Revert "code change for 1.4.0rc"

This reverts commit 08e604cb.

chapter_computer-vision/image-augmentation.md

@@ -125,10 +125,11 @@ no_aug = gdata.vision.transforms.Compose([
 接下来我们定义一个辅助函数来方便读取图像并应用图像增广。Gluon的数据集提供的`transform_first`函数将图像增广应用在每个训练样本（图像和标签）的第一个元素，即图像之上。有关`DataLoader`的详细介绍，可参考更早的[“图像分类数据集（Fashion-MNIST）”](../chapter_deep-learning-basics/fashion-mnist.md)一节。
 
 ```{.python .input  n=34}
+num_workers = 0 if sys.platform.startswith('win32') else 4
 def load_cifar10(is_train, augs, batch_size):
     return gdata.DataLoader(
         gdata.vision.CIFAR10(train=is_train).transform_first(augs),
-        batch_size=batch_size, shuffle=is_train, num_workers=4)
+        batch_size=batch_size, shuffle=is_train, num_workers=num_workers)
 ```
 
 ### 使用多GPU训练模型

chapter_computer-vision/semantic-segmentation-and-dataset.md

@@ -177,10 +177,11 @@ voc_test = VOCSegDataset(False, crop_size, voc_dir, colormap2label)
 
 ```{.python .input  n=11}
 batch_size = 64
+num_workers = 0 if sys.platform.startswith('win32') else 4
 train_iter = gdata.DataLoader(voc_train, batch_size, shuffle=True,
-                              last_batch='discard', num_workers=4)
+                              last_batch='discard', num_workers=num_workers)
 test_iter = gdata.DataLoader(voc_test, batch_size, last_batch='discard',
-                             num_workers=4)
+                             num_workers=num_workers)
 ```
 
 打印第一个小批量的形状。不同于图像分类和目标识别，这里的标签是一个三维的数组。

chapter_convolutional-neural-networks/alexnet.md

@@ -106,12 +106,13 @@ def load_data_fashion_mnist(batch_size, resize=None, root=os.path.join(
     transformer = gdata.vision.transforms.Compose(transformer)
     mnist_train = gdata.vision.FashionMNIST(root=root, train=True)
     mnist_test = gdata.vision.FashionMNIST(root=root, train=False)
+    num_workers = 0 if sys.platform.startswith('win32') else 4
     train_iter = gdata.DataLoader(
         mnist_train.transform_first(transformer), batch_size, shuffle=True,
-        num_workers=4)
+        num_workers=num_workers)
     test_iter = gdata.DataLoader(
         mnist_test.transform_first(transformer), batch_size, shuffle=False,
-        num_workers=4)
+        num_workers=num_workers)
     return train_iter, test_iter
 
 batch_size = 128

chapter_deep-learning-basics/fashion-mnist.md

@@ -88,12 +88,17 @@ show_fashion_mnist(X, get_fashion_mnist_labels(y))
 ```{.python .input  n=28}
 batch_size = 256
 transformer = gdata.vision.transforms.ToTensor()
+if sys.platform.startswith('win'):
+    num_workers = 0  # 0 表示不用额外的进程来加速读取数据。
+else:
+    num_workers = 4
+
 train_iter = gdata.DataLoader(mnist_train.transform_first(transformer),
                               batch_size, shuffle=True,
-                              num_workers=4)
+                              num_workers=num_workers)
 test_iter = gdata.DataLoader(mnist_test.transform_first(transformer),
                              batch_size, shuffle=False,
-                             num_workers=4)
+                             num_workers=num_workers)
 ```
 
 我们将获取并读取Fashion-MNIST数据集的逻辑封装在`gluonbook.load_data_fashion_mnist`函数中供后面章节调用。该函数将返回`train_iter`和`test_iter`两个变量。随着本书内容的不断深入，我们会进一步改进该函数。它的完整实现将在[“深度卷积神经网络（AlexNet）”](../chapter_convolutional-neural-networks/alexnet.md)一节中描述。

chapter_deep-learning-computation/read-write.md

@@ -64,14 +64,14 @@ y = net(x)
 
 ```{.python .input}
 filename = 'mlp.params'
-net.save_parameters(filename)
+net.save_params(filename)
 ```
 
