fix

hipparic · Mar 18, 2019 · e628b39 · e628b39
1 parent e615b83
commit e628b39
Show file tree

Hide file tree

Showing 5 changed files with 18 additions and 18 deletions.
diff --git a/chapter2/2.1.1.pytorch-basics-tensor.ipynb b/chapter2/2.1.1.pytorch-basics-tensor.ipynb
@@ -672,7 +672,7 @@
     }
    ],
    "source": [
-    "# 使用[0,1]均匀分布随机初始化二维数组\n",
+    "# 使用[0,1]正态分布随机初始化二维数组\n",
     "rnd = torch.rand(5, 3)\n",
     "rnd"
    ]
@@ -871,9 +871,9 @@
  ],
  "metadata": {
   "kernelspec": {
-   "display_name": "pytorch 1.0",
+   "display_name": "Python 3",
    "language": "python",
-   "name": "pytorch1"
+   "name": "python3"
   },
   "language_info": {
    "codemirror_mode": {
@@ -885,7 +885,7 @@
    "name": "python",
    "nbconvert_exporter": "python",
    "pygments_lexer": "ipython3",
-   "version": "3.6.6"
+   "version": "3.6.7"
   }
  },
  "nbformat": 4,

diff --git a/chapter2/2.1.2-pytorch-basics-autograd.ipynb b/chapter2/2.1.2-pytorch-basics-autograd.ipynb
@@ -41,7 +41,7 @@
    "cell_type": "markdown",
    "metadata": {},
    "source": [
-    "在张量创建时，通过设置 requires_grad 标识为Ture来告诉Pytorch需要对该张量进行自动的求导，PyTorch回记录该张量的每一步操作历史并自动计算"
+    "在张量创建时，通过设置 requires_grad 标识为Ture来告诉Pytorch需要对该张量进行自动的求导，PyTorch会记录该张量的每一步操作历史并自动计算"
    ]
   },
   {
@@ -249,9 +249,9 @@
  ],
  "metadata": {
   "kernelspec": {
-   "display_name": "Pytorch for Deeplearning",
+   "display_name": "Python 3",
    "language": "python",
-   "name": "pytorch"
+   "name": "python3"
   },
   "language_info": {
    "codemirror_mode": {

diff --git a/chapter2/2.1.3-pytorch-basics-nerual-network.ipynb b/chapter2/2.1.3-pytorch-basics-nerual-network.ipynb
@@ -401,9 +401,9 @@
  ],
  "metadata": {
   "kernelspec": {
-   "display_name": "pytorch 1.0",
+   "display_name": "Python 3",
    "language": "python",
-   "name": "pytorch1"
+   "name": "python3"
   },
   "language_info": {
    "codemirror_mode": {
@@ -415,7 +415,7 @@
    "name": "python",
    "nbconvert_exporter": "python",
    "pygments_lexer": "ipython3",
-   "version": "3.6.6"
+   "version": "3.6.7"
   }
  },
  "nbformat": 4,

diff --git a/chapter2/2.1.4-pytorch-basics-data-lorder.ipynb b/chapter2/2.1.4-pytorch-basics-data-lorder.ipynb
@@ -336,9 +336,9 @@
  ],
  "metadata": {
   "kernelspec": {
-   "display_name": "Pytorch for Deeplearning",
+   "display_name": "Python 3",
    "language": "python",
-   "name": "pytorch"
+   "name": "python3"
   },
   "language_info": {
    "codemirror_mode": {

diff --git a/chapter2/2.2-deep-learning-basic-mathematics.ipynb b/chapter2/2.2-deep-learning-basic-mathematics.ipynb
@@ -223,7 +223,7 @@
    "cell_type": "markdown",
    "metadata": {},
    "source": [
-    "优化器我们选择最长见的优化方法 SGD，就是每一次迭代计算mini-batch的梯度，然后对参数进行更新，学习率0.01 ，优化器本章后面也会进行介绍"
+    "优化器我们选择最常见的优化方法 SGD，就是每一次迭代计算mini-batch的梯度，然后对参数进行更新，学习率0.01 ，优化器本章后面也会进行介绍"
    ]
   },
   {
@@ -330,9 +330,9 @@
     "    optim.zero_grad()\n",
     "    # 计算损失\n",
     "    loss = criterion(outputs, labels)\n",
-    "    # 反响传播\n",
+    "    # 反向传播\n",
     "    loss.backward()\n",
-    "    # 使用优化器默认方行优化\n",
+    "    # 使用优化器默认方法优化\n",
     "    optim.step()\n",
     "    if (i%100==0):\n",
     "        #每 100次打印一下损失函数，看看效果\n",
@@ -391,7 +391,7 @@
     }
    ],
    "source": [
-    "predicted =model.forward(torch.from_numpy(x_train)).data.numpy()\n",
+    "predicted = model.forward(torch.from_numpy(x_train)).data.numpy()\n",
     "plt.plot(x_train, y_train, 'go', label = 'data', alpha = 0.3)\n",
     "plt.plot(x_train, predicted, label = 'predicted', alpha = 1)\n",
     "plt.legend()\n",
@@ -676,9 +676,9 @@
  ],
  "metadata": {
   "kernelspec": {
-   "display_name": "pytorch 1.0",
+   "display_name": "Python 3",
    "language": "python",
-   "name": "pytorch1"
+   "name": "python3"
   },
   "language_info": {
    "codemirror_mode": {