修正：修改计算错误，增加详细说明介绍

Author: zergtant

chapter2/2.1.3-pytorch-basics-nerual-network.ipynb

@@ -89,19 +89,24 @@
     "        # nn.Module子类的函数必须在构造函数中执行父类的构造函数\n",
     "        super(Net, self).__init__()\n",
     "        \n",
-    "        # 卷积层 '1'表示输入图片为单通道, '6'表示输出通道数，'5'表示卷积核为3*3\n",
+    "        # 卷积层 '1'表示输入图片为单通道, '6'表示输出通道数，'3'表示卷积核为3*3\n",
     "        self.conv1 = nn.Conv2d(1, 6, 3) \n",
-    "        #线性层，输入84个特征，输出10个特征\n",
-    "        self.fc1   = nn.Linear(1350, 10)\n",
-    "    #正向传播\n",
+    "        #线性层，输入1350个特征，输出10个特征\n",
+    "        self.fc1   = nn.Linear(1350, 10)  #这里的1350是如何计算的呢？这就要看后面的forward函数\n",
+    "    #正向传播 \n",
     "    def forward(self, x): \n",
+    "        print(x.size()) # 结果：[1, 1, 32, 32]\n",
     "        # 卷积 -> 激活 -> 池化 \n",
-    "        x = self.conv1(x)\n",
+    "        x = self.conv1(x) #根据卷积的尺寸计算公式，计算结果是30，具体计算公式后面第二张第四节 卷积神经网络 有详细介绍。\n",
     "        x = F.relu(x)\n",
-    "        x = F.max_pool2d(x, (2, 2))\n",
+    "        print(x.size()) # 结果：[1, 6, 30, 30]\n",
+    "        x = F.max_pool2d(x, (2, 2)) #我们使用池化层，计算结果是15\n",
     "        x = F.relu(x)\n",
+    "        print(x.size()) # 结果：[1, 6, 15, 15]\n",
     "        # reshape，‘-1’表示自适应\n",
+    "        #这里做的就是压扁的操作 就是把后面的[1, 6, 15, 15]压扁，变为 [1, 1350]\n",
     "        x = x.view(x.size()[0], -1) \n",
+    "        print(x.size()) # 这里就是fc1层的的输入1350 \n",
     "        x = self.fc1(x)        \n",
     "        return x\n",
     "\n",
@@ -128,48 +133,54 @@
      "output_type": "stream",
      "text": [
       "Parameter containing:\n",
-      "tensor([[[[-0.2569,  0.3030, -0.2508],\n",
-      "          [ 0.2527,  0.3013, -0.1692],\n",
-      "          [ 0.0445,  0.0929,  0.2674]]],\n",
+      "tensor([[[[ 0.2745,  0.2594,  0.0171],\n",
+      "          [ 0.0429,  0.3013, -0.0208],\n",
+      "          [ 0.1459, -0.3223,  0.1797]]],\n",
       "\n",
       "\n",
-      "        [[[-0.1670, -0.3166,  0.3315],\n",
-      "          [ 0.1171,  0.3244, -0.2757],\n",
-      "          [ 0.2158, -0.3002, -0.1742]]],\n",
+      "        [[[ 0.1847,  0.0227, -0.1919],\n",
+      "          [-0.0210, -0.1336, -0.2176],\n",
+      "          [-0.2164, -0.1244, -0.2428]]],\n",
       "\n",
       "\n",
-      "        [[[-0.1313,  0.2859,  0.1639],\n",
-      "          [-0.0260,  0.2024, -0.1361],\n",
-      "          [-0.1011, -0.1267,  0.2546]]],\n",
+      "        [[[ 0.1042, -0.0055, -0.2171],\n",
+      "          [ 0.3306, -0.2808,  0.2058],\n",
+      "          [ 0.2492,  0.2971,  0.2277]]],\n",
       "\n",
       "\n",
-      "        [[[-0.0267,  0.2839, -0.2581],\n",
-      "          [-0.2461, -0.0073,  0.3096],\n",
-      "          [ 0.2565, -0.2553,  0.3148]]],\n",
+      "        [[[ 0.2134, -0.0644, -0.3044],\n",
+      "          [ 0.0040,  0.0828, -0.2093],\n",
