diff --git a/Performance of Model 1.png b/Performance of Model 1.png
new file mode 100644
index 0000000000000000000000000000000000000000..912aeb1cb2d3cc31574f8857885a41f5b608ac1e
Binary files /dev/null and b/Performance of Model 1.png differ
diff --git a/TD2 Deep Learning.ipynb b/TD2 Deep Learning.ipynb
index 40aec981e8623c8690aa43afa1f21cbe3e03283e..abb507f6a947450bf579307a2bdb730a18311129 100644
--- a/TD2 Deep Learning.ipynb	
+++ b/TD2 Deep Learning.ipynb	
@@ -50,21 +50,30 @@
      "text": [
       "Requirement already satisfied: torch in c:\\users\\achraf faytout\\.conda\\envs\\be2\\lib\\site-packages (2.1.1)\n",
       "Requirement already satisfied: torchvision in c:\\users\\achraf faytout\\.conda\\envs\\be2\\lib\\site-packages (0.16.1)\n",
-      "Requirement already satisfied: filelock in c:\\users\\achraf faytout\\.conda\\envs\\be2\\lib\\site-packages (from torch) (3.13.1)\n",
-      "Requirement already satisfied: typing-extensions in c:\\users\\achraf faytout\\.conda\\envs\\be2\\lib\\site-packages (from torch) (4.7.1)\n",
-      "Requirement already satisfied: sympy in c:\\users\\achraf faytout\\.conda\\envs\\be2\\lib\\site-packages (from torch) (1.11.1)\n",
-      "Requirement already satisfied: networkx in c:\\users\\achraf faytout\\.conda\\envs\\be2\\lib\\site-packages (from torch) (3.1)\n",
-      "Requirement already satisfied: jinja2 in c:\\users\\achraf faytout\\.conda\\envs\\be2\\lib\\site-packages (from torch) (3.1.2)\n",
-      "Requirement already satisfied: fsspec in c:\\users\\achraf faytout\\.conda\\envs\\be2\\lib\\site-packages (from torch) (2023.10.0)\n",
+      "Collecting filelock (from torch)\n",
+      "  Using cached filelock-3.13.1-py3-none-any.whl.metadata (2.8 kB)\n",
+      "Requirement already satisfied: typing-extensions in c:\\users\\achraf faytout\\.conda\\envs\\be2\\lib\\site-packages (from torch) (4.8.0)\n",
+      "Requirement already satisfied: sympy in c:\\users\\achraf faytout\\.conda\\envs\\be2\\lib\\site-packages (from torch) (1.12)\n",
+      "Requirement already satisfied: networkx in c:\\users\\achraf faytout\\.conda\\envs\\be2\\lib\\site-packages (from torch) (3.2.1)\n",
+      "Collecting jinja2 (from torch)\n",
+      "  Using cached Jinja2-3.1.2-py3-none-any.whl (133 kB)\n",
+      "Collecting fsspec (from torch)\n",
+      "  Using cached fsspec-2023.10.0-py3-none-any.whl.metadata (6.8 kB)\n",
       "Requirement already satisfied: numpy in c:\\users\\achraf faytout\\.conda\\envs\\be2\\lib\\site-packages (from torchvision) (1.26.2)\n",
       "Requirement already satisfied: requests in c:\\users\\achraf faytout\\.conda\\envs\\be2\\lib\\site-packages (from torchvision) (2.31.0)\n",
       "Requirement already satisfied: pillow!=8.3.*,>=5.3.0 in c:\\users\\achraf faytout\\.conda\\envs\\be2\\lib\\site-packages (from torchvision) (10.0.1)\n",
-      "Requirement already satisfied: MarkupSafe>=2.0 in c:\\users\\achraf faytout\\.conda\\envs\\be2\\lib\\site-packages (from jinja2->torch) (2.1.1)\n",
+      "Collecting MarkupSafe>=2.0 (from jinja2->torch)\n",
+      "  Using cached MarkupSafe-2.1.3-cp310-cp310-win_amd64.whl.metadata (3.1 kB)\n",
       "Requirement already satisfied: charset-normalizer<4,>=2 in c:\\users\\achraf faytout\\.conda\\envs\\be2\\lib\\site-packages (from requests->torchvision) (3.3.2)\n",
       "Requirement already satisfied: idna<4,>=2.5 in c:\\users\\achraf faytout\\.conda\\envs\\be2\\lib\\site-packages (from requests->torchvision) (3.6)\n",
