jpg is: ant\n",
+      "Predicted class for ./hymenoptera_data/val/ants/2211974567_ee4606b493.jpg is: ant\n",
+      "Predicted class for ./hymenoptera_data/val/ants/2191997003_379df31291.jpg is: ant\n",
+      "Predicted class for ./hymenoptera_data/val/ants/183260961_64ab754c97.jpg is: ant\n",
+      "Predicted class for ./hymenoptera_data/val/ants/562589509_7e55469b97.jpg is: dung beetle\n",
+      "Predicted class for ./hymenoptera_data/val/ants/ants-devouring-remains-of-large-dead-insect-on-red-tile-in-Stellenbosch-South-Africa-closeup-1-DHD.jpg is: scorpion\n",
+      "Predicted class for ./hymenoptera_data/val/ants/751649788_78dd7d16ce.jpg is: dung beetle\n",
+      "Predicted class for ./hymenoptera_data/val/ants/157401988_d0564a9d02.jpg is: ant\n",
+      "Predicted class for ./hymenoptera_data/val/ants/2039585088_c6f47c592e.jpg is: ant\n",
+      "Predicted class for ./hymenoptera_data/val/ants/153320619_2aeb5fa0ee.jpg is: ant\n",
+      "Predicted class for ./hymenoptera_data/val/ants/649407494_9b6bc4949f.jpg is: ant\n",
+      "Predicted class for ./hymenoptera_data/val/ants/470127071_8b8ee2bd74.jpg is: ant\n",
+      "Predicted class for ./hymenoptera_data/val/ants/Hormiga.jpg is: ant\n",
+      "Predicted class for ./hymenoptera_data/val/ants/502717153_3e4865621a.jpg is: ant\n",
+      "Predicted class for ./hymenoptera_data/val/ants/573151833_ebbc274b77.jpg is: ant\n",
+      "Predicted class for ./hymenoptera_data/val/ants/57264437_a19006872f.jpg is: ant\n",
+      "Predicted class for ./hymenoptera_data/val/ants/540543309_ddbb193ee5.jpg is: ant\n",
+      "Predicted class for ./hymenoptera_data/val/ants/2255445811_dabcdf7258.jpg is: ant\n",
+      "Predicted class for ./hymenoptera_data/val/ants/445356866_6cb3289067.jpg is: ant\n",
+      "Predicted class for ./hymenoptera_data/val/ants/8124241_36b290d372.jpg is: ant\n",
+      "Predicted class for ./hymenoptera_data/val/ants/Ant-1818.jpg is: ant\n",
+      "Predicted class for ./hymenoptera_data/val/ants/208072188_f293096296.jpg is: dung beetle\n",
+      "Predicted class for ./hymenoptera_data/val/ants/2104709400_8831b4fc6f.jpg is: ant\n",
+      "Predicted class for ./hymenoptera_data/val/ants/159515240_d5981e20d1.jpg is: ant\n",
+      "Predicted class for ./hymenoptera_data/val/ants/518746016_bcc28f8b5b.jpg is: ant\n",
+      "Predicted class for ./hymenoptera_data/val/ants/10308379_1b6c72e180.jpg is: ant\n",
+      "Predicted class for ./hymenoptera_data/val/ants/172772109_d0a8e15fb0.jpg is: clothes iron\n",
+      "Predicted class for ./hymenoptera_data/val/ants/1440002809_b268d9a66a.jpg is: ant\n",
+      "Predicted class for ./hymenoptera_data/val/ants/1358854066_5ad8015f7f.jpg is: ant\n",
+      "Predicted class for ./hymenoptera_data/val/ants/412436937_4c2378efc2.jpg is: ant\n",
+      "Predicted class for ./hymenoptera_data/val/ants/119785936_dd428e40c3.jpg is: ant\n",
+      "Predicted class for ./hymenoptera_data/val/ants/1337725712_2eb53cd742.jpg is: ant\n",
+      "Predicted class for ./hymenoptera_data/val/ants/152286280_411648ec27.jpg is: ant\n",
+      "Predicted class for ./hymenoptera_data/val/ants/161292361_c16e0bf57a.jpg is: ant\n",
+      "Predicted class for ./hymenoptera_data/val/ants/477437164_bc3e6e594a.jpg is: ant\n",
+      "Predicted class for ./hymenoptera_data/val/ants/768870506_8f115d3d37.jpg is: ant\n",
+      "Predicted class for ./hymenoptera_data/val/ants/488272201_c5aa281348.jpg is: ant\n",
+      "Predicted class for ./hymenoptera_data/val/ants/2219621907_47bc7cc6b0.jpg is: ant\n",
+      "Predicted class for ./hymenoptera_data/val/ants/854534770_31f6156383.jpg is: ant\n",
+      "Predicted class for ./hymenoptera_data/val/ants/209615353_eeb38ba204.jpg is: ant\n",
+      "Predicted class for ./hymenoptera_data/val/ants/35558229_1fa4608a7a.jpg is: ant\n",
+      "Predicted class for ./hymenoptera_data/val/ants/11381045_b352a47d8c.jpg is: ant\n",
+      "Predicted class for ./hymenoptera_data/val/ants/212100470_b485e7b7b9.jpg is: ant\n",
+      "Predicted class for ./hymenoptera_data/val/ants/1743840368_b5ccda82b7.jpg is: ant\n",
+      "Predicted class for ./hymenoptera_data/val/ants/170652283_ecdaff5d1a.jpg is: ant\n",
+      "Predicted class for ./hymenoptera_data/val/ants/17081114_79b9a27724.jpg is: ant\n",
+      "Predicted class for ./hymenoptera_data/val/ants/8398478_50ef10c47a.jpg is: ant\n",
+      "Predicted class for ./hymenoptera_data/val/ants/1262751255_c56c042b7b.jpg is: ant\n",
+      "Predicted class for ./hymenoptera_data/val/ants/308196310_1db5ffa01b.jpg is: ant\n",
+      "Predicted class for ./hymenoptera_data/val/ants/desert_ant.jpg is: ant\n",
+      "Predicted class for ./hymenoptera_data/val/ants/153783656_85f9c3ac70.jpg is: ant\n",
+      "Predicted class for ./hymenoptera_data/val/ants/1119630822_cd325ea21a.jpg is: ant\n",
+      "Predicted class for ./hymenoptera_data/val/ants/319494379_648fb5a1c6.jpg is: ant\n",
+      "Predicted class for ./hymenoptera_data/val/ants/2127908701_d49dc83c97.jpg is: ant\n"
+     ]
+    }
+   ],
+   "source": [
+    "extensions = (\".png\", \".jpg\", \".jpeg\")\n",
+    "\n",
+    "weights = ResNet50_Weights.DEFAULT\n",
+    "# Download the model if it's not there already. It will take a bit on the first run, after that it's fast\n",
+    "model = models.resnet50(weights=weights)\n",
+    "# Send the model to the GPU\n",
+    "# model.cuda()\n",
+    "# Set layers such as dropout and batchnorm in evaluation mode\n",
+    "model.eval()\n",
+    "\n",
+    "for root, _, files in os.walk(\".\"):\n",
+    "    for file in files:\n",
+    "        if file.lower().endswith(extensions):\n",
+    "            file_path = os.path.join(root, file)\n",
+    "            try:\n",
+    "                # Load the image\n",
+    "                with Image.open(file_path) as image:\n",
+    "                    # Apply the model on the image\n",
+    "                    image = data_transform(image).unsqueeze(0)\n",
+    "                    # Get the 1000-dimensional model output\n",
+    "                    out = model(image)\n",
+    "                    # Find the predicted class\n",
+    "                    print(f\"Predicted class for {file_path} is: {labels[out.argmax()]}\")\n",
+    "            except Exception as e:\n",
+    "                print(f\"Error processing {file_path}: {e}\")\n"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "ab5f9059",
+   "metadata": {},
+   "source": [
+    "Quantized version"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 23,
+   "id": "48fef28f",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# Apply dynamic quantization to the model\n",
+    "quantized_model = torch.quantization.quantize_dynamic(\n",
+    "    model,  # Model to quantize\n",
+    "    {torch.nn.Linear},  # Layers to quantize (typically linear layers)\n",
+    "    dtype=torch.qint8  # Quantization data type\n",
+    ")"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 24,
+   "id": "2da60aaa",
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "Original model size: 100120.349609375 KB\n",
+      "Quantized model size: 94121.02734375 KB\n"
+     ]
+    }
+   ],
+   "source": [
+    "# Size comparison\n",
+    "def get_model_size(model, path=\"temp.pth\"):\n",
+    "    torch.save(model.state_dict(), path)\n",
+    "    size = os.path.getsize(path) / 1024  # Convert bytes to KB\n",
+    "    os.remove(path)  # Clean up\n",
+    "    return size\n",
+    "\n",
+    "print(\"Original model size:\", get_model_size(model), \"KB\")\n",
+    "print(\"Quantized model size:\", get_model_size(quantized_model), \"KB\")"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 25,
+   "id": "1adf2a5c",
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "Predicted class for ./dog.png is: Golden Retriever\n",
+      "Predicted class for ./gaspump.jpg is: gas pump\n",
+      "Predicted class for ./dog.jpg is: Golden Retriever\n",
+      "Predicted class for ./golf-cart.jpg is: golf cart\n",
+      "Predicted class for ./gondola.jpg is: gondola\n",
+      "Predicted class for ./eel.jpg is: eel\n",
+      "Predicted class for ./hymenoptera_data/train/bees/2638074627_6b3ae746a0.jpg is: bee\n",
+      "Predicted class for ./hymenoptera_data/train/bees/507288830_f46e8d4cb2.jpg is: bee\n",
+      "Predicted class for ./hymenoptera_data/train/bees/2405441001_b06c36fa72.jpg is: bee\n",
+      "Predicted class for ./hymenoptera_data/train/bees/2962405283_22718d9617.jpg is: bee\n",
+      "Predicted class for ./hymenoptera_data/train/bees/446296270_d9e8b93ecf.jpg is: bee\n",
+      "Predicted class for ./hymenoptera_data/train/bees/1092977343_cb42b38d62.jpg is: bee\n",
+      "Predicted class for ./hymenoptera_data/train/bees/2704348794_eb5d5178c2.jpg is: bee\n",
+      "Predicted class for ./hymenoptera_data/train/bees/2358061370_9daabbd9ac.jpg is: bee\n",
+      "Predicted class for ./hymenoptera_data/train/bees/2861002136_52c7c6f708.jpg is: bee\n",
+      "Predicted class for ./hymenoptera_data/train/bees/266644509_d30bb16a1b.jpg is: bee\n",
+      "Predicted class for ./hymenoptera_data/train/bees/2470492904_837e97800d.jpg is: bee\n",
+      "Predicted class for ./hymenoptera_data/train/bees/2053200300_8911ef438a.jpg is: bee\n",
+      "Predicted class for ./hymenoptera_data/train/bees/2601176055_8464e6aa71.jpg is: bee\n",
+      "Predicted class for ./hymenoptera_data/train/bees/473618094_8ffdcab215.jpg is: bee\n",
+      "Predicted class for ./hymenoptera_data/train/bees/150013791_969d9a968b.jpg is: bee\n",
+      "Predicted class for ./hymenoptera_data/train/bees/2486746709_c43cec0e42.jpg is: bee\n",
+      "Predicted class for ./hymenoptera_data/train/bees/452462677_7be43af8ff.jpg is: bee\n",
+      "Predicted class for ./hymenoptera_data/train/bees/2397446847_04ef3cd3e1.jpg is: bee\n",
+      "Predicted class for ./hymenoptera_data/train/bees/92663402_37f379e57a.jpg is: bee\n",
+      "Predicted class for ./hymenoptera_data/train/bees/2486729079_62df0920be.jpg is: bee\n",
+      "Predicted class for ./hymenoptera_data/train/bees/2551813042_8a070aeb2b.jpg is: bee\n",
+      "Predicted class for ./hymenoptera_data/train/bees/2792000093_e8ae0718cf.jpg is: bee\n",
+      "Predicted class for ./hymenoptera_data/train/bees/2477324698_3d4b1b1cab.jpg is: bee\n",
+      "Predicted class for ./hymenoptera_data/train/bees/2959730355_416a18c63c.jpg is: bee\n",
+      "Predicted class for ./hymenoptera_data/train/bees/774440991_63a4aa0cbe.jpg is: bee\n",
+      "Predicted class for ./hymenoptera_data/train/bees/2652877533_a564830cbf.jpg is: bee\n",
+      "Predicted class for ./hymenoptera_data/train/bees/21399619_3e61e5bb6f.jpg is: sea urchin\n",
+      "Predicted class for ./hymenoptera_data/train/bees/586041248_3032e277a9.jpg is: fly\n",
+      "Predicted class for ./hymenoptera_data/train/bees/39672681_1302d204d1.jpg is: bee\n",
+      "Predicted class for ./hymenoptera_data/train/bees/2345177635_caf07159b3.jpg is: bee\n",
+      "Predicted class for ./hymenoptera_data/train/bees/2321139806_d73d899e66.jpg is: bee\n",
+      "Predicted class for ./hymenoptera_data/train/bees/2528444139_fa728b0f5b.jpg is: bee\n",
+      "Predicted class for ./hymenoptera_data/train/bees/3044402684_3853071a87.jpg is: bee\n",
+      "Predicted class for ./hymenoptera_data/train/bees/2683605182_9d2a0c66cf.jpg is: honeycomb\n",
+      "Predicted class for ./hymenoptera_data/train/bees/2728759455_ce9bb8cd7a.jpg is: bee\n",
+      "Predicted class for ./hymenoptera_data/train/bees/522104315_5d3cb2758e.jpg is: bee\n",
+      "Predicted class for ./hymenoptera_data/train/bees/2493379287_4100e1dacc.jpg is: corn\n",
+      "Predicted class for ./hymenoptera_data/train/bees/478701318_bbd5e557b8.jpg is: bee\n",
+      "Predicted class for ./hymenoptera_data/train/bees/2610833167_79bf0bcae5.jpg is: bee\n",
+      "Predicted class for ./hymenoptera_data/train/bees/2710368626_cb42882dc8.jpg is: bee\n",
+      "Predicted class for ./hymenoptera_data/train/bees/1691282715_0addfdf5e8.jpg is: bee\n",
+      "Predicted class for ./hymenoptera_data/train/bees/2756397428_1d82a08807.jpg is: bee\n",
+      "Predicted class for ./hymenoptera_data/train/bees/1799726602_8580867f71.jpg is: bee\n",