+      "          [ 0.0204,  0.1065,  0.1168]]],\n",
       "\n",
       "\n",
-      "        [[[ 0.0848, -0.3026, -0.2878],\n",
-      "          [ 0.1124,  0.0947, -0.3182],\n",
-      "          [-0.1941, -0.2659,  0.1424]]],\n",
+      "        [[[ 0.1651, -0.2244,  0.3072],\n",
+      "          [-0.2301,  0.2443, -0.2340],\n",
+      "          [ 0.0685,  0.1026,  0.1754]]],\n",
       "\n",
       "\n",
-      "        [[[-0.0537,  0.0605, -0.2139],\n",
-      "          [ 0.2403, -0.1542,  0.0416],\n",
-      "          [ 0.0483,  0.1220, -0.1305]]]], requires_grad=True)\n",
+      "        [[[ 0.1691, -0.0790,  0.2617],\n",
+      "          [ 0.1956,  0.1477,  0.0877],\n",
+      "          [ 0.0538, -0.3091,  0.2030]]]], requires_grad=True)\n",
       "Parameter containing:\n",
-      "tensor([ 0.3156, -0.1656, -0.0010, -0.1745,  0.0580,  0.0558], requires_grad=True)\n",
+      "tensor([ 0.2355,  0.2949, -0.1283, -0.0848,  0.2027, -0.3331],\n",
+      "       requires_grad=True)\n",
       "Parameter containing:\n",
-      "tensor([[-0.0126,  0.0179,  0.0082,  ...,  0.0023,  0.0091, -0.0069],\n",
-      "        [ 0.0142,  0.0079,  0.0038,  ...,  0.0081, -0.0236,  0.0226],\n",
-      "        [-0.0068,  0.0093,  0.0153,  ..., -0.0085, -0.0012, -0.0122],\n",
+      "tensor([[ 2.0555e-02, -2.1445e-02, -1.7981e-02,  ..., -2.3864e-02,\n",
+      "          8.5149e-03, -6.2071e-04],\n",
+      "        [-1.1755e-02,  1.0010e-02,  2.1978e-02,  ...,  1.8433e-02,\n",
+      "          7.1362e-03, -4.0951e-03],\n",
+      "        [ 1.6187e-02,  2.1623e-02,  1.1840e-02,  ...,  5.7059e-03,\n",
+      "         -2.7165e-02,  1.3463e-03],\n",
       "        ...,\n",
-      "        [-0.0071,  0.0234, -0.0262,  ..., -0.0010, -0.0241, -0.0068],\n",
-      "        [ 0.0203, -0.0004,  0.0267,  ..., -0.0173,  0.0022, -0.0237],\n",
-      "        [ 0.0247,  0.0200, -0.0201,  ...,  0.0081,  0.0236,  0.0140]],\n",
-      "       requires_grad=True)\n",
+      "        [-3.2552e-03,  1.7277e-02, -1.4907e-02,  ...,  7.4232e-03,\n",
+      "         -2.7188e-02, -4.6431e-03],\n",
+      "        [-1.9786e-02, -3.7382e-03,  1.2259e-02,  ...,  3.2471e-03,\n",
+      "         -1.2375e-02, -1.6372e-02],\n",
+      "        [-8.2350e-03,  4.1301e-03, -1.9192e-03,  ..., -2.3119e-05,\n",
+      "          2.0167e-03,  1.9528e-02]], requires_grad=True)\n",
       "Parameter containing:\n",
-      "tensor([ 0.0198, -0.0144, -0.0156, -0.0073,  0.0185, -0.0177, -0.0012, -0.0125,\n",
-      "        -0.0136,  0.0125], requires_grad=True)\n"
+      "tensor([ 0.0162, -0.0146, -0.0218,  0.0212, -0.0119, -0.0142, -0.0079,  0.0171,\n",
+      "         0.0205,  0.0164], requires_grad=True)\n"
      ]
     }
    ],
@@ -218,6 +229,16 @@
    "execution_count": 6,
    "metadata": {},
