From e8a08a8a930ae78dd6663473b174d4cfc319c752 Mon Sep 17 00:00:00 2001
From: John <willems@disroot.org>
Date: Tue, 13 Jun 2023 22:12:02 +0200
Subject: [PATCH] test tensors

---
 .../C1W1_Your_First_GAN.ipynb                 | 92 +++++++++++++------
 1 file changed, 65 insertions(+), 27 deletions(-)

diff --git a/Courses/GANs_Specialization/1_Build_Basic_GANs/Week_1:Intro_to_GANs/C1W1_Your_First_GAN.ipynb b/Courses/GANs_Specialization/1_Build_Basic_GANs/Week_1:Intro_to_GANs/C1W1_Your_First_GAN.ipynb
index 70f7a5d..11cdba7 100644
--- a/Courses/GANs_Specialization/1_Build_Basic_GANs/Week_1:Intro_to_GANs/C1W1_Your_First_GAN.ipynb
+++ b/Courses/GANs_Specialization/1_Build_Basic_GANs/Week_1:Intro_to_GANs/C1W1_Your_First_GAN.ipynb
@@ -42,7 +42,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 52,
+   "execution_count": 2,
    "metadata": {
     "colab": {},
     "colab_type": "code",
@@ -61,6 +61,8 @@
     "from torch.utils.data import DataLoader\n",
     "import matplotlib.pyplot as plt\n",
     "\n",
+    "from collections import OrderedDict\n",
+    "\n",
     "torch.manual_seed(0) # Set for testing purposes, please do not change!\n",
     "\n",
     "def show_tensor_images(image_tensor, num_images=25, size=(1, 28, 28)):\n",
@@ -116,7 +118,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 23,
+   "execution_count": 3,
    "metadata": {
     "colab": {},
     "colab_type": "code",
@@ -150,6 +152,57 @@
     "    )"
    ]
   },
+  {
+   "cell_type": "code",
+   "execution_count": 37,
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "tensor([[-1.0690],\n",
+      "        [-0.2673],\n",
+      "        [ 1.3363]], grad_fn=<NativeBatchNormBackward0>)\n",
+      "tensor([[-1.0000, -1.0000],\n",
+      "        [ 1.0000,  1.0000]], grad_fn=<NativeBatchNormBackward0>)\n",
+      "tensor([[-1.0000, -1.0000, -1.0000],\n",
+      "        [ 1.0000,  1.0000,  1.0000]], grad_fn=<NativeBatchNormBackward0>)\n"
+     ]
+    }
+   ],
+   "source": [
+    "x1 = nn.BatchNorm1d(1)\n",
+    "x2 = nn.BatchNorm1d(2)\n",
+    "x3 = nn.BatchNorm1d(3)\n",
+    "a1 = torch.tensor([[5.],[6.],[8.]])         # torch.Size([3, 1])\n",
+    "a2 = torch.tensor([[2.,3.],[5.,4.]])        # torch.Size([2, 2])\n",
+    "a3 = torch.tensor([[2.,3.,6.],[5.,4.,9.]])  # torch.Size([2, 3])\n",
+    "print(x1(a1))\n",
+    "print(x2(a2))\n",
+    "print(x3(a3))"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 34,
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "torch.Size([3, 1])"
+      ]
+     },
+     "execution_count": 34,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "a1.size()"
+   ]
+  },
   {
    "cell_type": "code",
    "execution_count": 4,
@@ -224,34 +277,19 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 42,
+   "execution_count": 1,
    "metadata": {},
    "outputs": [
     {
-     "data": {
-      "text/plain": [
-       "Sequential(\n",
-       "  (0): Sequential(\n",
-       "    (0): Linear(in_features=10, out_features=128, bias=True)\n",
-       "    (1): BatchNorm1d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
-       "    (2): ReLU(inplace=True)\n",
-       "  )\n",
-       "  (1): Sequential(\n",
-       "    (0): Linear(in_features=128, out_features=256, bias=True)\n",
-       "    (1): BatchNorm1d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
-       "    (2): ReLU(inplace=True)\n",
-       "  )\n",
-       "  (2): Sequential(\n",
-       "    (0): Linear(in_features=256, out_features=512, bias=True)\n",
-       "    (1): BatchNorm1d(512, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
-       "    (2): ReLU(inplace=True)\n",
-       "  )\n",
-       ")"
-      ]
-     },
-     "execution_count": 42,
-     "metadata": {},
-     "output_type": "execute_result"
+     "ename": "NameError",
+     "evalue": "name 'nn' is not defined",
+     "output_type": "error",
+     "traceback": [
+      "\u001b[0;31m---------------------------------------------------------------------------\u001b[0m",
+      "\u001b[0;31mNameError\u001b[0m                                 Traceback (most recent call last)",
+      "Cell \u001b[0;32mIn[1], line 4\u001b[0m\n\u001b[1;32m      2\u001b[0m im_dim \u001b[39m=\u001b[39m \u001b[39m784\u001b[39m\n\u001b[1;32m      3\u001b[0m hidden_dim \u001b[39m=\u001b[39m \u001b[39m128\u001b[39m\n\u001b[0;32m----> 4\u001b[0m nn\u001b[39m.\u001b[39mSequential(\n\u001b[1;32m      5\u001b[0m     get_generator_block(z_dim, hidden_dim),\n\u001b[1;32m      6\u001b[0m     get_generator_block(hidden_dim, hidden_dim \u001b[39m*\u001b[39m \u001b[39m2\u001b[39m),\n\u001b[1;32m      7\u001b[0m     get_generator_block(hidden_dim \u001b[39m*\u001b[39m \u001b[39m2\u001b[39m, hidden_dim \u001b[39m*\u001b[39m \u001b[39m4\u001b[39m),\n\u001b[1;32m      8\u001b[0m )\n",
+      "\u001b[0;31mNameError\u001b[0m: name 'nn' is not defined"
+     ]
     }
    ],
    "source": [