+      "Predicted class for ./hymenoptera_data/train/bees/2477349551_e75c97cf4d.jpg is: bee\n",
+      "Predicted class for ./hymenoptera_data/train/bees/2031225713_50ed499635.jpg is: bee\n",
+      "Predicted class for ./hymenoptera_data/train/bees/2610838525_fe8e3cae47.jpg is: bee\n",
+      "Predicted class for ./hymenoptera_data/train/bees/3074585407_9854eb3153.jpg is: bee\n",
+      "Predicted class for ./hymenoptera_data/train/bees/2330918208_8074770c20.jpg is: bee\n",
+      "Predicted class for ./hymenoptera_data/train/bees/465133211_80e0c27f60.jpg is: bee\n",
+      "Predicted class for ./hymenoptera_data/train/bees/3079610310_ac2d0ae7bc.jpg is: bee\n",
+      "Predicted class for ./hymenoptera_data/train/bees/2495722465_879acf9d85.jpg is: bee\n",
+      "Predicted class for ./hymenoptera_data/train/bees/444532809_9e931e2279.jpg is: bee\n",
+      "Predicted class for ./hymenoptera_data/train/bees/1807583459_4fe92b3133.jpg is: bee\n",
+      "Predicted class for ./hymenoptera_data/train/bees/359928878_b3b418c728.jpg is: bee\n",
+      "Predicted class for ./hymenoptera_data/train/bees/2037437624_2d7bce461f.jpg is: bee\n",
+      "Predicted class for ./hymenoptera_data/train/bees/509247772_2db2d01374.jpg is: bee\n",
+      "Predicted class for ./hymenoptera_data/train/bees/90179376_abc234e5f4.jpg is: bee\n",
+      "Predicted class for ./hymenoptera_data/train/bees/3030772428_8578335616.jpg is: bee\n",
+      "Predicted class for ./hymenoptera_data/train/bees/873076652_eb098dab2d.jpg is: bee\n",
+      "Predicted class for ./hymenoptera_data/train/bees/17209602_fe5a5a746f.jpg is: bee\n",
+      "Predicted class for ./hymenoptera_data/train/bees/421515404_e87569fd8b.jpg is: bee\n",
+      "Predicted class for ./hymenoptera_data/train/bees/1097045929_1753d1c765.jpg is: honeycomb\n",
+      "Predicted class for ./hymenoptera_data/train/bees/2781170484_5d61835d63.jpg is: bee\n",
+      "Predicted class for ./hymenoptera_data/train/bees/3100226504_c0d4f1e3f1.jpg is: bee\n",
+      "Predicted class for ./hymenoptera_data/train/bees/2617161745_fa3ebe85b4.jpg is: bee\n",
+      "Predicted class for ./hymenoptera_data/train/bees/2580598377_a4caecdb54.jpg is: bee\n",
+      "Predicted class for ./hymenoptera_data/train/bees/208702903_42fb4d9748.jpg is: daisy\n",
+      "Predicted class for ./hymenoptera_data/train/bees/537309131_532bfa59ea.jpg is: bee\n",
+      "Predicted class for ./hymenoptera_data/train/bees/969455125_58c797ef17.jpg is: sulphur butterfly\n",
+      "Predicted class for ./hymenoptera_data/train/bees/365759866_b15700c59b.jpg is: cardoon\n",
+      "Predicted class for ./hymenoptera_data/train/bees/196430254_46bd129ae7.jpg is: bee\n",
+      "Predicted class for ./hymenoptera_data/train/bees/1232245714_f862fbe385.jpg is: bee\n",
+      "Predicted class for ./hymenoptera_data/train/bees/2445215254_51698ff797.jpg is: bee\n",
+      "Predicted class for ./hymenoptera_data/train/bees/760526046_547e8b381f.jpg is: bee\n",
+      "Predicted class for ./hymenoptera_data/train/bees/513545352_fd3e7c7c5d.jpg is: bee\n",
+      "Predicted class for ./hymenoptera_data/train/bees/2634617358_f32fd16bea.jpg is: bee\n",
+      "Predicted class for ./hymenoptera_data/train/bees/39747887_42df2855ee.jpg is: bee\n",
+      "Predicted class for ./hymenoptera_data/train/bees/354167719_22dca13752.jpg is: bee\n",
+      "Predicted class for ./hymenoptera_data/train/bees/2384149906_2cd8b0b699.jpg is: bee\n",
+      "Predicted class for ./hymenoptera_data/train/bees/2625499656_e3415e374d.jpg is: bee\n",
+      "Predicted class for ./hymenoptera_data/train/bees/2645107662_b73a8595cc.jpg is: bee\n",
+      "Predicted class for ./hymenoptera_data/train/bees/154600396_53e1252e52.jpg is: bee\n",
+      "Predicted class for ./hymenoptera_data/train/bees/279113587_b4843db199.jpg is: bee\n",
+      "Predicted class for ./hymenoptera_data/train/bees/98391118_bdb1e80cce.jpg is: fly\n",
+      "Predicted class for ./hymenoptera_data/train/bees/132511197_0b86ad0fff.jpg is: bee\n",
+      "Predicted class for ./hymenoptera_data/train/bees/2707440199_cd170bd512.jpg is: cardoon\n",
+      "Predicted class for ./hymenoptera_data/train/bees/342758693_c56b89b6b6.jpg is: bee\n",
+      "Predicted class for ./hymenoptera_data/train/bees/36900412_92b81831ad.jpg is: bee\n",
+      "Predicted class for ./hymenoptera_data/train/bees/2364597044_3c3e3fc391.jpg is: bee\n",
+      "Predicted class for ./hymenoptera_data/train/bees/1295655112_7813f37d21.jpg is: bee\n",
+      "Predicted class for ./hymenoptera_data/train/bees/2227611847_ec72d40403.jpg is: bee\n",
+      "Predicted class for ./hymenoptera_data/train/bees/205835650_e6f2614bee.jpg is: bee\n",
+      "Predicted class for ./hymenoptera_data/train/bees/1093831624_fb5fbe2308.jpg is: bee\n",
+      "Predicted class for ./hymenoptera_data/train/bees/129236073_0985e91c7d.jpg is: bee\n",
+      "Predicted class for ./hymenoptera_data/train/bees/198508668_97d818b6c4.jpg is: bee\n",
+      "Predicted class for ./hymenoptera_data/train/bees/1508176360_2972117c9d.jpg is: bee\n",
+      "Predicted class for ./hymenoptera_data/train/bees/457457145_5f86eb7e9c.jpg is: bee\n",
+      "Predicted class for ./hymenoptera_data/train/bees/2722592222_258d473e17.jpg is: bee\n",
+      "Predicted class for ./hymenoptera_data/train/bees/2822388965_f6dca2a275.jpg is: bee\n",
+      "Predicted class for ./hymenoptera_data/train/bees/2651621464_a2fa8722eb.jpg is: bee\n",
+      "Predicted class for ./hymenoptera_data/train/bees/132826773_dbbcb117b9.jpg is: bee\n",
+      "Predicted class for ./hymenoptera_data/train/bees/476347960_52edd72b06.jpg is: bee\n",
+      "Predicted class for ./hymenoptera_data/train/bees/3006264892_30e9cced70.jpg is: bee\n",
+      "Predicted class for ./hymenoptera_data/train/bees/760568592_45a52c847f.jpg is: bee\n",
+      "Predicted class for ./hymenoptera_data/train/bees/2452236943_255bfd9e58.jpg is: bee\n",
+      "Predicted class for ./hymenoptera_data/train/bees/472288710_2abee16fa0.jpg is: fly\n",
+      "Predicted class for ./hymenoptera_data/train/bees/2908916142_a7ac8b57a8.jpg is: bee\n",
+      "Predicted class for ./hymenoptera_data/train/bees/95238259_98470c5b10.jpg is: bee\n",
+      "Predicted class for ./hymenoptera_data/train/bees/85112639_6e860b0469.jpg is: bee\n",
+      "Predicted class for ./hymenoptera_data/train/bees/2801728106_833798c909.jpg is: bee\n",
+      "Predicted class for ./hymenoptera_data/train/bees/174142798_e5ad6d76e0.jpg is: bee\n",
+      "Predicted class for ./hymenoptera_data/train/bees/2467959963_a7831e9ff0.jpg is: bee\n",
+      "Predicted class for ./hymenoptera_data/train/bees/2538361678_9da84b77e3.jpg is: bee\n",
+      "Predicted class for ./hymenoptera_data/train/bees/196658222_3fffd79c67.jpg is: daisy\n",
+      "Predicted class for ./hymenoptera_data/train/bees/29494643_e3410f0d37.jpg is: bee\n",
+      "Predicted class for ./hymenoptera_data/train/bees/16838648_415acd9e3f.jpg is: bee\n",
+      "Predicted class for ./hymenoptera_data/train/bees/3030189811_01d095b793.jpg is: bee\n",
+      "Predicted class for ./hymenoptera_data/train/bees/469333327_358ba8fe8a.jpg is: bee\n",
+      "Predicted class for ./hymenoptera_data/train/bees/452462695_40a4e5b559.jpg is: bee\n",
+      "Predicted class for ./hymenoptera_data/train/bees/3090975720_71f12e6de4.jpg is: bee\n",
+      "Predicted class for ./hymenoptera_data/train/bees/2765347790_da6cf6cb40.jpg is: bee\n",
+      "Predicted class for ./hymenoptera_data/train/ants/957233405_25c1d1187b.jpg is: ant\n",
+      "Predicted class for ./hymenoptera_data/train/ants/2288481644_83ff7e4572.jpg is: ant\n",
+      "Predicted class for ./hymenoptera_data/train/ants/67270775_e9fdf77e9d.jpg is: ant\n",
+      "Predicted class for ./hymenoptera_data/train/ants/1808777855_2a895621d7.jpg is: ant\n",
+      "Predicted class for ./hymenoptera_data/train/ants/VietnameseAntMimicSpider.jpg is: southern black widow\n",
+      "Predicted class for ./hymenoptera_data/train/ants/swiss-army-ant.jpg is: ant\n",
+      "Predicted class for ./hymenoptera_data/train/ants/termite-vs-ant.jpg is: ant\n",
+      "Predicted class for ./hymenoptera_data/train/ants/245647475_9523dfd13e.jpg is: ant\n",
+      "Predicted class for ./hymenoptera_data/train/ants/384191229_5779cf591b.jpg is: ant\n",
+      "Predicted class for ./hymenoptera_data/train/ants/hormiga_co_por.jpg is: ant\n",
+      "Predicted class for ./hymenoptera_data/train/ants/531979952_bde12b3bc0.jpg is: ant\n",
+      "Predicted class for ./hymenoptera_data/train/ants/224655713_3956f7d39a.jpg is: ant\n",
+      "Predicted class for ./hymenoptera_data/train/ants/132478121_2a430adea2.jpg is: ant\n",
+      "Predicted class for ./hymenoptera_data/train/ants/512863248_43c8ce579b.jpg is: ant\n",
+      "Predicted class for ./hymenoptera_data/train/ants/533848102_70a85ad6dd.jpg is: ant\n",
+      "Predicted class for ./hymenoptera_data/train/ants/201558278_fe4caecc76.jpg is: ant\n",
+      "Predicted class for ./hymenoptera_data/train/ants/army-ants-red-picture.jpg is: ant\n",
+      "Predicted class for ./hymenoptera_data/train/ants/MehdiabadiAnt2_600.jpg is: ant\n",
+      "Predicted class for ./hymenoptera_data/train/ants/334167043_cbd1adaeb9.jpg is: ant\n",
+      "Predicted class for ./hymenoptera_data/train/ants/20935278_9190345f6b.jpg is: ant\n",
+      "Predicted class for ./hymenoptera_data/train/ants/540889389_48bb588b21.jpg is: ant\n",
+      "Predicted class for ./hymenoptera_data/train/ants/466430434_4000737de9.jpg is: ant\n",
+      "Predicted class for ./hymenoptera_data/train/ants/649026570_e58656104b.jpg is: ant\n",
+      "Predicted class for ./hymenoptera_data/train/ants/196057951_63bf063b92.jpg is: ant\n",
+      "Predicted class for ./hymenoptera_data/train/ants/1660097129_384bf54490.jpg is: ant\n",
+      "Predicted class for ./hymenoptera_data/train/ants/1286984635_5119e80de1.jpg is: ant\n",
+      "Predicted class for ./hymenoptera_data/train/ants/6240329_72c01e663e.jpg is: ant\n",
+      "Predicted class for ./hymenoptera_data/train/ants/Ant_1.jpg is: ant\n",
+      "Predicted class for ./hymenoptera_data/train/ants/522163566_fec115ca66.jpg is: ant\n",
+      "Predicted class for ./hymenoptera_data/train/ants/0013035.jpg is: ant\n",
+      "Predicted class for ./hymenoptera_data/train/ants/24335309_c5ea483bb8.jpg is: ant\n",
+      "Predicted class for ./hymenoptera_data/train/ants/150801171_cd86f17ed8.jpg is: ant\n",
+      "Predicted class for ./hymenoptera_data/train/ants/403746349_71384f5b58.jpg is: ant\n",
+      "Predicted class for ./hymenoptera_data/train/ants/460372577_f2f6a8c9fc.jpg is: ant\n",
+      "Predicted class for ./hymenoptera_data/train/ants/386190770_672743c9a7.jpg is: ant\n",
+      "Predicted class for ./hymenoptera_data/train/ants/886401651_f878e888cd.jpg is: ant\n",
+      "Predicted class for ./hymenoptera_data/train/ants/506249802_207cd979b4.jpg is: ant\n",
+      "Predicted class for ./hymenoptera_data/train/ants/841049277_b28e58ad05.jpg is: shoji\n",
+      "Predicted class for ./hymenoptera_data/train/ants/707895295_009cf23188.jpg is: ant\n",
+      "Predicted class for ./hymenoptera_data/train/ants/Nepenthes_rafflesiana_ant.jpg is: ant\n",
+      "Predicted class for ./hymenoptera_data/train/ants/518773929_734dbc5ff4.jpg is: ant\n",
+      "Predicted class for ./hymenoptera_data/train/ants/342438950_a3da61deab.jpg is: ant\n",
+      "Predicted class for ./hymenoptera_data/train/ants/1368913450_e146e2fb6d.jpg is: ant\n",
+      "Predicted class for ./hymenoptera_data/train/ants/49375974_e28ba6f17e.jpg is: ant\n",
+      "Predicted class for ./hymenoptera_data/train/ants/822537660_caf4ba5514.jpg is: ant\n",
+      "Predicted class for ./hymenoptera_data/train/ants/36439863_0bec9f554f.jpg is: ant\n",
+      "Predicted class for ./hymenoptera_data/train/ants/175998972.jpg is: ant\n",
+      "Predicted class for ./hymenoptera_data/train/ants/382971067_0bfd33afe0.jpg is: ant\n",
+      "Predicted class for ./hymenoptera_data/train/ants/1804095607_0341701e1c.jpg is: ant\n",
+      "Predicted class for ./hymenoptera_data/train/ants/188552436_605cc9b36b.jpg is: ant\n",
+      "Predicted class for ./hymenoptera_data/train/ants/339670531_94b75ae47a.jpg is: ant\n",
