diff --git a/chapter_appendix/gluonbook.md b/chapter_appendix/gluonbook.md
index 6528249785d45f979a0ed14932ab22a39f46ef12..13fa2105c1531517e2c7338c04d5e1e3a84ef410 100644
--- a/chapter_appendix/gluonbook.md
+++ b/chapter_appendix/gluonbook.md
@@ -14,7 +14,7 @@
 
 * `data_iter_random`，[循环神经网络](../chapter_recurrent-neural-networks/rnn.md)
 
-* `evaluate_accuracy`，[Softmax回归的从零开始实现](../chapter_deep-learning-basics/softmax-regression-scratch.md)
+* `evaluate_accuracy`，
 
 * `grad_clipping`，[循环神经网络](../chapter_recurrent-neural-networks/rnn.md)
 
diff --git a/chapter_computer-vision/image-augmentation.md b/chapter_computer-vision/image-augmentation.md
index b1aeb04858e2c56afc6e10f959e7e1da3d32761b..8e519498f47ba8fb9f4433cf1da2e7ce856f3448 100644
--- a/chapter_computer-vision/image-augmentation.md
+++ b/chapter_computer-vision/image-augmentation.md
@@ -114,10 +114,10 @@ def load_cifar10(is_train, augs, batch_size):
 
 ### 模型训练
 
-我们使用ResNet 18来训练CIFAR-10。训练的的代码与[“残差网络：ResNet”](../chapter_convolutional-neural-networks/resnet.md)中一致，除了使用所有可用的GPU和不同的学习率外。
+我们使用ResNet-18来训练CIFAR-10。训练的代码与[“残差网络：ResNet”](../chapter_convolutional-neural-networks/resnet.md)中一致，除了使用所有可用的GPU和不同的学习率外。
 
 ```{.python .input  n=13}
-def train(train_augs, test_augs, lr=0.1):
+def train_with_data_aug(train_augs, test_augs, lr=0.1):
     batch_size = 256
     ctx = gb.try_all_gpus()
     net = gb.resnet18(10)
@@ -132,13 +132,13 @@ def train(train_augs, test_augs, lr=0.1):
 首先我们看使用了图片增广的情况。
 
 ```{.python .input  n=14}
-train(train_augs, test_augs)
+train_with_data_aug(train_augs, test_augs)
 ```
 
 作为对比，我们尝试只对训练数据做中间剪裁。
 
 ```{.python .input  n=15}
-train(test_augs, test_augs)
+train_with_data_aug(test_augs, test_augs)
 ```
 
 可以看到，即使是简单的随机翻转也会有明显的效果。图片增广类似于正则项，它使得训练精度变低，但可以提高测试精度。
diff --git a/gluonbook/utils.py b/gluonbook/utils.py
index 2d9537e1543068d9d880290195274ca36a7add6a..d118f357d223086f4f8fab7ad6c3a9ac58bf845a 100644
--- a/gluonbook/utils.py
+++ b/gluonbook/utils.py
@@ -399,7 +399,7 @@ def train(train_iter, test_iter, net, loss, trainer, ctx, num_epochs,
             trainer.step(batch_size)
             n += batch_size
             m += sum([y.size for y in ys])
-            if print_batches and (i+1) % print_batches == 0:
+            if print_batches and (i + 1) % print_batches == 0:
                 print('batch %d, loss %f, train acc %f' % (
                     n, train_l_sum / n, train_acc_sum / m
                 ))
@@ -488,7 +488,7 @@ def train_ch3(net, train_iter, test_iter, loss, num_epochs, batch_size,
 
 
 def try_all_gpus():
-    """Return all available GPUs, or [mx.gpu()] if there is no GPU."""
+    """Return all available GPUs, or [mx.cpu()] if there is no GPU."""
     ctxes = []
     try:
         for i in range(16):