       "Requirement already satisfied: urllib3<3,>=1.21.1 in c:\\users\\achraf faytout\\.conda\\envs\\be2\\lib\\site-packages (from requests->torchvision) (2.1.0)\n",
       "Requirement already satisfied: certifi>=2017.4.17 in c:\\users\\achraf faytout\\.conda\\envs\\be2\\lib\\site-packages (from requests->torchvision) (2023.11.17)\n",
-      "Requirement already satisfied: mpmath>=0.19 in c:\\users\\achraf faytout\\.conda\\envs\\be2\\lib\\site-packages (from sympy->torch) (1.3.0)\n"
+      "Requirement already satisfied: mpmath>=0.19 in c:\\users\\achraf faytout\\.conda\\envs\\be2\\lib\\site-packages (from sympy->torch) (1.3.0)\n",
+      "Using cached filelock-3.13.1-py3-none-any.whl (11 kB)\n",
+      "Using cached fsspec-2023.10.0-py3-none-any.whl (166 kB)\n",
+      "Using cached MarkupSafe-2.1.3-cp310-cp310-win_amd64.whl (17 kB)\n",
+      "Installing collected packages: MarkupSafe, fsspec, filelock, jinja2\n",
+      "Successfully installed MarkupSafe-2.1.3 filelock-3.13.1 fsspec-2023.10.0 jinja2-3.1.2\n"
      ]
     }
    ],
@@ -92,7 +101,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 3,
+   "execution_count": 4,
    "id": "b1950f0a",
    "metadata": {},
    "outputs": [
@@ -100,34 +109,34 @@
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "tensor([[ 1.8828, -1.0059, -0.4481, -0.4452,  1.1012,  0.5528, -0.4446, -1.2475,\n",
-      "         -1.0458, -1.5559],\n",
-      "        [ 2.6994,  0.5091,  0.0545, -0.9753, -0.5175, -1.3184, -0.3091, -0.1875,\n",
-      "          0.0908,  0.5766],\n",
-      "        [ 0.4527, -0.6613,  0.2349, -0.1581,  0.8230,  0.2393,  0.2802, -1.3296,\n",
-      "          0.5578,  0.2187],\n",
-      "        [-0.2961,  0.3193,  0.0273, -1.4184, -0.0799,  1.1374, -0.1410,  0.2565,\n",
-      "         -0.6201,  0.0557],\n",
-      "        [ 2.1253, -0.0187,  0.1655,  0.2128, -1.7500,  0.1240,  0.3802, -0.0044,\n",
-      "         -1.9579, -1.0040],\n",
-      "        [ 0.7997,  1.3967,  0.4131,  1.0317, -0.2586, -0.0181, -0.3695, -0.9172,\n",
-      "          0.6297, -1.5012],\n",
-      "        [ 0.0682, -0.2179,  0.0404, -1.3868,  1.7578, -2.2365,  1.2623, -0.2020,\n",
-      "         -0.8817, -0.5123],\n",
-      "        [ 0.0788, -1.3835, -1.7053,  0.6960, -0.4434,  0.3524,  0.2566,  0.4434,\n",
-      "         -0.0250,  1.5694],\n",
-      "        [-1.7132,  0.5123,  1.4630, -0.4194,  0.1211,  2.1514, -0.7760,  0.3360,\n",
-      "         -1.0299, -0.1466],\n",
-      "        [ 0.2007, -0.2498,  1.1612, -0.8410,  0.2616,  0.5222,  1.5595,  0.6125,\n",
-      "          0.8382, -0.5771],\n",
-      "        [-0.0176,  0.5599,  0.6295,  1.0329,  1.4094,  1.3477, -1.6303, -1.0945,\n",
-      "         -1.2531, -0.0357],\n",
-      "        [ 0.5993, -0.2517,  0.5627,  0.4063,  1.3002, -1.3931,  1.3886, -1.2978,\n",
-      "          1.2636, -0.4323],\n",
-      "        [-1.0180,  1.0876,  0.1364,  0.1040,  0.8418, -0.1909,  0.4429,  0.3640,\n",
-      "         -0.0360,  0.0845],\n",
-      "        [-0.9201,  1.1223,  0.7203, -0.2873, -0.4576,  0.0902, -1.4914,  0.5851,\n",
-      "         -1.7298, -0.3709]])\n",
+      "tensor([[-1.2794,  0.4882, -0.5845,  1.7999, -0.3980, -1.5906,  0.0929,  2.7471,\n",
+      "         -0.7910,  0.2796],\n",
+      "        [ 1.5044, -1.0034, -0.7065, -0.3326,  0.1177, -0.0282,  0.1172,  0.9875,\n",
+      "         -0.4349, -0.0628],\n",