+      "Predicted class for ./hymenoptera_data/train/ants/374435068_7eee412ec4.jpg is: ant\n",
+      "Predicted class for ./hymenoptera_data/train/ants/1473187633_63ccaacea6.jpg is: cicada\n",
+      "Predicted class for ./hymenoptera_data/train/ants/258217966_d9d90d18d3.jpg is: ant\n",
+      "Predicted class for ./hymenoptera_data/train/ants/150801003_3390b73135.jpg is: ant\n",
+      "Predicted class for ./hymenoptera_data/train/ants/1030023514_aad5c608f9.jpg is: ant\n",
+      "Predicted class for ./hymenoptera_data/train/ants/2288450226_a6e96e8fdf.jpg is: ant\n",
+      "Predicted class for ./hymenoptera_data/train/ants/541630764_dbd285d63c.jpg is: ant\n",
+      "Predicted class for ./hymenoptera_data/train/ants/275429470_b2d7d9290b.jpg is: ant\n",
+      "Predicted class for ./hymenoptera_data/train/ants/6240338_93729615ec.jpg is: ant\n",
+      "Predicted class for ./hymenoptera_data/train/ants/424873399_47658a91fb.jpg is: ant\n",
+      "Predicted class for ./hymenoptera_data/train/ants/543417860_b14237f569.jpg is: ant\n",
+      "Predicted class for ./hymenoptera_data/train/ants/318052216_84dff3f98a.jpg is: ant\n",
+      "Predicted class for ./hymenoptera_data/train/ants/149244013_c529578289.jpg is: ant\n",
+      "Predicted class for ./hymenoptera_data/train/ants/1262877379_64fcada201.jpg is: ant\n",
+      "Predicted class for ./hymenoptera_data/train/ants/450057712_771b3bfc91.jpg is: ant\n",
+      "Predicted class for ./hymenoptera_data/train/ants/662541407_ff8db781e7.jpg is: ant\n",
+      "Predicted class for ./hymenoptera_data/train/ants/154124431_65460430f2.jpg is: ant\n",
+      "Predicted class for ./hymenoptera_data/train/ants/2019439677_2db655d361.jpg is: ant\n",
+      "Predicted class for ./hymenoptera_data/train/ants/1489674356_09d48dde0a.jpg is: ant\n",
+      "Predicted class for ./hymenoptera_data/train/ants/892108839_f1aad4ca46.jpg is: ant\n",
+      "Predicted class for ./hymenoptera_data/train/ants/522415432_2218f34bf8.jpg is: ant\n",
+      "Predicted class for ./hymenoptera_data/train/ants/178538489_bec7649292.jpg is: ant\n",
+      "Predicted class for ./hymenoptera_data/train/ants/ant photos.jpg is: ant\n",
+      "Predicted class for ./hymenoptera_data/train/ants/474806473_ca6caab245.jpg is: ladybug\n",
+      "Predicted class for ./hymenoptera_data/train/ants/408393566_b5b694119b.jpg is: ant\n",
+      "Predicted class for ./hymenoptera_data/train/ants/2278278459_6b99605e50.jpg is: ant\n",
+      "Predicted class for ./hymenoptera_data/train/ants/formica.jpeg is: ant\n",
+      "Predicted class for ./hymenoptera_data/train/ants/1269756697_0bce92cdab.jpg is: ant\n",
+      "Predicted class for ./hymenoptera_data/train/ants/2292213964_ca51ce4bef.jpg is: apiary\n",
+      "Predicted class for ./hymenoptera_data/train/ants/226951206_d6bf946504.jpg is: ant\n",
+      "Predicted class for ./hymenoptera_data/train/ants/938946700_ca1c669085.jpg is: ant\n",
+      "Predicted class for ./hymenoptera_data/train/ants/2265824718_2c96f485da.jpg is: ant\n",
+      "Predicted class for ./hymenoptera_data/train/ants/392382602_1b7bed32fa.jpg is: screwdriver\n",
+      "Predicted class for ./hymenoptera_data/train/ants/69639610_95e0de17aa.jpg is: ant\n",
+      "Predicted class for ./hymenoptera_data/train/ants/7759525_1363d24e88.jpg is: ant\n",
+      "Predicted class for ./hymenoptera_data/train/ants/424119020_6d57481dab.jpg is: ant\n",
+      "Predicted class for ./hymenoptera_data/train/ants/162603798_40b51f1654.jpg is: ant\n",
+      "Predicted class for ./hymenoptera_data/train/ants/28847243_e79fe052cd.jpg is: ant\n",
+      "Predicted class for ./hymenoptera_data/train/ants/998118368_6ac1d91f81.jpg is: ant\n",
+      "Predicted class for ./hymenoptera_data/train/ants/6743948_2b8c096dda.jpg is: crutch\n",
+      "Predicted class for ./hymenoptera_data/train/ants/484293231_e53cfc0c89.jpg is: ant\n",
+      "Predicted class for ./hymenoptera_data/train/ants/512164029_c0a66b8498.jpg is: ant\n",
+      "Predicted class for ./hymenoptera_data/train/ants/2265825502_fff99cfd2d.jpg is: ant\n",
+      "Predicted class for ./hymenoptera_data/train/ants/459694881_ac657d3187.jpg is: ant\n",
+      "Predicted class for ./hymenoptera_data/train/ants/1099452230_d1949d3250.jpg is: bee\n",
+      "Predicted class for ./hymenoptera_data/train/ants/kurokusa.jpg is: ant\n",
+      "Predicted class for ./hymenoptera_data/train/ants/116570827_e9c126745d.jpg is: ant\n",
+      "Predicted class for ./hymenoptera_data/train/ants/167890289_dd5ba923f3.jpg is: ant\n",
+      "Predicted class for ./hymenoptera_data/train/ants/1360291657_dc248c5eea.jpg is: ant\n",
+      "Predicted class for ./hymenoptera_data/train/ants/460874319_0a45ab4d05.jpg is: ant\n",
+      "Predicted class for ./hymenoptera_data/train/ants/45472593_bfd624f8dc.jpg is: ant\n",
+      "Predicted class for ./hymenoptera_data/train/ants/207947948_3ab29d7207.jpg is: ant\n",
+      "Predicted class for ./hymenoptera_data/train/ants/535522953_308353a07c.jpg is: ant\n",
+      "Predicted class for ./hymenoptera_data/train/ants/255434217_1b2b3fe0a4.jpg is: ant\n",
+      "Predicted class for ./hymenoptera_data/train/ants/560966032_988f4d7bc4.jpg is: ant\n",
+      "Predicted class for ./hymenoptera_data/train/ants/148715752_302c84f5a4.jpg is: harvestman\n",
+      "Predicted class for ./hymenoptera_data/train/ants/470127037_513711fd21.jpg is: ant\n",
+      "Predicted class for ./hymenoptera_data/train/ants/9715481_b3cb4114ff.jpg is: ant\n",
+      "Predicted class for ./hymenoptera_data/train/ants/684133190_35b62c0c1d.jpg is: ant\n",
+      "Predicted class for ./hymenoptera_data/train/ants/trap-jaw-ant-insect-bg.jpg is: ant\n",
+      "Predicted class for ./hymenoptera_data/train/ants/196757565_326437f5fe.jpg is: ant\n",
+      "Predicted class for ./hymenoptera_data/train/ants/5650366_e22b7e1065.jpg is: ant\n",
+      "Predicted class for ./hymenoptera_data/train/ants/1095476100_3906d8afde.jpg is: ant\n",
+      "Predicted class for ./hymenoptera_data/train/ants/1225872729_6f0856588f.jpg is: ant\n",
+      "Predicted class for ./hymenoptera_data/train/ants/795000156_a9900a4a71.jpg is: ant\n",
+      "Predicted class for ./hymenoptera_data/train/ants/1924473702_daa9aacdbe.jpg is: ant\n",
+      "Predicted class for ./hymenoptera_data/train/ants/82852639_52b7f7f5e3.jpg is: ant\n",
+      "Predicted class for ./hymenoptera_data/train/ants/1693954099_46d4c20605.jpg is: ant\n",
+      "Predicted class for ./hymenoptera_data/train/ants/201790779_527f4c0168.jpg is: ant\n",
+      "Predicted class for ./hymenoptera_data/train/ants/475961153_b8c13fd405.jpg is: ant\n",
+      "Predicted class for ./hymenoptera_data/train/ants/506249836_717b73f540.jpg is: ant\n",
+      "Predicted class for ./hymenoptera_data/train/ants/1917341202_d00a7f9af5.jpg is: ant\n",
+      "Predicted class for ./hymenoptera_data/val/bees/2717418782_bd83307d9f.jpg is: bee\n",
+      "Predicted class for ./hymenoptera_data/val/bees/2173503984_9c6aaaa7e2.jpg is: bee\n",
+      "Predicted class for ./hymenoptera_data/val/bees/54736755_c057723f64.jpg is: bee\n",
+      "Predicted class for ./hymenoptera_data/val/bees/2103637821_8d26ee6b90.jpg is: bee\n",
+      "Predicted class for ./hymenoptera_data/val/bees/603711658_4c8cd2201e.jpg is: bee\n",
+      "Predicted class for ./hymenoptera_data/val/bees/238161922_55fa9a76ae.jpg is: bee\n",
+      "Predicted class for ./hymenoptera_data/val/bees/2457841282_7867f16639.jpg is: bee\n",
+      "Predicted class for ./hymenoptera_data/val/bees/6a00d8341c630a53ef00e553d0beb18834-800wi.jpg is: bee\n",
+      "Predicted class for ./hymenoptera_data/val/bees/177677657_a38c97e572.jpg is: bee\n",
+      "Predicted class for ./hymenoptera_data/val/bees/348291597_ee836fbb1a.jpg is: bee\n",
+      "Predicted class for ./hymenoptera_data/val/bees/152789693_220b003452.jpg is: bee\n",
+      "Predicted class for ./hymenoptera_data/val/bees/2782079948_8d4e94a826.jpg is: bee\n",
+      "Predicted class for ./hymenoptera_data/val/bees/576452297_897023f002.jpg is: bee\n",
+      "Predicted class for ./hymenoptera_data/val/bees/1181173278_23c36fac71.jpg is: bee\n",
+      "Predicted class for ./hymenoptera_data/val/bees/3077452620_548c79fda0.jpg is: bee\n",
+      "Predicted class for ./hymenoptera_data/val/bees/586474709_ae436da045.jpg is: bee\n",
+      "Predicted class for ./hymenoptera_data/val/bees/26589803_5ba7000313.jpg is: bee\n",
+      "Predicted class for ./hymenoptera_data/val/bees/2478216347_535c8fe6d7.jpg is: bee\n",
+      "Predicted class for ./hymenoptera_data/val/bees/2668391343_45e272cd07.jpg is: bee\n",
+      "Predicted class for ./hymenoptera_data/val/bees/540976476_844950623f.jpg is: bee\n",
+      "Predicted class for ./hymenoptera_data/val/bees/144098310_a4176fd54d.jpg is: bee\n",
+      "Predicted class for ./hymenoptera_data/val/bees/1486120850_490388f84b.jpg is: bee\n",
+      "Predicted class for ./hymenoptera_data/val/bees/2670536155_c170f49cd0.jpg is: bee\n",
+      "Predicted class for ./hymenoptera_data/val/bees/1519368889_4270261ee3.jpg is: mushroom\n",
+      "Predicted class for ./hymenoptera_data/val/bees/2506114833_90a41c5267.jpg is: daisy\n",
+      "Predicted class for ./hymenoptera_data/val/bees/2438480600_40a1249879.jpg is: bee\n",
+      "Predicted class for ./hymenoptera_data/val/bees/187130242_4593a4c610.jpg is: bee\n",
+      "Predicted class for ./hymenoptera_data/val/bees/224841383_d050f5f510.jpg is: bee\n",
+      "Predicted class for ./hymenoptera_data/val/bees/59798110_2b6a3c8031.jpg is: bee\n",
+      "Predicted class for ./hymenoptera_data/val/bees/2883093452_7e3a1eb53f.jpg is: bee\n",
+      "Predicted class for ./hymenoptera_data/val/bees/2321144482_f3785ba7b2.jpg is: bee\n",
+      "Predicted class for ./hymenoptera_data/val/bees/abeja.jpg is: bee\n",
+      "Predicted class for ./hymenoptera_data/val/bees/203868383_0fcbb48278.jpg is: bee\n",
+      "Predicted class for ./hymenoptera_data/val/bees/44105569_16720a960c.jpg is: bee\n",
+      "Predicted class for ./hymenoptera_data/val/bees/272986700_d4d4bf8c4b.jpg is: bee\n",
+      "Predicted class for ./hymenoptera_data/val/bees/464594019_1b24a28bb1.jpg is: bee\n",
+      "Predicted class for ./hymenoptera_data/val/bees/485743562_d8cc6b8f73.jpg is: bee\n",
+      "Predicted class for ./hymenoptera_data/val/bees/2815838190_0a9889d995.jpg is: bee\n",
+      "Predicted class for ./hymenoptera_data/val/bees/603709866_a97c7cfc72.jpg is: bee\n",
+      "Predicted class for ./hymenoptera_data/val/bees/2086294791_6f3789d8a6.jpg is: bee\n",
+      "Predicted class for ./hymenoptera_data/val/bees/1328423762_f7a88a8451.jpg is: bee\n",
+      "Predicted class for ./hymenoptera_data/val/bees/416144384_961c326481.jpg is: dung beetle\n",
+      "Predicted class for ./hymenoptera_data/val/bees/2709775832_85b4b50a57.jpg is: apiary\n",
+      "Predicted class for ./hymenoptera_data/val/bees/1297972485_33266a18d9.jpg is: bee\n",
+      "Predicted class for ./hymenoptera_data/val/bees/2415414155_1916f03b42.jpg is: bee\n",
+      "Predicted class for ./hymenoptera_data/val/bees/149973093_da3c446268.jpg is: bee\n",
+      "Predicted class for ./hymenoptera_data/val/bees/2741763055_9a7bb00802.jpg is: bee\n",
+      "Predicted class for ./hymenoptera_data/val/bees/936182217_c4caa5222d.jpg is: bee\n",
+      "Predicted class for ./hymenoptera_data/val/bees/1799729694_0c40101071.jpg is: bee\n",
+      "Predicted class for ./hymenoptera_data/val/bees/2841437312_789699c740.jpg is: bee\n",
+      "Predicted class for ./hymenoptera_data/val/bees/2509402554_31821cb0b6.jpg is: bee\n",
+      "Predicted class for ./hymenoptera_data/val/bees/372228424_16da1f8884.jpg is: bee\n",
+      "Predicted class for ./hymenoptera_data/val/bees/456097971_860949c4fc.jpg is: bee\n",
+      "Predicted class for ./hymenoptera_data/val/bees/2525379273_dcb26a516d.jpg is: bee\n",
+      "Predicted class for ./hymenoptera_data/val/bees/2809496124_5f25b5946a.jpg is: bee\n",
+      "Predicted class for ./hymenoptera_data/val/bees/2060668999_e11edb10d0.jpg is: bee\n",
+      "Predicted class for ./hymenoptera_data/val/bees/1355974687_1341c1face.jpg is: bee\n",
+      "Predicted class for ./hymenoptera_data/val/bees/2751836205_6f7b5eff30.jpg is: bee\n",
