diff --git a/7_deep_learning/1_CNN/01-basic_conv.ipynb b/7_deep_learning/1_CNN/01-basic_conv.ipynb
index 15cb217..06bc20c 100644
--- a/7_deep_learning/1_CNN/01-basic_conv.ipynb
+++ b/7_deep_learning/1_CNN/01-basic_conv.ipynb
@@ -296,6 +296,15 @@
    "source": [
     "以上介绍了如何在 PyTorch 中使用卷积网络中的卷积模块和池化模块，接下来讲解卷积网络中几个非常著名的网络结构"
    ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "## 3. Stride，Padding\n",
+    "\n",
+    "FIXME：增加这部分的解释"
+   ]
   }
  ],
  "metadata": {
diff --git a/7_deep_learning/1_CNN/04-vgg.ipynb b/7_deep_learning/1_CNN/04-vgg.ipynb
index 83c196b..cba74ee 100644
--- a/7_deep_learning/1_CNN/04-vgg.ipynb
+++ b/7_deep_learning/1_CNN/04-vgg.ipynb
@@ -47,7 +47,7 @@
    "source": [
     "VGG网络的特点：\n",
     "* 小卷积核和连续的卷积层: VGG中使用的都是3×3卷积核，并且使用了连续多个卷积层。这样做的好处主要有，\n",
-    "    - 使用连续的的多个小卷积核(3×3)，来代替一个大的卷积核（例如(5×5)。使用小的卷积核的问题是，其感受野必然变小。所以，VGG中就使用连续的3×3卷积核，来增大感受野。VGG认为2个连续的3×3卷积核能够替代一个5×5卷积核，三个连续的3×3能够代替一个7×7。\n",
+    "    - 使用连续的的多个小卷积核(3×3)，来代替一个大的卷积核，例如(5×5)。使用小的卷积核的问题是，其感受野必然变小。所以，VGG中就使用连续的3×3卷积核，来增大感受野。VGG认为2个连续的3×3卷积核能够替代一个5×5卷积核，三个连续的3×3能够代替一个7×7。\n",
     "    - 小卷积核的参数较少。3个3×3的卷积核参数为3×3×3=27，而一个7×7的卷积核参数为7×7=49\n",
     "    - 由于每个卷积层都有一个非线性的激活函数，多个卷积层增加了非线性映射。\n",
     "* 小池化核，使用的是2×2\n",
@@ -521,7 +521,7 @@
    "name": "python",
    "nbconvert_exporter": "python",
    "pygments_lexer": "ipython3",
-   "version": "3.8.12"
+   "version": "3.7.9"
   }
  },
  "nbformat": 4,
diff --git a/7_deep_learning/1_CNN/05-googlenet.ipynb b/7_deep_learning/1_CNN/05-googlenet.ipynb
index c39fb9e..607e4c1 100644
--- a/7_deep_learning/1_CNN/05-googlenet.ipynb
+++ b/7_deep_learning/1_CNN/05-googlenet.ipynb
@@ -178,19 +178,19 @@
     "        \n",
     "        self.block1 = nn.Sequential(\n",
     "            Conv_ReLU(in_channel, out_channel=64, kernel=7, stride=2, padding=3),\n",
-    "            nn.MaxPool2d(3, 2)\n",
+    "            nn.MaxPool2d(kernel_size=3, stride=2)\n",
     "        )\n",
     "        \n",
     "        self.block2 = nn.Sequential(\n",
     "            Conv_ReLU(64, 64, kernel=1),\n",
     "            Conv_ReLU(64, 192, kernel=3, padding=1),\n",
-    "            nn.MaxPool2d(3, 2)\n",
+    "            nn.MaxPool2d(kernel_size=3, stride=2)\n",
     "        )\n",
     "        \n",
     "        self.block3 = nn.Sequential(\n",
     "            Inception(192, 64, 96, 128, 16, 32, 32),\n",
     "            Inception(256, 128, 128, 192, 32, 96, 64),\n",
-    "            nn.MaxPool2d(3, 2)\n",
+    "            nn.MaxPool2d(kernel_size=3, stride=2)\n",
     "        )\n",
     "        \n",
     "        self.block4 = nn.Sequential(\n",
@@ -199,13 +199,13 @@
     "            Inception(512, 128, 128, 256, 24, 64, 64),\n",
     "            Inception(512, 112, 144, 288, 32, 64, 64),\n",
     "            Inception(528, 256, 160, 320, 32, 128, 128),\n",
-    "            nn.MaxPool2d(3, 2)\n",
+    "            nn.MaxPool2d(kernel_size=3, stride=2)\n",
     "        )\n",
     "        \n",
     "        self.block5 = nn.Sequential(\n",