+      "        [ 0.8020, -0.9377, -1.4200,  0.8264,  0.2188, -1.2548, -1.6464,  0.4904,\n",
+      "         -1.4024, -1.0286],\n",
+      "        [-0.7846,  1.7147, -0.7240,  0.4274,  0.1361, -0.4141, -0.1784, -0.3079,\n",
+      "          0.4058, -1.3223],\n",
+      "        [ 0.0686,  0.7093, -0.9916, -0.1303,  0.0701, -1.2497, -1.9761, -0.6244,\n",
+      "          0.6928, -0.1080],\n",
+      "        [ 1.4553, -1.7249,  1.1030, -0.1678,  0.7122,  1.3154, -0.3891,  0.5928,\n",
+      "         -1.3212,  2.2003],\n",
+      "        [ 0.8434,  0.4557, -1.5143,  0.1695, -1.5549, -1.0949, -0.3064,  0.5745,\n",
+      "          0.8606,  0.1924],\n",
+      "        [-0.8485, -1.0998,  1.5792, -0.3993, -0.9275, -1.0458, -2.3410, -0.6423,\n",
+      "         -0.8848, -0.1965],\n",
+      "        [-0.5170,  0.2400,  0.8206,  0.1117, -0.3324, -0.3934,  0.7128, -0.0739,\n",
+      "          0.4508, -0.8692],\n",
+      "        [-1.2849, -0.3182,  1.9692,  0.5192,  0.2534,  0.0645, -0.5543,  0.4860,\n",
+      "          0.9970,  2.2465],\n",
+      "        [ 0.0090, -1.0049,  0.2339,  0.1390,  1.9514,  0.4566, -0.6524,  0.7028,\n",
+      "         -0.8895,  0.8269],\n",
+      "        [-0.7317, -0.7411,  0.2181, -0.4123, -0.3879,  0.5728,  2.8530, -0.8089,\n",
+      "         -0.3047, -0.8699],\n",
+      "        [ 0.3650, -0.4581, -0.6786,  1.7369, -0.2857, -0.9173, -0.2014,  0.3446,\n",
+      "          0.5785,  0.4457],\n",
+      "        [ 0.2585, -1.8061, -0.5656, -0.2165, -1.0256, -0.0692,  1.5222, -0.2625,\n",
+      "         -2.0423, -0.4768]])\n",
       "AlexNet(\n",
       "  (features): Sequential(\n",
       "    (0): Conv2d(3, 64, kernel_size=(11, 11), stride=(4, 4), padding=(2, 2))\n",
@@ -197,7 +206,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 4,
+   "execution_count": 5,
    "id": "6e18f2fd",
    "metadata": {},
    "outputs": [
@@ -231,7 +240,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 5,
+   "execution_count": 6,
    "id": "462666a2",
    "metadata": {},
    "outputs": [
@@ -304,7 +313,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 6,
+   "execution_count": 7,
    "metadata": {},
    "outputs": [
     {
@@ -346,7 +355,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 7,
+   "execution_count": 8,
    "id": "317bf070",
    "metadata": {},
    "outputs": [
@@ -410,7 +419,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 8,
+   "execution_count": 9,
    "id": "4b53f229",
    "metadata": {},
    "outputs": [
@@ -418,49 +427,50 @@
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Epoch: 0 \tTraining Loss: 42.996585 \tValidation Loss: 37.248631\n",
-      "Validation loss decreased (inf --> 37.248631).  Saving model ...\n",
-      "Epoch: 1 \tTraining Loss: 34.160423 \tValidation Loss: 32.043942\n",
-      "Validation loss decreased (37.248631 --> 32.043942).  Saving model ...\n",
-      "Epoch: 2 \tTraining Loss: 30.524945 \tValidation Loss: 29.317808\n",
-      "Validation loss decreased (32.043942 --> 29.317808).  Saving model ...\n",
-      "Epoch: 3 \tTraining Loss: 28.575873 \tValidation Loss: 27.824641\n",
-      "Validation loss decreased (29.317808 --> 27.824641).  Saving model ...\n",
-      "Epoch: 4 \tTraining Loss: 26.938963 \tValidation Loss: 26.998535\n",
-      "Validation loss decreased (27.824641 --> 26.998535).  Saving model ...\n",
-      "Epoch: 5 \tTraining Loss: 25.550005 \tValidation Loss: 26.820696\n",