+      "Predicted class for ./hymenoptera_data/val/bees/2702408468_d9ed795f4f.jpg is: bee\n",
+      "Predicted class for ./hymenoptera_data/val/bees/2444778727_4b781ac424.jpg is: bee\n",
+      "Predicted class for ./hymenoptera_data/val/bees/1032546534_06907fe3b3.jpg is: apiary\n",
+      "Predicted class for ./hymenoptera_data/val/bees/215512424_687e1e0821.jpg is: monarch butterfly\n",
+      "Predicted class for ./hymenoptera_data/val/bees/2745389517_250a397f31.jpg is: bee\n",
+      "Predicted class for ./hymenoptera_data/val/bees/590318879_68cf112861.jpg is: bee\n",
+      "Predicted class for ./hymenoptera_data/val/bees/2685605303_9eed79d59d.jpg is: cardoon\n",
+      "Predicted class for ./hymenoptera_data/val/bees/296565463_d07a7bed96.jpg is: bee\n",
+      "Predicted class for ./hymenoptera_data/val/bees/350436573_41f4ecb6c8.jpg is: bee\n",
+      "Predicted class for ./hymenoptera_data/val/bees/290082189_f66cb80bfc.jpg is: bee\n",
+      "Predicted class for ./hymenoptera_data/val/bees/10870992_eebeeb3a12.jpg is: bee\n",
+      "Predicted class for ./hymenoptera_data/val/bees/151603988_2c6f7d14c7.jpg is: bee\n",
+      "Predicted class for ./hymenoptera_data/val/bees/759745145_e8bc776ec8.jpg is: bee\n",
+      "Predicted class for ./hymenoptera_data/val/bees/181171681_c5a1a82ded.jpg is: bee\n",
+      "Predicted class for ./hymenoptera_data/val/bees/2104135106_a65eede1de.jpg is: bee\n",
+      "Predicted class for ./hymenoptera_data/val/bees/2470492902_3572c90f75.jpg is: bee\n",
+      "Predicted class for ./hymenoptera_data/val/bees/353266603_d3eac7e9a0.jpg is: bee\n",
+      "Predicted class for ./hymenoptera_data/val/bees/57459255_752774f1b2.jpg is: bee\n",
+      "Predicted class for ./hymenoptera_data/val/bees/2501530886_e20952b97d.jpg is: bee\n",
+      "Predicted class for ./hymenoptera_data/val/bees/65038344_52a45d090d.jpg is: bee\n",
+      "Predicted class for ./hymenoptera_data/val/bees/220376539_20567395d8.jpg is: bee\n",
+      "Predicted class for ./hymenoptera_data/val/bees/151594775_ee7dc17b60.jpg is: bee\n",
+      "Predicted class for ./hymenoptera_data/val/bees/400262091_701c00031c.jpg is: bee\n",
+      "Predicted class for ./hymenoptera_data/val/bees/72100438_73de9f17af.jpg is: bee\n",
+      "Predicted class for ./hymenoptera_data/val/bees/2407809945_fb525ef54d.jpg is: bee\n",
+      "Predicted class for ./hymenoptera_data/val/ants/459442412_412fecf3fe.jpg is: ant\n",
+      "Predicted class for ./hymenoptera_data/val/ants/800px-Meat_eater_ant_qeen_excavating_hole.jpg is: ant\n",
+      "Predicted class for ./hymenoptera_data/val/ants/892676922_4ab37dce07.jpg is: ant\n",
+      "Predicted class for ./hymenoptera_data/val/ants/F.pergan.28(f).jpg is: ant\n",
+      "Predicted class for ./hymenoptera_data/val/ants/1247887232_edcb61246c.jpg is: leafhopper\n",
+      "Predicted class for ./hymenoptera_data/val/ants/181942028_961261ef48.jpg is: ant\n",
+      "Predicted class for ./hymenoptera_data/val/ants/1073564163_225a64f170.jpg is: mantis\n",
+      "Predicted class for ./hymenoptera_data/val/ants/2238242353_52c82441df.jpg is: ant\n",
+      "Predicted class for ./hymenoptera_data/val/ants/205398178_c395c5e460.jpg is: ant\n",
+      "Predicted class for ./hymenoptera_data/val/ants/263615709_cfb28f6b8e.jpg is: ant\n",
+      "Predicted class for ./hymenoptera_data/val/ants/94999827_36895faade.jpg is: ant\n",
+      "Predicted class for ./hymenoptera_data/val/ants/436944325_d4925a38c7.jpg is: ant\n",
+      "Predicted class for ./hymenoptera_data/val/ants/161076144_124db762d6.jpg is: centipede\n",
+      "Predicted class for ./hymenoptera_data/val/ants/147542264_79506478c2.jpg is: ant\n",
+      "Predicted class for ./hymenoptera_data/val/ants/239161491_86ac23b0a3.jpg is: ant\n",
+      "Predicted class for ./hymenoptera_data/val/ants/1053149811_f62a3410d3.jpg is: ant\n",
+      "Predicted class for ./hymenoptera_data/val/ants/1124525276_816a07c17f.jpg is: ant\n",
+      "Predicted class for ./hymenoptera_data/val/ants/2211974567_ee4606b493.jpg is: ant\n",
+      "Predicted class for ./hymenoptera_data/val/ants/2191997003_379df31291.jpg is: ant\n",
+      "Predicted class for ./hymenoptera_data/val/ants/183260961_64ab754c97.jpg is: ant\n",
+      "Predicted class for ./hymenoptera_data/val/ants/562589509_7e55469b97.jpg is: dung beetle\n",
+      "Predicted class for ./hymenoptera_data/val/ants/ants-devouring-remains-of-large-dead-insect-on-red-tile-in-Stellenbosch-South-Africa-closeup-1-DHD.jpg is: scorpion\n",
+      "Predicted class for ./hymenoptera_data/val/ants/751649788_78dd7d16ce.jpg is: dung beetle\n",
+      "Predicted class for ./hymenoptera_data/val/ants/157401988_d0564a9d02.jpg is: ant\n",
+      "Predicted class for ./hymenoptera_data/val/ants/2039585088_c6f47c592e.jpg is: ant\n",
+      "Predicted class for ./hymenoptera_data/val/ants/153320619_2aeb5fa0ee.jpg is: ant\n",
+      "Predicted class for ./hymenoptera_data/val/ants/649407494_9b6bc4949f.jpg is: ant\n",
+      "Predicted class for ./hymenoptera_data/val/ants/470127071_8b8ee2bd74.jpg is: ant\n",
+      "Predicted class for ./hymenoptera_data/val/ants/Hormiga.jpg is: ant\n",
+      "Predicted class for ./hymenoptera_data/val/ants/502717153_3e4865621a.jpg is: ant\n",
+      "Predicted class for ./hymenoptera_data/val/ants/573151833_ebbc274b77.jpg is: ant\n",
+      "Predicted class for ./hymenoptera_data/val/ants/57264437_a19006872f.jpg is: ant\n",
+      "Predicted class for ./hymenoptera_data/val/ants/540543309_ddbb193ee5.jpg is: ant\n",
+      "Predicted class for ./hymenoptera_data/val/ants/2255445811_dabcdf7258.jpg is: ant\n",
+      "Predicted class for ./hymenoptera_data/val/ants/445356866_6cb3289067.jpg is: ant\n",
+      "Predicted class for ./hymenoptera_data/val/ants/8124241_36b290d372.jpg is: ant\n",
+      "Predicted class for ./hymenoptera_data/val/ants/Ant-1818.jpg is: ant\n",
+      "Predicted class for ./hymenoptera_data/val/ants/208072188_f293096296.jpg is: dung beetle\n",
+      "Predicted class for ./hymenoptera_data/val/ants/2104709400_8831b4fc6f.jpg is: ant\n",
+      "Predicted class for ./hymenoptera_data/val/ants/159515240_d5981e20d1.jpg is: ant\n",
+      "Predicted class for ./hymenoptera_data/val/ants/518746016_bcc28f8b5b.jpg is: ant\n",
+      "Predicted class for ./hymenoptera_data/val/ants/10308379_1b6c72e180.jpg is: ant\n",
+      "Predicted class for ./hymenoptera_data/val/ants/172772109_d0a8e15fb0.jpg is: clothes iron\n",
+      "Predicted class for ./hymenoptera_data/val/ants/1440002809_b268d9a66a.jpg is: ant\n",
+      "Predicted class for ./hymenoptera_data/val/ants/1358854066_5ad8015f7f.jpg is: ant\n",
+      "Predicted class for ./hymenoptera_data/val/ants/412436937_4c2378efc2.jpg is: ant\n",
+      "Predicted class for ./hymenoptera_data/val/ants/119785936_dd428e40c3.jpg is: ant\n",
+      "Predicted class for ./hymenoptera_data/val/ants/1337725712_2eb53cd742.jpg is: ant\n",
+      "Predicted class for ./hymenoptera_data/val/ants/152286280_411648ec27.jpg is: ant\n",
+      "Predicted class for ./hymenoptera_data/val/ants/161292361_c16e0bf57a.jpg is: ant\n",
+      "Predicted class for ./hymenoptera_data/val/ants/477437164_bc3e6e594a.jpg is: ant\n",
+      "Predicted class for ./hymenoptera_data/val/ants/768870506_8f115d3d37.jpg is: ant\n",
+      "Predicted class for ./hymenoptera_data/val/ants/488272201_c5aa281348.jpg is: ant\n",
+      "Predicted class for ./hymenoptera_data/val/ants/2219621907_47bc7cc6b0.jpg is: ant\n",
+      "Predicted class for ./hymenoptera_data/val/ants/854534770_31f6156383.jpg is: ant\n",
+      "Predicted class for ./hymenoptera_data/val/ants/209615353_eeb38ba204.jpg is: ant\n",
+      "Predicted class for ./hymenoptera_data/val/ants/35558229_1fa4608a7a.jpg is: ant\n",
+      "Predicted class for ./hymenoptera_data/val/ants/11381045_b352a47d8c.jpg is: ant\n",
+      "Predicted class for ./hymenoptera_data/val/ants/212100470_b485e7b7b9.jpg is: ant\n",
+      "Predicted class for ./hymenoptera_data/val/ants/1743840368_b5ccda82b7.jpg is: ant\n",
+      "Predicted class for ./hymenoptera_data/val/ants/170652283_ecdaff5d1a.jpg is: ant\n",
+      "Predicted class for ./hymenoptera_data/val/ants/17081114_79b9a27724.jpg is: ant\n",
+      "Predicted class for ./hymenoptera_data/val/ants/8398478_50ef10c47a.jpg is: ant\n",
+      "Predicted class for ./hymenoptera_data/val/ants/1262751255_c56c042b7b.jpg is: ant\n",
+      "Predicted class for ./hymenoptera_data/val/ants/308196310_1db5ffa01b.jpg is: ant\n",
+      "Predicted class for ./hymenoptera_data/val/ants/desert_ant.jpg is: ant\n",
+      "Predicted class for ./hymenoptera_data/val/ants/153783656_85f9c3ac70.jpg is: ant\n",
+      "Predicted class for ./hymenoptera_data/val/ants/1119630822_cd325ea21a.jpg is: ant\n",
+      "Predicted class for ./hymenoptera_data/val/ants/319494379_648fb5a1c6.jpg is: ant\n",
+      "Predicted class for ./hymenoptera_data/val/ants/2127908701_d49dc83c97.jpg is: ant\n"
+     ]
+    }
+   ],
+   "source": [
+    "extensions = (\".png\", \".jpg\", \".jpeg\")\n",
+    "\n",
+    "quantized_model.eval()\n",
+    "\n",
+    "for root, _, files in os.walk(\".\"):\n",
+    "    for file in files:\n",
+    "        if file.lower().endswith(extensions):\n",
+    "            file_path = os.path.join(root, file)\n",
+    "            try:\n",
+    "                # Load the image\n",
+    "                with Image.open(file_path) as image:\n",
+    "                    # Apply the model on the image\n",
+    "                    image = data_transform(image).unsqueeze(0)\n",
+    "                    # Get the 1000-dimensional model output\n",
+    "                    out = quantized_model(image)\n",
+    "                    # Find the predicted class\n",
+    "                    print(f\"Predicted class for {file_path} is: {labels[out.argmax()]}\")\n",
+    "            except Exception as e:\n",
+    "                print(f\"Error processing {file_path}: {e}\")\n"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "5cfd1681",
+   "metadata": {},
+   "source": [
+    "The quantized version also works. However, the size reduction is not much"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "42d94454",
+   "metadata": {},
+   "source": [
+    "Let's now work with another pretrained model: ConvNeXt"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 26,
+   "id": "46922764",
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "Predicted class for ./dog.png is: Golden Retriever\n",
+      "Predicted class for ./gaspump.jpg is: gas pump\n",
+      "Predicted class for ./dog.jpg is: Golden Retriever\n",
+      "Predicted class for ./golf-cart.jpg is: golf cart\n",
+      "Predicted class for ./gondola.jpg is: gondola\n",
+      "Predicted class for ./eel.jpg is: eel\n",
+      "Predicted class for ./hymenoptera_data/train/bees/2638074627_6b3ae746a0.jpg is: bee\n",
+      "Predicted class for ./hymenoptera_data/train/bees/507288830_f46e8d4cb2.jpg is: bee\n",
+      "Predicted class for ./hymenoptera_data/train/bees/2405441001_b06c36fa72.jpg is: bee\n",
+      "Predicted class for ./hymenoptera_data/train/bees/2962405283_22718d9617.jpg is: bee\n",
+      "Predicted class for ./hymenoptera_data/train/bees/446296270_d9e8b93ecf.jpg is: bee\n",
+      "Predicted class for ./hymenoptera_data/train/bees/1092977343_cb42b38d62.jpg is: bee\n",
+      "Predicted class for ./hymenoptera_data/train/bees/2704348794_eb5d5178c2.jpg is: bee\n",
+      "Predicted class for ./hymenoptera_data/train/bees/2358061370_9daabbd9ac.jpg is: bee\n",
+      "Predicted class for ./hymenoptera_data/train/bees/2861002136_52c7c6f708.jpg is: bee\n",
+      "Predicted class for ./hymenoptera_data/train/bees/266644509_d30bb16a1b.jpg is: bee\n",
+      "Predicted class for ./hymenoptera_data/train/bees/2470492904_837e97800d.jpg is: bee\n",
+      "Predicted class for ./hymenoptera_data/train/bees/2053200300_8911ef438a.jpg is: bee\n",
+      "Predicted class for ./hymenoptera_data/train/bees/2601176055_8464e6aa71.jpg is: bee\n",
+      "Predicted class for ./hymenoptera_data/train/bees/473618094_8ffdcab215.jpg is: bee\n",
+      "Predicted class for ./hymenoptera_data/train/bees/150013791_969d9a968b.jpg is: bee\n",
+      "Predicted class for ./hymenoptera_data/train/bees/2486746709_c43cec0e42.jpg is: bee\n",
