Improve some contents

4_logistic_regression/2-Logistic_regression.ipynb

@@ -181,7 +181,9 @@
   {
    "cell_type": "code",
    "execution_count": 2,
-   "metadata": {},
+   "metadata": {
+    "collapsed": true
+   },
    "outputs": [],
    "source": [
     "%matplotlib inline\n",
@@ -234,7 +236,9 @@
   {
    "cell_type": "code",
    "execution_count": 4,
-   "metadata": {},
+   "metadata": {
+    "collapsed": true
+   },
    "outputs": [],
    "source": [
     "def plot_decision_boundary(predict_func, data, label, figName=None):\n",
@@ -263,7 +267,9 @@
   {
    "cell_type": "code",
    "execution_count": 7,
-   "metadata": {},
+   "metadata": {
+    "collapsed": true
+   },
    "outputs": [],
    "source": [
     "\n",
@@ -780,7 +786,7 @@
    "name": "python",
    "nbconvert_exporter": "python",
    "pygments_lexer": "ipython3",
-   "version": "3.7.9"
+   "version": "3.5.4"
   }
  },
  "nbformat": 4,

7_deep_learning/1_CNN/03-AlexNet.ipynb

@@ -13,7 +13,9 @@
   {
    "cell_type": "code",
    "execution_count": 3,
-   "metadata": {},
+   "metadata": {
+    "collapsed": true
+   },
    "outputs": [],
    "source": [
     "import torch.nn as nn\n",
@@ -97,7 +99,9 @@
   {
    "cell_type": "code",
    "execution_count": 5,
-   "metadata": {},
+   "metadata": {
+    "collapsed": true
+   },
    "outputs": [],
    "source": [
     "from torchvision.datasets import CIFAR10\n",
@@ -216,7 +220,9 @@
   {
    "cell_type": "code",
    "execution_count": null,
-   "metadata": {},
+   "metadata": {
+    "collapsed": true
+   },
    "outputs": [],
    "source": [
     "# save raw data\n",
@@ -241,7 +247,7 @@
    "name": "python",
    "nbconvert_exporter": "python",
    "pygments_lexer": "ipython3",
-   "version": "3.7.9"
+   "version": "3.5.4"
   }
  },
  "nbformat": 4,

7_deep_learning/1_CNN/05-googlenet.ipynb

@@ -42,7 +42,8 @@
     "ExecuteTime": {
      "end_time": "2017-12-22T12:51:05.427292Z",
      "start_time": "2017-12-22T12:51:04.924747Z"
-    }
+    },
+    "collapsed": true
    },
    "outputs": [],
    "source": [
@@ -61,7 +62,8 @@
     "ExecuteTime": {
      "end_time": "2017-12-22T12:51:08.890890Z",
      "start_time": "2017-12-22T12:51:08.876313Z"
-    }
+    },
+    "collapsed": true
    },
    "outputs": [],
    "source": [
@@ -82,7 +84,8 @@
     "ExecuteTime": {
      "end_time": "2017-12-22T12:51:09.671474Z",
      "start_time": "2017-12-22T12:51:09.587337Z"
-    }
+    },
+    "collapsed": true
    },
    "outputs": [],
    "source": [
@@ -167,7 +170,8 @@
     "ExecuteTime": {
      "end_time": "2017-12-22T12:51:13.149380Z",
      "start_time": "2017-12-22T12:51:12.934110Z"
-    }
+    },
+    "collapsed": true
    },
    "outputs": [],
    "source": [
@@ -280,7 +284,8 @@
     "ExecuteTime": {
      "end_time": "2017-12-22T12:51:16.387778Z",
      "start_time": "2017-12-22T12:51:15.121350Z"
-    }
+    },
+    "collapsed": true
    },
    "outputs": [],
    "source": [
@@ -447,7 +452,7 @@
    "name": "python",
    "nbconvert_exporter": "python",
    "pygments_lexer": "ipython3",
-   "version": "3.7.9"
+   "version": "3.5.4"
   }
  },
  "nbformat": 4,