-      "Validation loss decreased (26.998535 --> 26.820696).  Saving model ...\n",
-      "Epoch: 6 \tTraining Loss: 24.375535 \tValidation Loss: 25.311895\n",
-      "Validation loss decreased (26.820696 --> 25.311895).  Saving model ...\n",
-      "Epoch: 7 \tTraining Loss: 23.341043 \tValidation Loss: 24.180573\n",
-      "Validation loss decreased (25.311895 --> 24.180573).  Saving model ...\n",
-      "Epoch: 8 \tTraining Loss: 22.365410 \tValidation Loss: 23.835102\n",
-      "Validation loss decreased (24.180573 --> 23.835102).  Saving model ...\n",
-      "Epoch: 9 \tTraining Loss: 21.577228 \tValidation Loss: 24.845098\n",
-      "Epoch: 10 \tTraining Loss: 20.739596 \tValidation Loss: 23.204051\n",
-      "Validation loss decreased (23.835102 --> 23.204051).  Saving model ...\n",
-      "Epoch: 11 \tTraining Loss: 20.004250 \tValidation Loss: 22.925011\n",
-      "Validation loss decreased (23.204051 --> 22.925011).  Saving model ...\n",
-      "Epoch: 12 \tTraining Loss: 19.272478 \tValidation Loss: 22.303851\n",
-      "Validation loss decreased (22.925011 --> 22.303851).  Saving model ...\n",
-      "Epoch: 13 \tTraining Loss: 18.652569 \tValidation Loss: 22.138239\n",
-      "Validation loss decreased (22.303851 --> 22.138239).  Saving model ...\n",
-      "Epoch: 14 \tTraining Loss: 18.023433 \tValidation Loss: 22.224670\n",
-      "Epoch: 15 \tTraining Loss: 17.370177 \tValidation Loss: 22.718537\n",
-      "Epoch: 16 \tTraining Loss: 16.794893 \tValidation Loss: 22.140640\n",
-      "Epoch: 17 \tTraining Loss: 16.167470 \tValidation Loss: 22.600644\n",
-      "Epoch: 18 \tTraining Loss: 15.698444 \tValidation Loss: 22.326390\n",
-      "Epoch: 19 \tTraining Loss: 15.151722 \tValidation Loss: 23.030794\n",
-      "Epoch: 20 \tTraining Loss: 14.663699 \tValidation Loss: 23.143683\n",
-      "Epoch: 21 \tTraining Loss: 14.106726 \tValidation Loss: 22.807385\n",
-      "Epoch: 22 \tTraining Loss: 13.637904 \tValidation Loss: 23.447134\n",
-      "Epoch: 23 \tTraining Loss: 13.097671 \tValidation Loss: 24.971700\n",
-      "Epoch: 24 \tTraining Loss: 12.662973 \tValidation Loss: 25.471628\n",
-      "Epoch: 25 \tTraining Loss: 12.245027 \tValidation Loss: 25.685873\n",
-      "Epoch: 26 \tTraining Loss: 11.807602 \tValidation Loss: 25.143901\n",
-      "Epoch: 27 \tTraining Loss: 11.385496 \tValidation Loss: 25.764403\n",
-      "Epoch: 28 \tTraining Loss: 10.937347 \tValidation Loss: 26.373830\n",
-      "Epoch: 29 \tTraining Loss: 10.539471 \tValidation Loss: 27.607664\n"
+      "Epoch: 0 \tTraining Loss: 42.684944 \tValidation Loss: 38.051762\n",
+      "Validation loss decreased (inf --> 38.051762).  Saving model ...\n",
+      "Epoch: 1 \tTraining Loss: 34.362200 \tValidation Loss: 32.100003\n",
+      "Validation loss decreased (38.051762 --> 32.100003).  Saving model ...\n",
+      "Epoch: 2 \tTraining Loss: 30.699758 \tValidation Loss: 29.829906\n",
+      "Validation loss decreased (32.100003 --> 29.829906).  Saving model ...\n",
+      "Epoch: 3 \tTraining Loss: 28.636639 \tValidation Loss: 27.644334\n",
+      "Validation loss decreased (29.829906 --> 27.644334).  Saving model ...\n",
+      "Epoch: 4 \tTraining Loss: 27.035070 \tValidation Loss: 26.414261\n",
+      "Validation loss decreased (27.644334 --> 26.414261).  Saving model ...\n",
+      "Epoch: 5 \tTraining Loss: 25.561310 \tValidation Loss: 25.290589\n",
+      "Validation loss decreased (26.414261 --> 25.290589).  Saving model ...\n",