+      "Predicted class for ./hymenoptera_data/train/bees/452462677_7be43af8ff.jpg is: bee\n",
+      "Predicted class for ./hymenoptera_data/train/bees/2397446847_04ef3cd3e1.jpg is: bee\n",
+      "Predicted class for ./hymenoptera_data/train/bees/92663402_37f379e57a.jpg is: bee\n",
+      "Predicted class for ./hymenoptera_data/train/bees/2486729079_62df0920be.jpg is: bee\n",
+      "Predicted class for ./hymenoptera_data/train/bees/2551813042_8a070aeb2b.jpg is: bee\n",
+      "Predicted class for ./hymenoptera_data/train/bees/2792000093_e8ae0718cf.jpg is: bee\n",
+      "Predicted class for ./hymenoptera_data/train/bees/2477324698_3d4b1b1cab.jpg is: bee\n",
+      "Predicted class for ./hymenoptera_data/train/bees/2959730355_416a18c63c.jpg is: bee\n",
+      "Predicted class for ./hymenoptera_data/train/bees/774440991_63a4aa0cbe.jpg is: bee\n",
+      "Predicted class for ./hymenoptera_data/train/bees/2652877533_a564830cbf.jpg is: bee\n",
+      "Predicted class for ./hymenoptera_data/train/bees/21399619_3e61e5bb6f.jpg is: bee\n",
+      "Predicted class for ./hymenoptera_data/train/bees/586041248_3032e277a9.jpg is: fly\n",
+      "Predicted class for ./hymenoptera_data/train/bees/39672681_1302d204d1.jpg is: bee\n",
+      "Predicted class for ./hymenoptera_data/train/bees/2345177635_caf07159b3.jpg is: bee\n",
+      "Predicted class for ./hymenoptera_data/train/bees/2321139806_d73d899e66.jpg is: bee\n",
+      "Predicted class for ./hymenoptera_data/train/bees/2528444139_fa728b0f5b.jpg is: bee\n",
+      "Predicted class for ./hymenoptera_data/train/bees/3044402684_3853071a87.jpg is: bee\n",
+      "Predicted class for ./hymenoptera_data/train/bees/2683605182_9d2a0c66cf.jpg is: honeycomb\n",
+      "Predicted class for ./hymenoptera_data/train/bees/2728759455_ce9bb8cd7a.jpg is: bee\n",
+      "Predicted class for ./hymenoptera_data/train/bees/522104315_5d3cb2758e.jpg is: bee\n",
+      "Predicted class for ./hymenoptera_data/train/bees/2493379287_4100e1dacc.jpg is: corn\n",
+      "Predicted class for ./hymenoptera_data/train/bees/478701318_bbd5e557b8.jpg is: bee\n",
+      "Predicted class for ./hymenoptera_data/train/bees/2610833167_79bf0bcae5.jpg is: bee\n",
+      "Predicted class for ./hymenoptera_data/train/bees/2710368626_cb42882dc8.jpg is: bee\n",
+      "Predicted class for ./hymenoptera_data/train/bees/1691282715_0addfdf5e8.jpg is: bee\n",
+      "Predicted class for ./hymenoptera_data/train/bees/2756397428_1d82a08807.jpg is: bee\n",
+      "Predicted class for ./hymenoptera_data/train/bees/1799726602_8580867f71.jpg is: bee\n",
+      "Predicted class for ./hymenoptera_data/train/bees/2477349551_e75c97cf4d.jpg is: bee\n",
+      "Predicted class for ./hymenoptera_data/train/bees/2031225713_50ed499635.jpg is: bee\n",
+      "Predicted class for ./hymenoptera_data/train/bees/2610838525_fe8e3cae47.jpg is: bee\n",
+      "Predicted class for ./hymenoptera_data/train/bees/3074585407_9854eb3153.jpg is: bee\n",
+      "Predicted class for ./hymenoptera_data/train/bees/2330918208_8074770c20.jpg is: bee\n",
+      "Predicted class for ./hymenoptera_data/train/bees/465133211_80e0c27f60.jpg is: bee\n",
+      "Predicted class for ./hymenoptera_data/train/bees/3079610310_ac2d0ae7bc.jpg is: bee\n",
+      "Predicted class for ./hymenoptera_data/train/bees/2495722465_879acf9d85.jpg is: bee\n",
+      "Predicted class for ./hymenoptera_data/train/bees/444532809_9e931e2279.jpg is: bee\n",
+      "Predicted class for ./hymenoptera_data/train/bees/1807583459_4fe92b3133.jpg is: bee\n",
+      "Predicted class for ./hymenoptera_data/train/bees/359928878_b3b418c728.jpg is: bee\n",
+      "Predicted class for ./hymenoptera_data/train/bees/2037437624_2d7bce461f.jpg is: bee\n",
+      "Predicted class for ./hymenoptera_data/train/bees/509247772_2db2d01374.jpg is: bee\n",
+      "Predicted class for ./hymenoptera_data/train/bees/90179376_abc234e5f4.jpg is: bee\n",
+      "Predicted class for ./hymenoptera_data/train/bees/3030772428_8578335616.jpg is: bee\n",
+      "Predicted class for ./hymenoptera_data/train/bees/873076652_eb098dab2d.jpg is: bee\n",
+      "Predicted class for ./hymenoptera_data/train/bees/17209602_fe5a5a746f.jpg is: bee\n",
+      "Predicted class for ./hymenoptera_data/train/bees/421515404_e87569fd8b.jpg is: bee\n",
+      "Predicted class for ./hymenoptera_data/train/bees/1097045929_1753d1c765.jpg is: honeycomb\n",
+      "Predicted class for ./hymenoptera_data/train/bees/2781170484_5d61835d63.jpg is: bee\n",
+      "Predicted class for ./hymenoptera_data/train/bees/3100226504_c0d4f1e3f1.jpg is: bee\n",
+      "Predicted class for ./hymenoptera_data/train/bees/2617161745_fa3ebe85b4.jpg is: bee\n",
+      "Predicted class for ./hymenoptera_data/train/bees/2580598377_a4caecdb54.jpg is: bee\n",
+      "Predicted class for ./hymenoptera_data/train/bees/208702903_42fb4d9748.jpg is: bee\n",
+      "Predicted class for ./hymenoptera_data/train/bees/537309131_532bfa59ea.jpg is: bee\n",
+      "Predicted class for ./hymenoptera_data/train/bees/969455125_58c797ef17.jpg is: bee\n",
+      "Predicted class for ./hymenoptera_data/train/bees/365759866_b15700c59b.jpg is: cardoon\n",
+      "Predicted class for ./hymenoptera_data/train/bees/196430254_46bd129ae7.jpg is: bee\n",
+      "Predicted class for ./hymenoptera_data/train/bees/1232245714_f862fbe385.jpg is: bee\n",
+      "Predicted class for ./hymenoptera_data/train/bees/2445215254_51698ff797.jpg is: bee\n",
+      "Predicted class for ./hymenoptera_data/train/bees/760526046_547e8b381f.jpg is: bee\n",
+      "Predicted class for ./hymenoptera_data/train/bees/513545352_fd3e7c7c5d.jpg is: bee\n",
+      "Predicted class for ./hymenoptera_data/train/bees/2634617358_f32fd16bea.jpg is: bee\n",
+      "Predicted class for ./hymenoptera_data/train/bees/39747887_42df2855ee.jpg is: bee\n",
+      "Predicted class for ./hymenoptera_data/train/bees/354167719_22dca13752.jpg is: bee\n",
+      "Predicted class for ./hymenoptera_data/train/bees/2384149906_2cd8b0b699.jpg is: bee\n",
+      "Predicted class for ./hymenoptera_data/train/bees/2625499656_e3415e374d.jpg is: bee\n",
+      "Predicted class for ./hymenoptera_data/train/bees/2645107662_b73a8595cc.jpg is: bee\n",
+      "Predicted class for ./hymenoptera_data/train/bees/154600396_53e1252e52.jpg is: bee\n",
+      "Predicted class for ./hymenoptera_data/train/bees/279113587_b4843db199.jpg is: bee\n",
+      "Predicted class for ./hymenoptera_data/train/bees/98391118_bdb1e80cce.jpg is: bee\n",
+      "Predicted class for ./hymenoptera_data/train/bees/132511197_0b86ad0fff.jpg is: bee\n",
+      "Predicted class for ./hymenoptera_data/train/bees/2707440199_cd170bd512.jpg is: bee\n",
+      "Predicted class for ./hymenoptera_data/train/bees/342758693_c56b89b6b6.jpg is: fly\n",
+      "Predicted class for ./hymenoptera_data/train/bees/36900412_92b81831ad.jpg is: bee\n",
+      "Predicted class for ./hymenoptera_data/train/bees/2364597044_3c3e3fc391.jpg is: bee\n",
+      "Predicted class for ./hymenoptera_data/train/bees/1295655112_7813f37d21.jpg is: bee\n",
+      "Predicted class for ./hymenoptera_data/train/bees/2227611847_ec72d40403.jpg is: bee\n",
+      "Predicted class for ./hymenoptera_data/train/bees/205835650_e6f2614bee.jpg is: bee\n",
+      "Predicted class for ./hymenoptera_data/train/bees/1093831624_fb5fbe2308.jpg is: bee\n",
+      "Predicted class for ./hymenoptera_data/train/bees/129236073_0985e91c7d.jpg is: bee\n",
+      "Predicted class for ./hymenoptera_data/train/bees/198508668_97d818b6c4.jpg is: bee\n",
+      "Predicted class for ./hymenoptera_data/train/bees/1508176360_2972117c9d.jpg is: fly\n",
+      "Predicted class for ./hymenoptera_data/train/bees/457457145_5f86eb7e9c.jpg is: bee\n",
+      "Predicted class for ./hymenoptera_data/train/bees/2722592222_258d473e17.jpg is: bee\n",
+      "Predicted class for ./hymenoptera_data/train/bees/2822388965_f6dca2a275.jpg is: bee\n",
+      "Predicted class for ./hymenoptera_data/train/bees/2651621464_a2fa8722eb.jpg is: bee\n",
+      "Predicted class for ./hymenoptera_data/train/bees/132826773_dbbcb117b9.jpg is: bee\n",
+      "Predicted class for ./hymenoptera_data/train/bees/476347960_52edd72b06.jpg is: bee\n",
+      "Predicted class for ./hymenoptera_data/train/bees/3006264892_30e9cced70.jpg is: bee\n",
+      "Predicted class for ./hymenoptera_data/train/bees/760568592_45a52c847f.jpg is: bee\n",
+      "Predicted class for ./hymenoptera_data/train/bees/2452236943_255bfd9e58.jpg is: bee\n",
+      "Predicted class for ./hymenoptera_data/train/bees/472288710_2abee16fa0.jpg is: bee\n",
+      "Predicted class for ./hymenoptera_data/train/bees/2908916142_a7ac8b57a8.jpg is: bee\n",
+      "Predicted class for ./hymenoptera_data/train/bees/95238259_98470c5b10.jpg is: bee\n",
+      "Predicted class for ./hymenoptera_data/train/bees/85112639_6e860b0469.jpg is: bee\n",
+      "Predicted class for ./hymenoptera_data/train/bees/2801728106_833798c909.jpg is: bee\n",
+      "Predicted class for ./hymenoptera_data/train/bees/174142798_e5ad6d76e0.jpg is: bee\n",
+      "Predicted class for ./hymenoptera_data/train/bees/2467959963_a7831e9ff0.jpg is: bee\n",
+      "Predicted class for ./hymenoptera_data/train/bees/2538361678_9da84b77e3.jpg is: bee\n",
+      "Predicted class for ./hymenoptera_data/train/bees/196658222_3fffd79c67.jpg is: bee\n",
+      "Predicted class for ./hymenoptera_data/train/bees/29494643_e3410f0d37.jpg is: bee\n",
+      "Predicted class for ./hymenoptera_data/train/bees/16838648_415acd9e3f.jpg is: bee\n",
+      "Predicted class for ./hymenoptera_data/train/bees/3030189811_01d095b793.jpg is: bee\n",
+      "Predicted class for ./hymenoptera_data/train/bees/469333327_358ba8fe8a.jpg is: bee\n",
+      "Predicted class for ./hymenoptera_data/train/bees/452462695_40a4e5b559.jpg is: bee\n",
+      "Predicted class for ./hymenoptera_data/train/bees/3090975720_71f12e6de4.jpg is: bee\n",
+      "Predicted class for ./hymenoptera_data/train/bees/2765347790_da6cf6cb40.jpg is: bee\n",
+      "Predicted class for ./hymenoptera_data/train/ants/957233405_25c1d1187b.jpg is: ant\n",
+      "Predicted class for ./hymenoptera_data/train/ants/2288481644_83ff7e4572.jpg is: ant\n",
+      "Predicted class for ./hymenoptera_data/train/ants/67270775_e9fdf77e9d.jpg is: ant\n",
+      "Predicted class for ./hymenoptera_data/train/ants/1808777855_2a895621d7.jpg is: ant\n",
+      "Predicted class for ./hymenoptera_data/train/ants/VietnameseAntMimicSpider.jpg is: ant\n",
+      "Predicted class for ./hymenoptera_data/train/ants/swiss-army-ant.jpg is: ant\n",
+      "Predicted class for ./hymenoptera_data/train/ants/termite-vs-ant.jpg is: ant\n",
+      "Predicted class for ./hymenoptera_data/train/ants/245647475_9523dfd13e.jpg is: ant\n",
+      "Predicted class for ./hymenoptera_data/train/ants/384191229_5779cf591b.jpg is: ant\n",
+      "Predicted class for ./hymenoptera_data/train/ants/hormiga_co_por.jpg is: ant\n",
+      "Predicted class for ./hymenoptera_data/train/ants/531979952_bde12b3bc0.jpg is: ant\n",
+      "Predicted class for ./hymenoptera_data/train/ants/224655713_3956f7d39a.jpg is: ant\n",
+      "Predicted class for ./hymenoptera_data/train/ants/132478121_2a430adea2.jpg is: ant\n",
+      "Predicted class for ./hymenoptera_data/train/ants/512863248_43c8ce579b.jpg is: ant\n",
+      "Predicted class for ./hymenoptera_data/train/ants/533848102_70a85ad6dd.jpg is: ant\n",
+      "Predicted class for ./hymenoptera_data/train/ants/201558278_fe4caecc76.jpg is: ant\n",
+      "Predicted class for ./hymenoptera_data/train/ants/army-ants-red-picture.jpg is: ant\n",
+      "Predicted class for ./hymenoptera_data/train/ants/MehdiabadiAnt2_600.jpg is: ant\n",
+      "Predicted class for ./hymenoptera_data/train/ants/334167043_cbd1adaeb9.jpg is: ant\n",
+      "Predicted class for ./hymenoptera_data/train/ants/20935278_9190345f6b.jpg is: ant\n",
+      "Predicted class for ./hymenoptera_data/train/ants/540889389_48bb588b21.jpg is: ant\n",
+      "Predicted class for ./hymenoptera_data/train/ants/466430434_4000737de9.jpg is: daisy\n",
+      "Predicted class for ./hymenoptera_data/train/ants/649026570_e58656104b.jpg is: ant\n",