7_deep_learning/1_CNN/07-densenet.ipynb

@@ -45,7 +45,8 @@
     "ExecuteTime": {
      "end_time": "2017-12-22T15:38:31.113030Z",
      "start_time": "2017-12-22T15:38:30.612922Z"
-    }
+    },
+    "collapsed": true
    },
    "outputs": [],
    "source": [
@@ -71,7 +72,8 @@
     "ExecuteTime": {
      "end_time": "2017-12-22T15:38:31.121249Z",
      "start_time": "2017-12-22T15:38:31.115369Z"
-    }
+    },
+    "collapsed": true
    },
    "outputs": [],
    "source": [
@@ -98,7 +100,8 @@
     "ExecuteTime": {
      "end_time": "2017-12-22T15:38:31.145274Z",
      "start_time": "2017-12-22T15:38:31.123363Z"
-    }
+    },
+    "collapsed": true
    },
    "outputs": [],
    "source": [
@@ -168,11 +171,12 @@
     "ExecuteTime": {
      "end_time": "2017-12-22T15:38:31.222120Z",
      "start_time": "2017-12-22T15:38:31.215770Z"
-    }
+    },
+    "collapsed": true
    },
    "outputs": [],
    "source": [
-    "def transition(in_channel, out_channel):\n",
+    "def Transition_Block(in_channel, out_channel):\n",
     "    trans_layer = nn.Sequential(\n",
     "        nn.BatchNorm2d(in_channel),\n",
     "        nn.ReLU(True),\n",
@@ -209,7 +213,7 @@
     }
    ],
    "source": [
-    "test_net = transition(3, 12)\n",
+    "test_net = Transition_Block(3, 12)\n",
     "test_x = Variable(torch.zeros(1, 3, 96, 96))\n",
     "print('input shape: {} x {} x {}'.format(test_x.shape[1], test_x.shape[2], test_x.shape[3]))\n",
     "test_y = test_net(test_x)\n",
@@ -232,7 +236,8 @@
     "ExecuteTime": {
      "end_time": "2017-12-22T15:38:31.318822Z",
      "start_time": "2017-12-22T15:38:31.236857Z"
-    }
+    },
+    "collapsed": true
    },
    "outputs": [],
    "source": [
@@ -240,10 +245,11 @@
     "    def __init__(self, in_channel, num_classes, growth_rate=32, block_layers=[6, 12, 24, 16]):\n",
     "        super(DenseNet, self).__init__()\n",
     "        self.block1 = nn.Sequential(\n",
-    "            nn.Conv2d(in_channel, 64, 7, 2, 3),\n",
+    "            nn.Conv2d(in_channels=in_channel, out_channels=64, \n",
+    "                      kernel_size=7, stride=2, padding=3),\n",
     "            nn.BatchNorm2d(64),\n",
     "            nn.ReLU(True),\n",
-    "            nn.MaxPool2d(3, 2, padding=1)\n",
+    "            nn.MaxPool2d(kernel_size=3, stride=2, padding=1)\n",
     "        )\n",
     "        \n",
     "        channels = 64\n",
@@ -252,7 +258,7 @@
     "            block.append(Dense_Block(channels, growth_rate, layers))\n",
     "            channels += layers * growth_rate\n",
     "            if i != len(block_layers) - 1:\n",
-    "                block.append(transition(channels, channels // 2)) # 通过 transition 层将大小减半，通道数减半\n",
+    "                block.append(Transition_Block(channels, channels // 2)) # 通过 transition 层将大小减半，通道数减半\n",
     "                channels = channels // 2\n",
     "        \n",
     "        self.block2 = nn.Sequential(*block)\n",
@@ -303,7 +309,8 @@
     "ExecuteTime": {
      "end_time": "2017-12-22T15:38:32.894729Z",
      "start_time": "2017-12-22T15:38:31.656356Z"
-    }
+    },
+    "collapsed": true
    },
    "outputs": [],
    "source": [
@@ -458,7 +465,7 @@
    "name": "python",
    "nbconvert_exporter": "python",
    "pygments_lexer": "ipython3",
-   "version": "3.7.9"
+   "version": "3.5.4"
   }
  },
  "nbformat": 4,

7_deep_learning/1_CNN/08-batch-normalization.ipynb

@@ -59,7 +59,7 @@
    "source": [
     "* 第一和第二个公式计算出一个 batch 中数据的均值和方差\n",
     "* 第三个公式对 batch 中的每个数据点做标准化，$\\epsilon$ 是为了计算稳定引入的一个小的常数，通常取 $10^{-5}$\n",
-    "* 最后利用权重修正得到最后的输出结果，其中 $\\gamma$ $\\beta$是权值变换参数，也是网络参数在训练过程一起学习\n",
+    "* 最后利用权重修正得到最后的输出结果，其中 $\\gamma$，$\\beta$是权值变换参数，也是网络参数在训练过程一起学习\n",
     "\n",
     "下面演示一维的情况，也就是神经网络中的情况"
    ]
@@ -427,6 +427,13 @@
     "下面我们在卷积网络下试用一下批标准化看看效果"
    ]
   },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "FIXME：设计一个更有说服力的例子"
+   ]
+  },
   {
    "cell_type": "code",
    "execution_count": null,
@@ -588,7 +595,7 @@
    "name": "python",
    "nbconvert_exporter": "python",
    "pygments_lexer": "ipython3",
-   "version": "3.7.9"
+   "version": "3.5.4"
   }
  },
  "nbformat": 4,

7_deep_learning/1_CNN/09-lr-decay.ipynb

@@ -267,7 +267,7 @@
     "    if epoch == 20:\n",
     "        set_learning_rate(optimizer, 0.01) # 20 次修改学习率为 0.01\n",
     "    elif epoch == 60:\n",
-    "        set_learning_rate(optimizer, 0.005) # 60 次修改学习率为 0.01\n",
+    "        set_learning_rate(optimizer, 0.005) # 60 次修改学习率为 0.005\n",
     "\n",
     "    train_loss = 0\n",
     "    net = net.train()\n",

7_deep_learning/1_CNN/10-regularization.ipynb

@@ -160,7 +160,7 @@
    "name": "python",
    "nbconvert_exporter": "python",
    "pygments_lexer": "ipython3",
-   "version": "3.7.9"
+   "version": "3.5.4"
   }
  },
  "nbformat": 4,

7_deep_learning/1_CNN/11-data-augumentation.ipynb

@@ -612,7 +612,7 @@
    "name": "python",
    "nbconvert_exporter": "python",
    "pygments_lexer": "ipython3",
-   "version": "3.7.9"
+   "version": "3.5.4"
   }
  },
  "nbformat": 4,