Update autograd description

6_pytorch/0_basic/2-autograd.ipynb

@@ -10,7 +10,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 2,
+   "execution_count": 1,
    "metadata": {},
    "outputs": [],
    "source": [
@@ -28,7 +28,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 3,
+   "execution_count": 2,
    "metadata": {},
    "outputs": [
     {
@@ -67,7 +67,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 4,
+   "execution_count": 3,
    "metadata": {},
    "outputs": [
     {
@@ -93,7 +93,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 25,
+   "execution_count": 4,
    "metadata": {},
    "outputs": [
     {
@@ -115,7 +115,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 26,
+   "execution_count": 5,
    "metadata": {},
    "outputs": [],
    "source": [
@@ -127,12 +127,12 @@
    "cell_type": "markdown",
    "metadata": {},
    "source": [
-    "如果你对矩阵乘法不熟悉，可以查看下面的[网址进行复习](https://baike.baidu.com/item/%E7%9F%A9%E9%98%B5%E4%B9%98%E6%B3%95/5446029?fr=aladdin)"
+    "如果你对矩阵乘法不熟悉，可以查看下面的[《矩阵乘法说明》](https://baike.baidu.com/item/%E7%9F%A9%E9%98%B5%E4%B9%98%E6%B3%95/5446029?fr=aladdin)进行复习"
    ]
   },
   {
    "cell_type": "code",
-   "execution_count": 27,
+   "execution_count": 6,
    "metadata": {},
    "outputs": [
     {
@@ -326,7 +326,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 20,
+   "execution_count": 16,
    "metadata": {},
    "outputs": [
     {
@@ -345,7 +345,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 21,
+   "execution_count": 17,
    "metadata": {},
    "outputs": [],
    "source": [
@@ -354,7 +354,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 22,
+   "execution_count": 18,
    "metadata": {},
    "outputs": [
     {
@@ -371,7 +371,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 23,
+   "execution_count": 19,
    "metadata": {},
    "outputs": [],
    "source": [
@@ -413,7 +413,7 @@
    "cell_type": "markdown",
    "metadata": {},
    "source": [
-    "## 4 练习题\n",
+    "## 4. 练习题\n",
     "\n",
     "定义\n",
     "\n",
@@ -462,7 +462,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 29,
+   "execution_count": 25,
    "metadata": {},
    "outputs": [],
    "source": [
@@ -475,18 +475,31 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 18,
+   "execution_count": 29,
    "metadata": {},
-   "outputs": [],
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "tensor([2., 3., 4.], requires_grad=True)\n",
+      "tensor([2., 0., 0.])\n"
+     ]
+    }
+   ],
    "source": [
-    "#k.backward(torch.ones_like(k)) \n",
-    "#print(x.grad)\n",
-    "# 和上一个的区别在于该算法是求得导数和，并不是分布求解。"
+    "# demo to show how to use `.backward`\n",
+    "x = torch.tensor([2,3,4], dtype=torch.float, requires_grad=True)\n",
+    "print(x)\n",
+    "y = x*2\n",
+    "\n",
+    "y.backward(torch.tensor([1, 0, 0], dtype=torch.float))\n",
+    "print(x.grad)"
    ]
   },
   {
    "cell_type": "code",
-   "execution_count": 30,
+   "execution_count": 26,
    "metadata": {},
    "outputs": [
     {
@@ -500,6 +513,7 @@
     }
    ],
    "source": [
+    "# calc k_0 -> (x_0, x_1)\n",
     "j = torch.zeros(2, 2)\n",
     "k.backward(torch.FloatTensor([1, 0]), retain_graph=True)\n",
     "print(k)\n",
@@ -508,6 +522,7 @@
     "\n",
     "x.grad.data.zero_() # 归零之前求得的梯度\n",
     "\n",
+    "# calc k_1 -> (x_0, x_1)\n",
     "k.backward(torch.FloatTensor([0, 1]))\n",
     "j[1] = x.grad.data\n",
     "print(x.grad.data)\n"
@@ -515,24 +530,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 31,
-   "metadata": {},
-   "outputs": [
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      "tensor([13., 13.], grad_fn=<CopySlices>)\n"
-     ]
-    }
-   ],
-   "source": [
-    "print(k)"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 32,
+   "execution_count": 30,
    "metadata": {},
    "outputs": [
     {

6_pytorch/2_CNN/1-basic_conv.ipynb

@@ -355,7 +355,7 @@
    "name": "python",
    "nbconvert_exporter": "python",
    "pygments_lexer": "ipython3",
-   "version": "3.6.9"
+   "version": "3.7.9"
   }
  },
  "nbformat": 4,

6_pytorch/2_CNN/2-batch-normalization.ipynb

@@ -572,7 +572,7 @@
    "name": "python",
    "nbconvert_exporter": "python",
    "pygments_lexer": "ipython3",
-   "version": "3.6.9"
+   "version": "3.7.9"
   }
  },
  "nbformat": 4,

README.md

@@ -4,7 +4,7 @@
 
 由于**本课程需要大量的编程练习才能取得比较好的学习效果**，因此需要认真去完成[《机器学习-作业和报告》](https://gitee.com/pi-lab/machinelearning_homework)，写作业的过程可以查阅网上的资料，但是不能直接照抄，需要自己独立思考并独立写出代码。
 
-为了让大家更好的自学本课程，课程讲座的视频会陆续上传到[《B站 - 机器学习》](https://www.bilibili.com/video/BV1oZ4y1N7ei/)，欢迎大家观看学习。
+为了让大家更好的自学本课程，课程讲座的视频在[《B站 - 机器学习》](https://www.bilibili.com/video/BV1oZ4y1N7ei/)，欢迎大家观看学习。
 
 ![Machine Learning Cover](images/machine_learning_1.png)