+      "Predicted class for ./hymenoptera_data/train/ants/196057951_63bf063b92.jpg is: leaf beetle\n",
+      "Predicted class for ./hymenoptera_data/train/ants/1660097129_384bf54490.jpg is: ant\n",
+      "Predicted class for ./hymenoptera_data/train/ants/1286984635_5119e80de1.jpg is: ant\n",
+      "Predicted class for ./hymenoptera_data/train/ants/6240329_72c01e663e.jpg is: ant\n",
+      "Predicted class for ./hymenoptera_data/train/ants/Ant_1.jpg is: ant\n",
+      "Predicted class for ./hymenoptera_data/train/ants/522163566_fec115ca66.jpg is: ant\n",
+      "Predicted class for ./hymenoptera_data/train/ants/0013035.jpg is: ant\n",
+      "Predicted class for ./hymenoptera_data/train/ants/24335309_c5ea483bb8.jpg is: ant\n",
+      "Predicted class for ./hymenoptera_data/train/ants/150801171_cd86f17ed8.jpg is: ant\n",
+      "Predicted class for ./hymenoptera_data/train/ants/403746349_71384f5b58.jpg is: longhorn beetle\n",
+      "Predicted class for ./hymenoptera_data/train/ants/460372577_f2f6a8c9fc.jpg is: ant\n",
+      "Predicted class for ./hymenoptera_data/train/ants/386190770_672743c9a7.jpg is: ant\n",
+      "Predicted class for ./hymenoptera_data/train/ants/886401651_f878e888cd.jpg is: ant\n",
+      "Predicted class for ./hymenoptera_data/train/ants/506249802_207cd979b4.jpg is: ant\n",
+      "Predicted class for ./hymenoptera_data/train/ants/841049277_b28e58ad05.jpg is: ant\n",
+      "Predicted class for ./hymenoptera_data/train/ants/707895295_009cf23188.jpg is: ant\n",
+      "Predicted class for ./hymenoptera_data/train/ants/Nepenthes_rafflesiana_ant.jpg is: ant\n",
+      "Predicted class for ./hymenoptera_data/train/ants/518773929_734dbc5ff4.jpg is: ant\n",
+      "Predicted class for ./hymenoptera_data/train/ants/342438950_a3da61deab.jpg is: ant\n",
+      "Predicted class for ./hymenoptera_data/train/ants/1368913450_e146e2fb6d.jpg is: ant\n",
+      "Predicted class for ./hymenoptera_data/train/ants/49375974_e28ba6f17e.jpg is: ant\n",
+      "Predicted class for ./hymenoptera_data/train/ants/822537660_caf4ba5514.jpg is: ant\n",
+      "Predicted class for ./hymenoptera_data/train/ants/36439863_0bec9f554f.jpg is: ant\n",
+      "Predicted class for ./hymenoptera_data/train/ants/175998972.jpg is: ant\n",
+      "Predicted class for ./hymenoptera_data/train/ants/382971067_0bfd33afe0.jpg is: ant\n",
+      "Predicted class for ./hymenoptera_data/train/ants/1804095607_0341701e1c.jpg is: ant\n",
+      "Predicted class for ./hymenoptera_data/train/ants/188552436_605cc9b36b.jpg is: ant\n",
+      "Predicted class for ./hymenoptera_data/train/ants/339670531_94b75ae47a.jpg is: ant\n",
+      "Predicted class for ./hymenoptera_data/train/ants/374435068_7eee412ec4.jpg is: ant\n",
+      "Predicted class for ./hymenoptera_data/train/ants/1473187633_63ccaacea6.jpg is: bee\n",
+      "Predicted class for ./hymenoptera_data/train/ants/258217966_d9d90d18d3.jpg is: ant\n",
+      "Predicted class for ./hymenoptera_data/train/ants/150801003_3390b73135.jpg is: ant\n",
+      "Predicted class for ./hymenoptera_data/train/ants/1030023514_aad5c608f9.jpg is: ant\n",
+      "Predicted class for ./hymenoptera_data/train/ants/2288450226_a6e96e8fdf.jpg is: ant\n",
+      "Predicted class for ./hymenoptera_data/train/ants/541630764_dbd285d63c.jpg is: ant\n",
+      "Predicted class for ./hymenoptera_data/train/ants/275429470_b2d7d9290b.jpg is: ant\n",
+      "Predicted class for ./hymenoptera_data/train/ants/6240338_93729615ec.jpg is: ant\n",
+      "Predicted class for ./hymenoptera_data/train/ants/424873399_47658a91fb.jpg is: ant\n",
+      "Predicted class for ./hymenoptera_data/train/ants/543417860_b14237f569.jpg is: ant\n",
+      "Predicted class for ./hymenoptera_data/train/ants/318052216_84dff3f98a.jpg is: ant\n",
+      "Predicted class for ./hymenoptera_data/train/ants/149244013_c529578289.jpg is: ant\n",
+      "Predicted class for ./hymenoptera_data/train/ants/1262877379_64fcada201.jpg is: ant\n",
+      "Predicted class for ./hymenoptera_data/train/ants/450057712_771b3bfc91.jpg is: ant\n",
+      "Predicted class for ./hymenoptera_data/train/ants/662541407_ff8db781e7.jpg is: ant\n",
+      "Predicted class for ./hymenoptera_data/train/ants/154124431_65460430f2.jpg is: ant\n",
+      "Predicted class for ./hymenoptera_data/train/ants/2019439677_2db655d361.jpg is: rock crab\n",
+      "Predicted class for ./hymenoptera_data/train/ants/1489674356_09d48dde0a.jpg is: ant\n",
+      "Predicted class for ./hymenoptera_data/train/ants/892108839_f1aad4ca46.jpg is: ant\n",
+      "Predicted class for ./hymenoptera_data/train/ants/522415432_2218f34bf8.jpg is: ant\n",
+      "Predicted class for ./hymenoptera_data/train/ants/178538489_bec7649292.jpg is: ant\n",
+      "Predicted class for ./hymenoptera_data/train/ants/ant photos.jpg is: ant\n",
+      "Predicted class for ./hymenoptera_data/train/ants/474806473_ca6caab245.jpg is: ladybug\n",
+      "Predicted class for ./hymenoptera_data/train/ants/408393566_b5b694119b.jpg is: ant\n",
+      "Predicted class for ./hymenoptera_data/train/ants/2278278459_6b99605e50.jpg is: ant\n",
+      "Predicted class for ./hymenoptera_data/train/ants/formica.jpeg is: ant\n",
+      "Predicted class for ./hymenoptera_data/train/ants/1269756697_0bce92cdab.jpg is: ant\n",
+      "Predicted class for ./hymenoptera_data/train/ants/2292213964_ca51ce4bef.jpg is: ant\n",
+      "Predicted class for ./hymenoptera_data/train/ants/226951206_d6bf946504.jpg is: ant\n",
+      "Predicted class for ./hymenoptera_data/train/ants/938946700_ca1c669085.jpg is: ant\n",
+      "Predicted class for ./hymenoptera_data/train/ants/2265824718_2c96f485da.jpg is: ant\n",
+      "Predicted class for ./hymenoptera_data/train/ants/392382602_1b7bed32fa.jpg is: screwdriver\n",
+      "Predicted class for ./hymenoptera_data/train/ants/69639610_95e0de17aa.jpg is: ant\n",
+      "Predicted class for ./hymenoptera_data/train/ants/7759525_1363d24e88.jpg is: ant\n",
+      "Predicted class for ./hymenoptera_data/train/ants/424119020_6d57481dab.jpg is: ant\n",
+      "Predicted class for ./hymenoptera_data/train/ants/162603798_40b51f1654.jpg is: ant\n",
+      "Predicted class for ./hymenoptera_data/train/ants/28847243_e79fe052cd.jpg is: ant\n",
+      "Predicted class for ./hymenoptera_data/train/ants/998118368_6ac1d91f81.jpg is: ant\n",
+      "Predicted class for ./hymenoptera_data/train/ants/6743948_2b8c096dda.jpg is: ant\n",
+      "Predicted class for ./hymenoptera_data/train/ants/484293231_e53cfc0c89.jpg is: ant\n",
+      "Predicted class for ./hymenoptera_data/train/ants/512164029_c0a66b8498.jpg is: ant\n",
+      "Predicted class for ./hymenoptera_data/train/ants/2265825502_fff99cfd2d.jpg is: ant\n",
+      "Predicted class for ./hymenoptera_data/train/ants/459694881_ac657d3187.jpg is: ant\n",
+      "Predicted class for ./hymenoptera_data/train/ants/1099452230_d1949d3250.jpg is: ant\n",
+      "Predicted class for ./hymenoptera_data/train/ants/kurokusa.jpg is: ant\n",
+      "Predicted class for ./hymenoptera_data/train/ants/116570827_e9c126745d.jpg is: ant\n",
+      "Predicted class for ./hymenoptera_data/train/ants/167890289_dd5ba923f3.jpg is: ant\n",
+      "Predicted class for ./hymenoptera_data/train/ants/1360291657_dc248c5eea.jpg is: ant\n",
+      "Predicted class for ./hymenoptera_data/train/ants/460874319_0a45ab4d05.jpg is: ant\n",
+      "Predicted class for ./hymenoptera_data/train/ants/45472593_bfd624f8dc.jpg is: ant\n",
+      "Predicted class for ./hymenoptera_data/train/ants/207947948_3ab29d7207.jpg is: ant\n",
+      "Predicted class for ./hymenoptera_data/train/ants/535522953_308353a07c.jpg is: ant\n",
+      "Predicted class for ./hymenoptera_data/train/ants/255434217_1b2b3fe0a4.jpg is: ant\n",
+      "Predicted class for ./hymenoptera_data/train/ants/560966032_988f4d7bc4.jpg is: ant\n",
+      "Predicted class for ./hymenoptera_data/train/ants/148715752_302c84f5a4.jpg is: ant\n",
+      "Predicted class for ./hymenoptera_data/train/ants/470127037_513711fd21.jpg is: ant\n",
+      "Predicted class for ./hymenoptera_data/train/ants/9715481_b3cb4114ff.jpg is: ant\n",
+      "Predicted class for ./hymenoptera_data/train/ants/684133190_35b62c0c1d.jpg is: ant\n",
+      "Predicted class for ./hymenoptera_data/train/ants/trap-jaw-ant-insect-bg.jpg is: ant\n",
+      "Predicted class for ./hymenoptera_data/train/ants/196757565_326437f5fe.jpg is: ant\n",
+      "Predicted class for ./hymenoptera_data/train/ants/5650366_e22b7e1065.jpg is: ant\n",
+      "Predicted class for ./hymenoptera_data/train/ants/1095476100_3906d8afde.jpg is: ant\n",
+      "Predicted class for ./hymenoptera_data/train/ants/1225872729_6f0856588f.jpg is: ant\n",
+      "Predicted class for ./hymenoptera_data/train/ants/795000156_a9900a4a71.jpg is: ant\n",
+      "Predicted class for ./hymenoptera_data/train/ants/1924473702_daa9aacdbe.jpg is: ant\n",
+      "Predicted class for ./hymenoptera_data/train/ants/82852639_52b7f7f5e3.jpg is: ant\n",
+      "Predicted class for ./hymenoptera_data/train/ants/1693954099_46d4c20605.jpg is: ant\n",
+      "Predicted class for ./hymenoptera_data/train/ants/201790779_527f4c0168.jpg is: ant\n",
+      "Predicted class for ./hymenoptera_data/train/ants/475961153_b8c13fd405.jpg is: ant\n",
+      "Predicted class for ./hymenoptera_data/train/ants/506249836_717b73f540.jpg is: ant\n",
+      "Predicted class for ./hymenoptera_data/train/ants/1917341202_d00a7f9af5.jpg is: ant\n",
+      "Predicted class for ./hymenoptera_data/val/bees/2717418782_bd83307d9f.jpg is: fly\n",
+      "Predicted class for ./hymenoptera_data/val/bees/2173503984_9c6aaaa7e2.jpg is: bee\n",
+      "Predicted class for ./hymenoptera_data/val/bees/54736755_c057723f64.jpg is: bee\n",
+      "Predicted class for ./hymenoptera_data/val/bees/2103637821_8d26ee6b90.jpg is: bee\n",
+      "Predicted class for ./hymenoptera_data/val/bees/603711658_4c8cd2201e.jpg is: bee\n",
+      "Predicted class for ./hymenoptera_data/val/bees/238161922_55fa9a76ae.jpg is: bee\n",
+      "Predicted class for ./hymenoptera_data/val/bees/2457841282_7867f16639.jpg is: bee\n",
+      "Predicted class for ./hymenoptera_data/val/bees/6a00d8341c630a53ef00e553d0beb18834-800wi.jpg is: bee\n",
+      "Predicted class for ./hymenoptera_data/val/bees/177677657_a38c97e572.jpg is: bee\n",
+      "Predicted class for ./hymenoptera_data/val/bees/348291597_ee836fbb1a.jpg is: bee\n",
+      "Predicted class for ./hymenoptera_data/val/bees/152789693_220b003452.jpg is: bee\n",
+      "Predicted class for ./hymenoptera_data/val/bees/2782079948_8d4e94a826.jpg is: bee\n",
+      "Predicted class for ./hymenoptera_data/val/bees/576452297_897023f002.jpg is: bee\n",
+      "Predicted class for ./hymenoptera_data/val/bees/1181173278_23c36fac71.jpg is: bee\n",
+      "Predicted class for ./hymenoptera_data/val/bees/3077452620_548c79fda0.jpg is: bee\n",
+      "Predicted class for ./hymenoptera_data/val/bees/586474709_ae436da045.jpg is: bee\n",
+      "Predicted class for ./hymenoptera_data/val/bees/26589803_5ba7000313.jpg is: bee\n",
+      "Predicted class for ./hymenoptera_data/val/bees/2478216347_535c8fe6d7.jpg is: bee\n",
+      "Predicted class for ./hymenoptera_data/val/bees/2668391343_45e272cd07.jpg is: bee\n",
+      "Predicted class for ./hymenoptera_data/val/bees/540976476_844950623f.jpg is: bee\n",
+      "Predicted class for ./hymenoptera_data/val/bees/144098310_a4176fd54d.jpg is: bee\n",
+      "Predicted class for ./hymenoptera_data/val/bees/1486120850_490388f84b.jpg is: bee\n",
+      "Predicted class for ./hymenoptera_data/val/bees/2670536155_c170f49cd0.jpg is: bee\n",
+      "Predicted class for ./hymenoptera_data/val/bees/1519368889_4270261ee3.jpg is: armadillo\n",
+      "Predicted class for ./hymenoptera_data/val/bees/2506114833_90a41c5267.jpg is: daisy\n",
+      "Predicted class for ./hymenoptera_data/val/bees/2438480600_40a1249879.jpg is: bee\n",
+      "Predicted class for ./hymenoptera_data/val/bees/187130242_4593a4c610.jpg is: bee\n",
+      "Predicted class for ./hymenoptera_data/val/bees/224841383_d050f5f510.jpg is: bee\n",
+      "Predicted class for ./hymenoptera_data/val/bees/59798110_2b6a3c8031.jpg is: cockroach\n",
+      "Predicted class for ./hymenoptera_data/val/bees/2883093452_7e3a1eb53f.jpg is: bee\n",