     "            Inception(832, 256, 160, 320, 32, 128, 128),\n",
     "            Inception(832, 384, 182, 384, 48, 128, 128),\n",
-    "            nn.AvgPool2d(2)\n",
+    "            nn.AvgPool2d(kernel_size=2)\n",
     "        )\n",
     "        \n",
     "        self.classifier = nn.Linear(1024, num_classes)\n",
@@ -214,18 +214,23 @@
     "        x = self.block1(x)\n",
     "        if self.verbose:\n",
     "            print('block 1 output: {}'.format(x.shape))\n",
+    "            \n",
     "        x = self.block2(x)\n",
     "        if self.verbose:\n",
     "            print('block 2 output: {}'.format(x.shape))\n",
+    "            \n",
     "        x = self.block3(x)\n",
     "        if self.verbose:\n",
     "            print('block 3 output: {}'.format(x.shape))\n",
+    "            \n",
     "        x = self.block4(x)\n",
     "        if self.verbose:\n",
     "            print('block 4 output: {}'.format(x.shape))\n",
+    "            \n",
     "        x = self.block5(x)\n",
     "        if self.verbose:\n",
     "            print('block 5 output: {}'.format(x.shape))\n",
+    "            \n",
     "        x = x.view(x.shape[0], -1)\n",
     "        x = self.classifier(x)\n",
     "        return x"
@@ -442,7 +447,7 @@
    "name": "python",
    "nbconvert_exporter": "python",
    "pygments_lexer": "ipython3",
-   "version": "3.8.12"
+   "version": "3.7.9"
   }
  },
  "nbformat": 4,
diff --git a/7_deep_learning/1_CNN/06-resnet.ipynb b/7_deep_learning/1_CNN/06-resnet.ipynb
index 00160a2..f4705a9 100644
--- a/7_deep_learning/1_CNN/06-resnet.ipynb
+++ b/7_deep_learning/1_CNN/06-resnet.ipynb
@@ -441,7 +441,7 @@
    "name": "python",
    "nbconvert_exporter": "python",
    "pygments_lexer": "ipython3",
-   "version": "3.8.12"
+   "version": "3.7.9"
   }
  },
  "nbformat": 4,
diff --git a/7_deep_learning/1_CNN/07-densenet.ipynb b/7_deep_learning/1_CNN/07-densenet.ipynb
index a5ea209..95e13a6 100644
--- a/7_deep_learning/1_CNN/07-densenet.ipynb
+++ b/7_deep_learning/1_CNN/07-densenet.ipynb
@@ -458,7 +458,7 @@
    "name": "python",
    "nbconvert_exporter": "python",
    "pygments_lexer": "ipython3",
-   "version": "3.8.12"
+   "version": "3.7.9"
   }
  },
  "nbformat": 4,
diff --git a/7_deep_learning/2_RNN/pytorch-rnn.ipynb b/7_deep_learning/2_RNN/pytorch-rnn.ipynb
index 79fa800..e0a812e 100644
--- a/7_deep_learning/2_RNN/pytorch-rnn.ipynb
+++ b/7_deep_learning/2_RNN/pytorch-rnn.ipynb
@@ -813,7 +813,7 @@
    "name": "python",
    "nbconvert_exporter": "python",
    "pygments_lexer": "ipython3",
-   "version": "3.6.8"
+   "version": "3.7.9"
   }
  },
  "nbformat": 4,
diff --git a/7_deep_learning/2_RNN/rnn-for-image.ipynb b/7_deep_learning/2_RNN/rnn-for-image.ipynb
index 26e6f3a..379af8d 100644
--- a/7_deep_learning/2_RNN/rnn-for-image.ipynb
+++ b/7_deep_learning/2_RNN/rnn-for-image.ipynb
@@ -183,7 +183,7 @@
    "name": "python",
    "nbconvert_exporter": "python",
    "pygments_lexer": "ipython3",
-   "version": "3.6.8"
+   "version": "3.7.9"
   }
  },
  "nbformat": 4,