    "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "torch.Size([1, 1, 32, 32])\n",
+      "torch.Size([1, 6, 30, 30])\n",
+      "torch.Size([1, 6, 15, 15])\n",
+      "torch.Size([1, 1350])\n"
+     ]
+    },
     {
      "data": {
       "text/plain": [
@@ -230,11 +251,31 @@
     }
    ],
    "source": [
-    "input = torch.randn(1, 1, 32, 32)\n",
+    "input = torch.randn(1, 1, 32, 32) # 这里的对应前面fforward的输入是32\n",
     "out = net(input)\n",
     "out.size()"
    ]
   },
+  {
+   "cell_type": "code",
+   "execution_count": 7,
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "torch.Size([1, 1, 32, 32])"
+      ]
+     },
+     "execution_count": 7,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "input.size()"
+   ]
+  },
   {
    "cell_type": "markdown",
    "metadata": {},
@@ -244,7 +285,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 7,
+   "execution_count": 8,
    "metadata": {},
    "outputs": [],
    "source": [
@@ -271,14 +312,14 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 8,
+   "execution_count": 9,
    "metadata": {},
    "outputs": [
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "29.04529571533203\n"
+      "28.92203712463379\n"
      ]
     }
    ],
@@ -304,7 +345,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 9,
+   "execution_count": 10,
    "metadata": {},
    "outputs": [],
    "source": [
@@ -313,11 +354,22 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 10,
+   "execution_count": 11,
    "metadata": {},
-   "outputs": [],
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "torch.Size([1, 1, 32, 32])\n",
+      "torch.Size([1, 6, 30, 30])\n",
+      "torch.Size([1, 6, 15, 15])\n",
+      "torch.Size([1, 1350])\n"
+     ]
+    }
+   ],
    "source": [
-    "out = net(input)\n",
+    "out = net(input) # 这里调用的时候会打印出我们在forword函数中打印的x的大小\n",
     "criterion = nn.MSELoss()\n",
     "loss = criterion(out, y)\n",
     "#新建一个优化器，SGD只需要要调整的参数和学习率\n",
@@ -334,15 +386,24 @@
    "cell_type": "markdown",
    "metadata": {},
    "source": [
-    "这样，神经网络的数据的一个完整的传播就已经通过PyTorch实现了，下面一章将介绍PyTorch提供的数据加载和处理工具，使用这些工具可以方便的处理所需要的数据"
+    "这样，神经网络的数据的一个完整的传播就已经通过PyTorch实现了，下面一章将介绍PyTorch提供的数据加载和处理工具，使用这些工具可以方便的处理所需要的数据。\n",
+    "\n",
+    "看完这节，大家可能对神经网络模型里面的一些参数的计算方式还有疑惑，这部分会在第二张第四节 卷积神经网络 有详细介绍，并且在第三章 第二节 MNIST数据集手写数字识别 的实践代码中有详细的注释说明。"
    ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": []
   }
  ],
  "metadata": {
   "kernelspec": {
-   "display_name": "Pytorch for Deeplearning",
+   "display_name": "pytorch 1.0",
    "language": "python",
-   "name": "pytorch"
+   "name": "pytorch1"
   },
   "language_info": {
    "codemirror_mode": {
@@ -354,7 +415,7 @@
    "name": "python",
    "nbconvert_exporter": "python",
    "pygments_lexer": "ipython3",
-   "version": "3.6.7"
+   "version": "3.6.6"
   }
  },
  "nbformat": 4,