+      "Predicted class for ./hymenoptera_data/val/bees/2321144482_f3785ba7b2.jpg is: bee\n",
+      "Predicted class for ./hymenoptera_data/val/bees/abeja.jpg is: bee\n",
+      "Predicted class for ./hymenoptera_data/val/bees/203868383_0fcbb48278.jpg is: bee\n",
+      "Predicted class for ./hymenoptera_data/val/bees/44105569_16720a960c.jpg is: bee\n",
+      "Predicted class for ./hymenoptera_data/val/bees/272986700_d4d4bf8c4b.jpg is: bee\n",
+      "Predicted class for ./hymenoptera_data/val/bees/464594019_1b24a28bb1.jpg is: bee\n",
+      "Predicted class for ./hymenoptera_data/val/bees/485743562_d8cc6b8f73.jpg is: bee\n",
+      "Predicted class for ./hymenoptera_data/val/bees/2815838190_0a9889d995.jpg is: bee\n",
+      "Predicted class for ./hymenoptera_data/val/bees/603709866_a97c7cfc72.jpg is: bee\n",
+      "Predicted class for ./hymenoptera_data/val/bees/2086294791_6f3789d8a6.jpg is: bee\n",
+      "Predicted class for ./hymenoptera_data/val/bees/1328423762_f7a88a8451.jpg is: bee\n",
+      "Predicted class for ./hymenoptera_data/val/bees/416144384_961c326481.jpg is: dung beetle\n",
+      "Predicted class for ./hymenoptera_data/val/bees/2709775832_85b4b50a57.jpg is: wool\n",
+      "Predicted class for ./hymenoptera_data/val/bees/1297972485_33266a18d9.jpg is: bee\n",
+      "Predicted class for ./hymenoptera_data/val/bees/2415414155_1916f03b42.jpg is: bee\n",
+      "Predicted class for ./hymenoptera_data/val/bees/149973093_da3c446268.jpg is: bee\n",
+      "Predicted class for ./hymenoptera_data/val/bees/2741763055_9a7bb00802.jpg is: bee\n",
+      "Predicted class for ./hymenoptera_data/val/bees/936182217_c4caa5222d.jpg is: bee\n",
+      "Predicted class for ./hymenoptera_data/val/bees/1799729694_0c40101071.jpg is: bee\n",
+      "Predicted class for ./hymenoptera_data/val/bees/2841437312_789699c740.jpg is: bee\n",
+      "Predicted class for ./hymenoptera_data/val/bees/2509402554_31821cb0b6.jpg is: bookstore\n",
+      "Predicted class for ./hymenoptera_data/val/bees/372228424_16da1f8884.jpg is: bee\n",
+      "Predicted class for ./hymenoptera_data/val/bees/456097971_860949c4fc.jpg is: bee\n",
+      "Predicted class for ./hymenoptera_data/val/bees/2525379273_dcb26a516d.jpg is: bee\n",
+      "Predicted class for ./hymenoptera_data/val/bees/2809496124_5f25b5946a.jpg is: bee\n",
+      "Predicted class for ./hymenoptera_data/val/bees/2060668999_e11edb10d0.jpg is: bee\n",
+      "Predicted class for ./hymenoptera_data/val/bees/1355974687_1341c1face.jpg is: bee\n",
+      "Predicted class for ./hymenoptera_data/val/bees/2751836205_6f7b5eff30.jpg is: bee\n",
+      "Predicted class for ./hymenoptera_data/val/bees/2702408468_d9ed795f4f.jpg is: bee\n",
+      "Predicted class for ./hymenoptera_data/val/bees/2444778727_4b781ac424.jpg is: bee\n",
+      "Predicted class for ./hymenoptera_data/val/bees/1032546534_06907fe3b3.jpg is: honeycomb\n",
+      "Predicted class for ./hymenoptera_data/val/bees/215512424_687e1e0821.jpg is: monarch butterfly\n",
+      "Predicted class for ./hymenoptera_data/val/bees/2745389517_250a397f31.jpg is: bee\n",
+      "Predicted class for ./hymenoptera_data/val/bees/590318879_68cf112861.jpg is: bee\n",
+      "Predicted class for ./hymenoptera_data/val/bees/2685605303_9eed79d59d.jpg is: bee\n",
+      "Predicted class for ./hymenoptera_data/val/bees/296565463_d07a7bed96.jpg is: bee\n",
+      "Predicted class for ./hymenoptera_data/val/bees/350436573_41f4ecb6c8.jpg is: bee\n",
+      "Predicted class for ./hymenoptera_data/val/bees/290082189_f66cb80bfc.jpg is: bee\n",
+      "Predicted class for ./hymenoptera_data/val/bees/10870992_eebeeb3a12.jpg is: bee\n",
+      "Predicted class for ./hymenoptera_data/val/bees/151603988_2c6f7d14c7.jpg is: bee\n",
+      "Predicted class for ./hymenoptera_data/val/bees/759745145_e8bc776ec8.jpg is: bee\n",
+      "Predicted class for ./hymenoptera_data/val/bees/181171681_c5a1a82ded.jpg is: bee\n",
+      "Predicted class for ./hymenoptera_data/val/bees/2104135106_a65eede1de.jpg is: bee\n",
+      "Predicted class for ./hymenoptera_data/val/bees/2470492902_3572c90f75.jpg is: bee\n",
+      "Predicted class for ./hymenoptera_data/val/bees/353266603_d3eac7e9a0.jpg is: bee\n",
+      "Predicted class for ./hymenoptera_data/val/bees/57459255_752774f1b2.jpg is: bee\n",
+      "Predicted class for ./hymenoptera_data/val/bees/2501530886_e20952b97d.jpg is: bee\n",
+      "Predicted class for ./hymenoptera_data/val/bees/65038344_52a45d090d.jpg is: bee\n",
+      "Predicted class for ./hymenoptera_data/val/bees/220376539_20567395d8.jpg is: bee\n",
+      "Predicted class for ./hymenoptera_data/val/bees/151594775_ee7dc17b60.jpg is: bee\n",
+      "Predicted class for ./hymenoptera_data/val/bees/400262091_701c00031c.jpg is: bee\n",
+      "Predicted class for ./hymenoptera_data/val/bees/72100438_73de9f17af.jpg is: bee\n",
+      "Predicted class for ./hymenoptera_data/val/bees/2407809945_fb525ef54d.jpg is: bee\n",
+      "Predicted class for ./hymenoptera_data/val/ants/459442412_412fecf3fe.jpg is: ant\n",
+      "Predicted class for ./hymenoptera_data/val/ants/800px-Meat_eater_ant_qeen_excavating_hole.jpg is: ant\n",
+      "Predicted class for ./hymenoptera_data/val/ants/892676922_4ab37dce07.jpg is: ant\n",
+      "Predicted class for ./hymenoptera_data/val/ants/F.pergan.28(f).jpg is: ant\n",
+      "Predicted class for ./hymenoptera_data/val/ants/1247887232_edcb61246c.jpg is: tick\n",
+      "Predicted class for ./hymenoptera_data/val/ants/181942028_961261ef48.jpg is: ant\n",
+      "Predicted class for ./hymenoptera_data/val/ants/1073564163_225a64f170.jpg is: ant\n",
+      "Predicted class for ./hymenoptera_data/val/ants/2238242353_52c82441df.jpg is: ant\n",
+      "Predicted class for ./hymenoptera_data/val/ants/205398178_c395c5e460.jpg is: ant\n",
+      "Predicted class for ./hymenoptera_data/val/ants/263615709_cfb28f6b8e.jpg is: ant\n",
+      "Predicted class for ./hymenoptera_data/val/ants/94999827_36895faade.jpg is: ant\n",
+      "Predicted class for ./hymenoptera_data/val/ants/436944325_d4925a38c7.jpg is: ant\n",
+      "Predicted class for ./hymenoptera_data/val/ants/161076144_124db762d6.jpg is: centipede\n",
+      "Predicted class for ./hymenoptera_data/val/ants/147542264_79506478c2.jpg is: ant\n",
+      "Predicted class for ./hymenoptera_data/val/ants/239161491_86ac23b0a3.jpg is: ant\n",
+      "Predicted class for ./hymenoptera_data/val/ants/1053149811_f62a3410d3.jpg is: ant\n",
+      "Predicted class for ./hymenoptera_data/val/ants/1124525276_816a07c17f.jpg is: ant\n",
+      "Predicted class for ./hymenoptera_data/val/ants/2211974567_ee4606b493.jpg is: ant\n",
+      "Predicted class for ./hymenoptera_data/val/ants/2191997003_379df31291.jpg is: ant\n",
+      "Predicted class for ./hymenoptera_data/val/ants/183260961_64ab754c97.jpg is: ant\n",
+      "Predicted class for ./hymenoptera_data/val/ants/562589509_7e55469b97.jpg is: ant\n",
+      "Predicted class for ./hymenoptera_data/val/ants/ants-devouring-remains-of-large-dead-insect-on-red-tile-in-Stellenbosch-South-Africa-closeup-1-DHD.jpg is: weevil\n",
+      "Predicted class for ./hymenoptera_data/val/ants/751649788_78dd7d16ce.jpg is: ant\n",
+      "Predicted class for ./hymenoptera_data/val/ants/157401988_d0564a9d02.jpg is: ant\n",
+      "Predicted class for ./hymenoptera_data/val/ants/2039585088_c6f47c592e.jpg is: ant\n",
+      "Predicted class for ./hymenoptera_data/val/ants/153320619_2aeb5fa0ee.jpg is: ant\n",
+      "Predicted class for ./hymenoptera_data/val/ants/649407494_9b6bc4949f.jpg is: ant\n",
+      "Predicted class for ./hymenoptera_data/val/ants/470127071_8b8ee2bd74.jpg is: ant\n",
+      "Predicted class for ./hymenoptera_data/val/ants/Hormiga.jpg is: ant\n",
+      "Predicted class for ./hymenoptera_data/val/ants/502717153_3e4865621a.jpg is: ant\n",
+      "Predicted class for ./hymenoptera_data/val/ants/573151833_ebbc274b77.jpg is: ant\n",
+      "Predicted class for ./hymenoptera_data/val/ants/57264437_a19006872f.jpg is: ant\n",
+      "Predicted class for ./hymenoptera_data/val/ants/540543309_ddbb193ee5.jpg is: ant\n",
+      "Predicted class for ./hymenoptera_data/val/ants/2255445811_dabcdf7258.jpg is: ant\n",
+      "Predicted class for ./hymenoptera_data/val/ants/445356866_6cb3289067.jpg is: ant\n",
+      "Predicted class for ./hymenoptera_data/val/ants/8124241_36b290d372.jpg is: ant\n",
+      "Predicted class for ./hymenoptera_data/val/ants/Ant-1818.jpg is: ant\n",
+      "Predicted class for ./hymenoptera_data/val/ants/208072188_f293096296.jpg is: ant\n",
+      "Predicted class for ./hymenoptera_data/val/ants/2104709400_8831b4fc6f.jpg is: ant\n",
+      "Predicted class for ./hymenoptera_data/val/ants/159515240_d5981e20d1.jpg is: ant\n",
+      "Predicted class for ./hymenoptera_data/val/ants/518746016_bcc28f8b5b.jpg is: ant\n",
+      "Predicted class for ./hymenoptera_data/val/ants/10308379_1b6c72e180.jpg is: ant\n",
+      "Predicted class for ./hymenoptera_data/val/ants/172772109_d0a8e15fb0.jpg is: oil filter\n",
+      "Predicted class for ./hymenoptera_data/val/ants/1440002809_b268d9a66a.jpg is: ant\n",
+      "Predicted class for ./hymenoptera_data/val/ants/1358854066_5ad8015f7f.jpg is: ant\n",
+      "Predicted class for ./hymenoptera_data/val/ants/412436937_4c2378efc2.jpg is: ant\n",
+      "Predicted class for ./hymenoptera_data/val/ants/119785936_dd428e40c3.jpg is: ant\n",
+      "Predicted class for ./hymenoptera_data/val/ants/1337725712_2eb53cd742.jpg is: ant\n",
+      "Predicted class for ./hymenoptera_data/val/ants/152286280_411648ec27.jpg is: ant\n",
+      "Predicted class for ./hymenoptera_data/val/ants/161292361_c16e0bf57a.jpg is: ant\n",
+      "Predicted class for ./hymenoptera_data/val/ants/477437164_bc3e6e594a.jpg is: scorpion\n",
+      "Predicted class for ./hymenoptera_data/val/ants/768870506_8f115d3d37.jpg is: ant\n",
+      "Predicted class for ./hymenoptera_data/val/ants/488272201_c5aa281348.jpg is: ant\n",
+      "Predicted class for ./hymenoptera_data/val/ants/2219621907_47bc7cc6b0.jpg is: ant\n",
+      "Predicted class for ./hymenoptera_data/val/ants/854534770_31f6156383.jpg is: ant\n",
+      "Predicted class for ./hymenoptera_data/val/ants/209615353_eeb38ba204.jpg is: ant\n",
+      "Predicted class for ./hymenoptera_data/val/ants/35558229_1fa4608a7a.jpg is: ant\n",
+      "Predicted class for ./hymenoptera_data/val/ants/11381045_b352a47d8c.jpg is: ant\n",
+      "Predicted class for ./hymenoptera_data/val/ants/212100470_b485e7b7b9.jpg is: ant\n",
+      "Predicted class for ./hymenoptera_data/val/ants/1743840368_b5ccda82b7.jpg is: ant\n",
+      "Predicted class for ./hymenoptera_data/val/ants/170652283_ecdaff5d1a.jpg is: ant\n",
+      "Predicted class for ./hymenoptera_data/val/ants/17081114_79b9a27724.jpg is: ant\n",
+      "Predicted class for ./hymenoptera_data/val/ants/8398478_50ef10c47a.jpg is: ant\n",
+      "Predicted class for ./hymenoptera_data/val/ants/1262751255_c56c042b7b.jpg is: ant\n",
+      "Predicted class for ./hymenoptera_data/val/ants/308196310_1db5ffa01b.jpg is: ant\n",
+      "Predicted class for ./hymenoptera_data/val/ants/desert_ant.jpg is: ant\n",
+      "Predicted class for ./hymenoptera_data/val/ants/153783656_85f9c3ac70.jpg is: ant\n",
+      "Predicted class for ./hymenoptera_data/val/ants/1119630822_cd325ea21a.jpg is: ant\n",
+      "Predicted class for ./hymenoptera_data/val/ants/319494379_648fb5a1c6.jpg is: ant\n",
+      "Predicted class for ./hymenoptera_data/val/ants/2127908701_d49dc83c97.jpg is: ant\n"
+     ]
+    }
+   ],
+   "source": [
+    "weights = ConvNeXt_Tiny_Weights.DEFAULT  # Use the default pretrained weights\n",
+    "model = models.convnext_tiny(weights=weights)\n",
+    "\n",
+    "model.eval()\n",
+    "\n",
+    "for root, _, files in os.walk(\".\"):\n",
+    "    for file in files:\n",
+    "        if file.lower().endswith(extensions):\n",
+    "            file_path = os.path.join(root, file)\n",
+    "            try:\n",
+    "                # Load the image\n",
+    "                with Image.open(file_path) as image:\n",
+    "                    # Apply the model on the image\n",
+    "                    image = data_transform(image).unsqueeze(0)\n",