 接下来，我们再实例化一次定义好的多层感知机。跟随机初始化模型参数不同，我们在这里直接读取保存在文件里的参数。
 
 ```{.python .input  n=8}
 net2 = MLP()
-net2.load_parameters(filename)
+net2.load_params(filename)
 ```
 
 因为这两个实例都有同样的模型参数，那么对同一个输入`x`的计算结果将会是一样。我们来验证一下。

chapter_natural-language-processing/word2vec-gluon.md

@@ -6,7 +6,6 @@
 
 ```{.python .input  n=1}
 import collections
-import gluonbook as gb
 import math
 from mxnet import autograd, gluon, nd
 from mxnet.gluon import data as gdata, loss as gloss, nn
@@ -182,9 +181,10 @@ def batchify(data):
 
 ```{.python .input  n=14}
 batch_size = 512
+num_workers = 0 if sys.platform.startswith('win32') else 4
 dataset = gdata.ArrayDataset(all_centers, all_contexts, all_negatives)
 data_iter = gdata.DataLoader(dataset, batch_size, shuffle=True,
-                             batchify_fn=batchify, num_workers=4)
+                             batchify_fn=batchify, num_workers=num_workers)
 for batch in data_iter:
     for name, data in zip(['centers', 'contexts_negatives', 'masks',
                            'labels'], batch):
@@ -275,10 +275,8 @@ print('%.7f' % ((sigmd(1.1) + sigmd(-0.6) + sigmd(-2.2)) / 3))
 ```{.python .input  n=22}
 embed_size = 100
 net = nn.Sequential()
-net.add(nn.Embedding(input_dim=len(idx_to_token), output_dim=embed_size,
-                     sparse_grad=True),
-        nn.Embedding(input_dim=len(idx_to_token), output_dim=embed_size,
-                     sparse_grad=True))
+net.add(nn.Embedding(input_dim=len(idx_to_token), output_dim=embed_size),
+        nn.Embedding(input_dim=len(idx_to_token), output_dim=embed_size))
 ```
 
 ### 训练
@@ -287,15 +285,13 @@ net.add(nn.Embedding(input_dim=len(idx_to_token), output_dim=embed_size,
 
 ```{.python .input  n=23}
 def train(net, lr, num_epochs):
-    ctx = gb.try_gpu()
-    net.initialize(ctx=ctx, force_reinit=True)
+    net.initialize(force_reinit=True)
     trainer = gluon.Trainer(net.collect_params(), 'adam',
                             {'learning_rate': lr})
     for epoch in range(num_epochs):
         start_time, train_l_sum = time.time(), 0
         for batch in data_iter:
-            center, context_negative, mask, label = [
-                data.as_in_context(ctx) for data in batch]
+            center, context_negative, mask, label = batch
             with autograd.record():
                 pred = skip_gram(center, context_negative, net[0], net[1])
                 # 使用掩码变量 mask 来避免填充项对损失函数计算的影响。

gluonbook/utils.py

@@ -235,13 +235,14 @@ def load_data_fashion_mnist(batch_size, resize=None, root=os.path.join(
 
     mnist_train = gdata.vision.FashionMNIST(root=root, train=True)
     mnist_test = gdata.vision.FashionMNIST(root=root, train=False)
+    num_workers = 0 if sys.platform.startswith('win32') else 4
 
     train_iter = gdata.DataLoader(mnist_train.transform_first(transformer),
                                   batch_size, shuffle=True,
-                                  num_workers=4)
+                                  num_workers=num_workers)
     test_iter = gdata.DataLoader(mnist_test.transform_first(transformer),
                                  batch_size, shuffle=False,
-                                 num_workers=4)
+                                 num_workers=num_workers)
     return train_iter, test_iter