Update 3_neural_networks_tutorial.ipynb

Author: syliudf

chapter1/3_neural_networks_tutorial.ipynb

@@ -51,7 +51,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 2,
+   "execution_count": 1,
    "metadata": {},
    "outputs": [
     {
@@ -124,7 +124,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 4,
+   "execution_count": 2,
    "metadata": {},
    "outputs": [
     {
@@ -153,15 +153,15 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 5,
+   "execution_count": 6,
    "metadata": {},
    "outputs": [
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "tensor([[-0.0204, -0.0268, -0.0829,  0.1420, -0.0192,  0.1848,  0.0723, -0.0393,\n",
-      "         -0.0275,  0.0867]], grad_fn=<ThAddmmBackward>)\n"
+      "tensor([[ 0.1120,  0.0713,  0.1014, -0.0696, -0.1210,  0.0084, -0.0206,  0.1366,\n",
+      "         -0.0455, -0.0036]], grad_fn=<AddmmBackward>)\n"
      ]
     }
    ],
@@ -181,7 +181,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 6,
+   "execution_count": 7,
    "metadata": {},
    "outputs": [],
    "source": [
@@ -232,14 +232,14 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 7,
+   "execution_count": 8,
    "metadata": {},
    "outputs": [
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "tensor(1.3172, grad_fn=<MseLossBackward>)\n"
+      "tensor(0.8109, grad_fn=<MseLossBackward>)\n"
      ]
     }
    ],
@@ -257,9 +257,8 @@
    "cell_type": "markdown",
    "metadata": {},
    "source": [
-    "Now, if you follow ``loss`` in the backward direction, using its\n",
-    "``.grad_fn`` attribute, you will see a graph of computations that looks\n",
-    "like this:\n",
+    "现在，如果在反向过程中跟随``loss`` ， 使用它的\n",
+    "``.grad_fn`` 属性，将看到如下所示的计算图。\n",
     "\n",
     "::\n",
     "\n",
@@ -268,19 +267,29 @@
     "          -> MSELoss\n",
     "          -> loss\n",
     "\n",
-    "So, when we call ``loss.backward()``, the whole graph is differentiated\n",
-    "w.r.t. the loss, and all Tensors in the graph that has ``requires_grad=True``\n",
-    "will have their ``.grad`` Tensor accumulated with the gradient.\n",
+    "所以，当我们调用 ``loss.backward()``时,整张计算图都会\n",
+    "根据loss进行微分，而且图中所有设置为``requires_grad=True``的张量\n",
+    "将会拥有一个随着梯度累积的``.grad`` 张量。\n",
     "\n",
-    "For illustration, let us follow a few steps backward:\n",
+    "为了说明，让我们向后退几步:\n",
     "\n"
    ]
   },
   {
    "cell_type": "code",
-   "execution_count": null,
+   "execution_count": 9,
    "metadata": {},
-   "outputs": [],
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "<MseLossBackward object at 0x7f3b49fe2470>\n",
+      "<AddmmBackward object at 0x7f3bb05f17f0>\n",
+      "<AccumulateGrad object at 0x7f3b4a3c34e0>\n"
+     ]
+    }
+   ],
    "source": [
     "print(loss.grad_fn)  # MSELoss\n",
     "print(loss.grad_fn.next_functions[0][0])  # Linear\n",
@@ -304,7 +313,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 8,
+   "execution_count": 10,
    "metadata": {},
    "outputs": [
     {
@@ -314,7 +323,7 @@
       "conv1.bias.grad before backward\n",
       "tensor([0., 0., 0., 0., 0., 0.])\n",
       "conv1.bias.grad after backward\n",
-      "tensor([ 0.0074, -0.0249, -0.0107,  0.0326, -0.0017, -0.0059])\n"
+      "tensor([ 0.0051,  0.0042,  0.0026,  0.0152, -0.0040, -0.0036])\n"
      ]
     }
    ],
@@ -364,7 +373,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 9,
+   "execution_count": 11,
    "metadata": {},
    "outputs": [],
    "source": [
@@ -385,11 +394,10 @@
    "cell_type": "markdown",
    "metadata": {},
    "source": [
-    ".. Note::\n",
+    ".. 注意::\n",
     "    \n",
-    "      Observe how gradient buffers had to be manually set to zero using\n",
-    "      ``optimizer.zero_grad()``. This is because gradients are accumulated\n",
-    "      as explained in `Backprop`_ section.\n",
+    "      观察如何使用``optimizer.zero_grad()``手动将梯度缓冲区设置为零。\n",
+    "      这是因为梯度是按Backprop部分中的说明累积的。\n",
     "\n"
    ]
   },
@@ -403,9 +411,9 @@
  ],
  "metadata": {
   "kernelspec": {
-   "display_name": "Pytorch for Deeplearning",
+   "display_name": "Python 3",
    "language": "python",
-   "name": "pytorch"
+   "name": "python3"
   },
   "language_info": {
    "codemirror_mode": {
@@ -417,7 +425,7 @@
    "name": "python",
    "nbconvert_exporter": "python",
    "pygments_lexer": "ipython3",
-   "version": "3.6.7"
+   "version": "3.7.3"
   }
  },
  "nbformat": 4,