+    "                    # Get the 1000-dimensional model output\n",
+    "                    out = model(image)\n",
+    "                    # Find the predicted class\n",
+    "                    print(f\"Predicted class for {file_path} is: {labels[out.argmax()]}\")\n",
+    "            except Exception as e:\n",
+    "                print(f\"Error processing {file_path}: {e}\")"
+   ]
+  },
   {
    "cell_type": "markdown",
    "id": "5d57da4b",
@@ -1586,10 +2997,21 @@
   },
   {
    "cell_type": "code",
-   "execution_count": null,
+   "execution_count": 27,
    "id": "be2d31f5",
    "metadata": {},
-   "outputs": [],
+   "outputs": [
+    {
+     "data": {
+      "image/png": "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",
+      "text/plain": [
+       "<Figure size 640x480 with 1 Axes>"
+      ]
+     },
+     "metadata": {},
+     "output_type": "display_data"
+    }
+   ],
    "source": [
     "import os\n",
     "\n",
@@ -1678,10 +3100,93 @@
   },
   {
    "cell_type": "code",
-   "execution_count": null,
+   "execution_count": 30,
    "id": "572d824c",
    "metadata": {},
-   "outputs": [],
+   "outputs": [
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "/Users/zhangzhengfei/miniconda3/lib/python3.12/site-packages/torchvision/models/_utils.py:208: UserWarning: The parameter 'pretrained' is deprecated since 0.13 and may be removed in the future, please use 'weights' instead.\n",
+      "  warnings.warn(\n",
+      "/Users/zhangzhengfei/miniconda3/lib/python3.12/site-packages/torchvision/models/_utils.py:223: UserWarning: Arguments other than a weight enum or `None` for 'weights' are deprecated since 0.13 and may be removed in the future. The current behavior is equivalent to passing `weights=ResNet18_Weights.IMAGENET1K_V1`. You can also use `weights=ResNet18_Weights.DEFAULT` to get the most up-to-date weights.\n",
+      "  warnings.warn(msg)\n"
+     ]
+    },
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "Epoch 1/10\n",
+      "----------\n"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "/Users/zhangzhengfei/miniconda3/lib/python3.12/site-packages/torch/optim/lr_scheduler.py:224: UserWarning: Detected call of `lr_scheduler.step()` before `optimizer.step()`. In PyTorch 1.1.0 and later, you should call them in the opposite order: `optimizer.step()` before `lr_scheduler.step()`.  Failure to do this will result in PyTorch skipping the first value of the learning rate schedule. See more details at https://pytorch.org/docs/stable/optim.html#how-to-adjust-learning-rate\n",
+      "  warnings.warn(\n"
+     ]
+    },
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "train Loss: 0.6181 Acc: 0.6762\n",
+      "val Loss: 0.1930 Acc: 0.9481\n",
+      "\n",
+      "Epoch 2/10\n",
+      "----------\n",
+      "train Loss: 0.4707 Acc: 0.7787\n",
+      "val Loss: 0.1752 Acc: 0.9221\n",
+      "\n",
+      "Epoch 3/10\n",
+      "----------\n",
+      "train Loss: 0.4391 Acc: 0.7992\n",
+      "val Loss: 0.1901 Acc: 0.8961\n",
+      "\n",
+      "Epoch 4/10\n",
+      "----------\n",
+      "train Loss: 0.3229 Acc: 0.8525\n",
+      "val Loss: 0.2757 Acc: 0.8831\n",
+      "\n",
+      "Epoch 5/10\n",
+      "----------\n",
+      "train Loss: 0.4638 Acc: 0.7910\n",
+      "val Loss: 0.1796 Acc: 0.9351\n",
+      "\n",
+      "Epoch 6/10\n",
+      "----------\n",
+      "train Loss: 0.4439 Acc: 0.8033\n",
+      "val Loss: 0.1834 Acc: 0.9351\n",
+      "\n",
+      "Epoch 7/10\n",
+      "----------\n",
+      "train Loss: 0.3871 Acc: 0.8361\n",
+      "val Loss: 0.1590 Acc: 0.9481\n",
+      "\n",
+      "Epoch 8/10\n",
+      "----------\n",
+      "train Loss: 0.3795 Acc: 0.8156\n",
+      "val Loss: 0.1496 Acc: 0.9610\n",
+      "\n",
+      "Epoch 9/10\n",
+      "----------\n",
+      "train Loss: 0.3447 Acc: 0.8566\n",
+      "val Loss: 0.1346 Acc: 0.9481\n",
+      "\n",
+      "Epoch 10/10\n",
+      "----------\n",
+      "train Loss: 0.3489 Acc: 0.8402\n",
+      "val Loss: 0.1876 Acc: 0.9351\n",
+      "\n",
+      "Training complete in 8m 34s\n",
+      "Best val Acc: 0.961039\n"
+     ]
+    }
+   ],
    "source": [
     "import copy\n",
     "import os\n",
@@ -1727,13 +3232,20 @@
     "    x: datasets.ImageFolder(os.path.join(data_dir, x), data_transforms[x])\n",
     "    for x in [\"train\", \"val\"]\n",
     "}\n",
+    "\n",
+    "val, test = torch.utils.data.random_split(image_datasets[\"val\"], [0.5, 0.5])\n",
+    "image_datasets[\"val\"] = val\n",
+    "image_datasets[\"test\"] = test\n",
+    "\n",
     "dataloaders = {\n",
     "    x: torch.utils.data.DataLoader(\n",
     "        image_datasets[x], batch_size=4, shuffle=True, num_workers=4\n",
     "    )\n",
-    "    for x in [\"train\", \"val\"]\n",
+    "    for x in [\"train\", \"val\", \"test\"]\n",
     "}\n",
-    "dataset_sizes = {x: len(image_datasets[x]) for x in [\"train\", \"val\"]}\n",
+    "\n",
+    "\n",
+    "dataset_sizes = {x: len(image_datasets[x]) for x in [\"train\", \"val\", \"test\"]}\n",
     "class_names = image_datasets[\"train\"].classes\n",
     "device = torch.device(\"cuda:0\" if torch.cuda.is_available() else \"cpu\")\n",
     "\n",
@@ -1872,13 +3384,194 @@
     "Study the code and the results obtained.\n",
     "\n",
     "Modify the code and add an \"eval_model\" function to allow\n",
-    "the evaluation of the model on a test set (different from the learning and validation sets used during the learning phase). Study the results obtained.\n",
+    "the evaluation of the model on a test set (different from the learning and validation sets used during the learning phase). Study the results obtained. \n",
+    "\n",
+    "**Model evaluation below, set splitting for testing is already integrated in the above code**\n",
     "\n",
     "Now modify the code to replace the current classification layer with a set of two layers using a \"relu\" activation function for the middle layer, and the \"dropout\" mechanism for both layers. Renew the experiments and study the results obtained.\n",
     "\n",
     "Apply ther quantization (post and quantization aware) and evaluate impact on model size and accuracy."
    ]
   },
+  {
+   "cell_type": "code",
+   "execution_count": 31,
+   "id": "2b23d952",
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "Test Loss: 0.1947 Acc: 0.9474\n"
+     ]
+    }
+   ],
+   "source": [
+    "def eval_model(model, criterion):\n",
+    "    model.eval()  # Set model to evaluation mode\n",
+    "    running_loss = 0.0\n",
+    "    running_corrects = 0\n",
+    "\n",
+    "    with torch.no_grad():\n",
+    "        for inputs, labels in dataloaders[\"test\"]:\n",
+    "            inputs = inputs.to(device)\n",
+    "            labels = labels.to(device)\n",
+    "\n",
+    "            # Forward pass\n",
+    "            outputs = model(inputs)\n",
+    "            _, preds = torch.max(outputs, 1)\n",
+    "            loss = criterion(outputs, labels)\n",
+    "\n",
+    "            # Statistics\n",
+    "            running_loss += loss.item() * inputs.size(0)\n",
+    "            running_corrects += torch.sum(preds == labels.data)\n",
+    "\n",
+    "    test_loss = running_loss / dataset_sizes[\"test\"]\n",
+    "    test_acc = running_corrects.double() / dataset_sizes[\"test\"]\n",
+    "\n",
+    "    print(\"Test Loss: {:.4f} Acc: {:.4f}\".format(test_loss, test_acc))\n",
+    "\n",
+    "    return test_loss, test_acc\n",
+    "\n",
+    "\n",
+    "test_loss, test_acc = eval_model(model, criterion)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 33,
+   "id": "a6775fac",
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "Epoch 1/10\n",
+      "----------\n",
+      "train Loss: 0.6545 Acc: 0.5943\n",
+      "val Loss: 0.5005 Acc: 0.6753\n",
+      "\n",
+      "Epoch 2/10\n",
+      "----------\n",
+      "train Loss: 0.6066 Acc: 0.6516\n",
+      "val Loss: 0.4681 Acc: 0.8961\n",
+      "\n",
+      "Epoch 3/10\n",
+      "----------\n",
+      "train Loss: 0.5511 Acc: 0.6926\n",
+      "val Loss: 0.3274 Acc: 0.9351\n",
+      "\n",
+      "Epoch 4/10\n",
+      "----------\n",
+      "train Loss: 0.4574 Acc: 0.8115\n",
+      "val Loss: 0.2405 Acc: 0.9610\n",
+      "\n",
+      "Epoch 5/10\n",
+      "----------\n",
+      "train Loss: 0.4664 Acc: 0.7541\n",
+      "val Loss: 0.2585 Acc: 0.9091\n",
+      "\n",
+      "Epoch 6/10\n",
+      "----------\n",
+      "train Loss: 0.5221 Acc: 0.7295\n",
+      "val Loss: 0.2222 Acc: 0.9610\n",
+      "\n",
+      "Epoch 7/10\n",
+      "----------\n",
+      "train Loss: 0.5263 Acc: 0.6803\n",
+      "val Loss: 0.2159 Acc: 0.9481\n",
+      "\n",
+      "Epoch 8/10\n",
+      "----------\n",
+      "train Loss: 0.4898 Acc: 0.7336\n",
+      "val Loss: 0.2358 Acc: 0.9221\n",
+      "\n",
+      "Epoch 9/10\n",
+      "----------\n",
+      "train Loss: 0.5439 Acc: 0.6844\n",
+      "val Loss: 0.2218 Acc: 0.9610\n",
+      "\n",
+      "Epoch 10/10\n",
+      "----------\n",
+      "train Loss: 0.4909 Acc: 0.7418\n",
+      "val Loss: 0.2330 Acc: 0.9351\n",
+      "\n",
+      "Training complete in 8m 35s\n",
+      "Best val Acc: 0.961039\n",
+      "Test Loss: 0.2661 Acc: 0.9474\n"
+     ]
+    },
+    {
+     "data": {
+      "text/plain": [
+       "(0.26611060727583735, tensor(0.9474, dtype=torch.float64))"
+      ]
+     },
+     "execution_count": 33,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "# Download a pre-trained ResNet18 model and freeze its weights\n",
+    "model = torchvision.models.resnet18(pretrained=True)\n",
+    "for param in model.parameters():\n",
+    "    param.requires_grad = False\n",
+    "\n",
+    "# Replace the final fully connected layer\n",
+    "# Parameters of newly constructed modules have requires_grad=True by default\n",
+    "num_ftrs = model.fc.in_features # 512\n",
+    "model.fc = nn.Sequential(nn.Linear(num_ftrs, 64), \n",
+    "                         nn.ReLU(), \n",
+    "                         nn.Dropout(p=0.4),\n",
+    "                         nn.Linear(64, 2),\n",
+    "                         nn.Dropout(p=0.4)\n",
+    "                         )\n",
+    "# Send the model to the GPU\n",
+    "model = model.to(device)\n",
+    "# Set the loss function\n",
+    "criterion = nn.CrossEntropyLoss()\n",
+    "\n",
+    "# Observe that only the parameters of the final layer are being optimized\n",
+    "optimizer_conv = optim.SGD(model.fc.parameters(), lr=0.001, momentum=0.9)\n",
+    "exp_lr_scheduler = lr_scheduler.StepLR(optimizer_conv, step_size=7, gamma=0.1)\n",
+    "model, epoch_time = train_model(\n",
+    "    model, criterion, optimizer_conv, exp_lr_scheduler, num_epochs=10\n",
+    ")\n",
+    "eval_model(model, criterion)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 34,
+   "id": "a7b0621d",
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "Test Loss: 0.2658 Acc: 0.9474\n"
+     ]
+    },
+    {
+     "data": {
+      "text/plain": [
+       "(0.26576109740294906, tensor(0.9474, dtype=torch.float64))"
+      ]
+     },
+     "execution_count": 34,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "quantized_model_2 = torch.quantization.quantize_dynamic(model, dtype=torch.qint8)\n",
+    "eval_model(quantized_model_2, criterion)"
+   ]
+  },
   {
    "cell_type": "markdown",
    "id": "04a263f0",
diff --git a/dog.jpg b/dog.jpg
new file mode 100644
index 0000000000000000000000000000000000000000..786dc161c6d8981020d04d7a7082ab1d4fcb1bef
Binary files /dev/null and b/dog.jpg differ
diff --git a/eel.jpg b/eel.jpg
new file mode 100644
index 0000000000000000000000000000000000000000..7ae86fa45de08a38b3910a266845a6bab73ca04f
Binary files /dev/null and b/eel.jpg differ
diff --git a/gaspump.jpg b/gaspump.jpg
new file mode 100644
index 0000000000000000000000000000000000000000..490348c9118083f28dfca9aa9500d93bc0075c67
Binary files /dev/null and b/gaspump.jpg differ
diff --git a/golf-cart.jpg b/golf-cart.jpg
new file mode 100644
index 0000000000000000000000000000000000000000..af492d317b7452085f37fb413de02994a6a106e0
Binary files /dev/null and b/golf-cart.jpg differ
diff --git a/gondola.jpg b/gondola.jpg
new file mode 100644
index 0000000000000000000000000000000000000000..a7c9712a3ffaf8f68c84471bfd1d4e1cb8a978c4
Binary files /dev/null and b/gondola.jpg differ