+      "Epoch: 6 \tTraining Loss: 24.435097 \tValidation Loss: 24.265817\n",
+      "Validation loss decreased (25.290589 --> 24.265817).  Saving model ...\n",
+      "Epoch: 7 \tTraining Loss: 23.348866 \tValidation Loss: 23.822086\n",
+      "Validation loss decreased (24.265817 --> 23.822086).  Saving model ...\n",
+      "Epoch: 8 \tTraining Loss: 22.444620 \tValidation Loss: 23.803609\n",
+      "Validation loss decreased (23.822086 --> 23.803609).  Saving model ...\n",
+      "Epoch: 9 \tTraining Loss: 21.623235 \tValidation Loss: 22.938253\n",
+      "Validation loss decreased (23.803609 --> 22.938253).  Saving model ...\n",
+      "Epoch: 10 \tTraining Loss: 20.838078 \tValidation Loss: 22.255618\n",
+      "Validation loss decreased (22.938253 --> 22.255618).  Saving model ...\n",
+      "Epoch: 11 \tTraining Loss: 20.030158 \tValidation Loss: 22.129453\n",
+      "Validation loss decreased (22.255618 --> 22.129453).  Saving model ...\n",
+      "Epoch: 12 \tTraining Loss: 19.361079 \tValidation Loss: 21.821713\n",
+      "Validation loss decreased (22.129453 --> 21.821713).  Saving model ...\n",
+      "Epoch: 13 \tTraining Loss: 18.696286 \tValidation Loss: 22.176465\n",
+      "Epoch: 14 \tTraining Loss: 18.010778 \tValidation Loss: 21.106473\n",
+      "Validation loss decreased (21.821713 --> 21.106473).  Saving model ...\n",
+      "Epoch: 15 \tTraining Loss: 17.438658 \tValidation Loss: 21.717994\n",
+      "Epoch: 16 \tTraining Loss: 16.805439 \tValidation Loss: 21.671730\n",
+      "Epoch: 17 \tTraining Loss: 16.255950 \tValidation Loss: 22.948138\n",
+      "Epoch: 18 \tTraining Loss: 15.736671 \tValidation Loss: 23.720485\n",
+      "Epoch: 19 \tTraining Loss: 15.186564 \tValidation Loss: 21.873747\n",
+      "Epoch: 20 \tTraining Loss: 14.735234 \tValidation Loss: 21.490069\n",
+      "Epoch: 21 \tTraining Loss: 14.149223 \tValidation Loss: 22.076123\n",
+      "Epoch: 22 \tTraining Loss: 13.684295 \tValidation Loss: 23.688867\n",
+      "Epoch: 23 \tTraining Loss: 13.208945 \tValidation Loss: 23.035013\n",
+      "Epoch: 24 \tTraining Loss: 12.753977 \tValidation Loss: 23.947329\n",
+      "Epoch: 25 \tTraining Loss: 12.327804 \tValidation Loss: 23.363292\n",
+      "Epoch: 26 \tTraining Loss: 11.929456 \tValidation Loss: 24.268032\n",
+      "Epoch: 27 \tTraining Loss: 11.526298 \tValidation Loss: 24.391640\n",
+      "Epoch: 28 \tTraining Loss: 11.076694 \tValidation Loss: 24.709161\n",
+      "Epoch: 29 \tTraining Loss: 10.715857 \tValidation Loss: 26.162475\n"
      ]
     }
    ],
@@ -546,13 +556,31 @@
   },
   {
    "cell_type": "code",
-   "execution_count": null,
+   "execution_count": 10,
    "id": "d39df818",
    "metadata": {},
-   "outputs": [],
+   "outputs": [
+    {
+     "data": {
+      "image/png": "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",
+      "text/plain": [
+       "<Figure size 640x480 with 1 Axes>"
+      ]
+     },
+     "metadata": {},
+     "output_type": "display_data"
+    },
+    {
+     "data": {
+      "text/plain": [
+       "<Figure size 640x480 with 0 Axes>"
+      ]
+     },
+     "metadata": {},
+     "output_type": "display_data"
+    }
+   ],
    "source": [
-    "import matplotlib.pyplot as plt\n",
-    "\n",
     "plt.plot(range(n_epochs), train_loss_list, label = \"Training\")\n",
     "plt.plot(range(n_epochs), valid_loss_list, label = \"Validation\") # to observe the overfitting\n",
     "plt.xlabel(\"Epoch\")\n",