Merge pull request #579 from JiabinYang/book02_refine

Refine the text and the presentation of inference result of "02.recognize_digits"

02.recognize_digits/README.cn.md

@@ -38,9 +38,9 @@ $$ y_i = \text{softmax}(\sum_j W_{i,j}x_j + b_i) $$
 
 对于有 $N$ 个类别的多分类问题，指定 $N$ 个输出节点，$N$ 维结果向量经过softmax将归一化为 $N$ 个[0,1]范围内的实数值，分别表示该样本属于这 $N$ 个类别的概率。此处的 $y_i$ 即对应该图片为数字 $i$ 的预测概率。
 
-在分类问题中，我们一般采用交叉熵代价损失函数（cross entropy），公式如下：
+在分类问题中，我们一般采用交叉熵代价损失函数（cross entropy loss），公式如下：
 
-$$  \text{crossentropy}(label, y) = -\sum_i label_ilog(y_i) $$
+$$  \text{_L_<sub>cross-entropy</sub>}(label, y) = -\sum_i label_ilog(y_i) $$
 
 图2为softmax回归的网络图，图中权重用蓝线表示、偏置用红线表示、+1代表偏置参数的系数为1。
 
@@ -155,6 +155,7 @@ PaddlePaddle在API中提供了自动加载[MNIST](http://yann.lecun.com/exdb/mni
 ```python
 import paddle
 import paddle.fluid as fluid
+from __future__ import print_function
 ```
 
 ### Program Functions 配置
@@ -294,8 +295,8 @@ def event_handler(event):
         if event.step % 100 == 0:
             # event.metrics maps with train program return arguments.
             # event.metrics[0] will yeild avg_cost and event.metrics[1] will yeild acc in this example.
-            print "Pass %d, Batch %d, Cost %f" % (
-                event.step, event.epoch, event.metrics[0])
+            print("Pass %d, Batch %d, Cost %f" % (
+                event.step, event.epoch, event.metrics[0]))
 
     if isinstance(event, fluid.EndEpochEvent):
         avg_cost, acc = trainer.test(
@@ -419,7 +420,7 @@ img = load_image(cur_dir + '/image/infer_3.png')
 ```python
 results = inferencer.infer({'img': img})
 lab = np.argsort(results)  # probs and lab are the results of one batch data
-print "Label of image/infer_3.png is: %d" % lab[0][0][-1]
+print ("Inference result of image/infer_3.png is: %d" % lab[0][0][-1])
 ```
 
 ## 总结

02.recognize_digits/README.md

@@ -50,7 +50,7 @@ For an $N$-class classification problem with $N$ output nodes, Softmax normalize
 
 In such a classification problem, we usually use the cross entropy loss function:
 
-$$  \text{crossentropy}(label, y) = -\sum_i label_ilog(y_i) $$
+$$  \text{_L_<sub>cross-entropy</sub>}(label, y) = -\sum_i label_ilog(y_i) $$
 
 Fig. 2 illustrates a softmax regression network, with the weights in blue, and the bias in red. `+1` indicates that the bias is $1$.
 
@@ -161,6 +161,7 @@ A PaddlePaddle program starts from importing the API package:
 ```python
 import paddle
 import paddle.fluid as fluid
+from __future__ import print_function
 ```
 
 ### Program Functions Configuration
@@ -300,8 +301,8 @@ def event_handler(event):
         if event.step % 100 == 0:
             # event.metrics maps with train program return arguments.
             # event.metrics[0] will yeild avg_cost and event.metrics[1] will yeild acc in this example.
-            print "Pass %d, Batch %d, Cost %f" % (
-                event.step, event.epoch, event.metrics[0])
+            print("Pass %d, Batch %d, Cost %f" % (
+                event.step, event.epoch, event.metrics[0]))
 
     if isinstance(event, fluid.EndEpochEvent):
         avg_cost, acc = trainer.test(
@@ -432,7 +433,7 @@ Now we are ready to do inference.
 ```python
 results = inferencer.infer({'img': img})
 lab = np.argsort(results)  # probs and lab are the results of one batch data
-print "Label of image/infer_3.png is: %d" % lab[0][0][-1]
+print("Inference result of image/infer_3.png is: %d" % lab[0][0][-1])
 ```
 
 

02.recognize_digits/index.cn.html

@@ -80,9 +80,9 @@ $$ y_i = \text{softmax}(\sum_j W_{i,j}x_j + b_i) $$
 
 对于有 $N$ 个类别的多分类问题，指定 $N$ 个输出节点，$N$ 维结果向量经过softmax将归一化为 $N$ 个[0,1]范围内的实数值，分别表示该样本属于这 $N$ 个类别的概率。此处的 $y_i$ 即对应该图片为数字 $i$ 的预测概率。
 
-在分类问题中，我们一般采用交叉熵代价损失函数（cross entropy），公式如下：
+在分类问题中，我们一般采用交叉熵代价损失函数（cross entropy loss），公式如下：
 
-$$  \text{crossentropy}(label, y) = -\sum_i label_ilog(y_i) $$
+$$  \text{_L_<sub>cross-entropy</sub>}(label, y) = -\sum_i label_ilog(y_i) $$
 
 图2为softmax回归的网络图，图中权重用蓝线表示、偏置用红线表示、+1代表偏置参数的系数为1。
 
@@ -197,6 +197,7 @@ PaddlePaddle在API中提供了自动加载[MNIST](http://yann.lecun.com/exdb/mni
 ```python
 import paddle
 import paddle.fluid as fluid
+from __future__ import print_function
 ```
 
 ### Program Functions 配置
@@ -336,8 +337,8 @@ def event_handler(event):
         if event.step % 100 == 0:
             # event.metrics maps with train program return arguments.
             # event.metrics[0] will yeild avg_cost and event.metrics[1] will yeild acc in this example.
-            print "Pass %d, Batch %d, Cost %f" % (
-                event.step, event.epoch, event.metrics[0])
+            print("Pass %d, Batch %d, Cost %f" % (
+                event.step, event.epoch, event.metrics[0]))
 
     if isinstance(event, fluid.EndEpochEvent):
         avg_cost, acc = trainer.test(
@@ -461,7 +462,7 @@ img = load_image(cur_dir + '/image/infer_3.png')
 ```python
 results = inferencer.infer({'img': img})
 lab = np.argsort(results)  # probs and lab are the results of one batch data
-print "Label of image/infer_3.png is: %d" % lab[0][0][-1]
+print ("Inference result of image/infer_3.png is: %d" % lab[0][0][-1])
 ```
 
 ## 总结

02.recognize_digits/index.html

@@ -92,7 +92,7 @@ For an $N$-class classification problem with $N$ output nodes, Softmax normalize
 
 In such a classification problem, we usually use the cross entropy loss function:
 
-$$  \text{crossentropy}(label, y) = -\sum_i label_ilog(y_i) $$
+$$  \text{_L_<sub>cross-entropy</sub>}(label, y) = -\sum_i label_ilog(y_i) $$
 
 Fig. 2 illustrates a softmax regression network, with the weights in blue, and the bias in red. `+1` indicates that the bias is $1$.
 
@@ -203,6 +203,7 @@ A PaddlePaddle program starts from importing the API package:
 ```python
 import paddle
 import paddle.fluid as fluid
+from __future__ import print_function
 ```
 
 ### Program Functions Configuration
@@ -342,8 +343,8 @@ def event_handler(event):
         if event.step % 100 == 0:
             # event.metrics maps with train program return arguments.
             # event.metrics[0] will yeild avg_cost and event.metrics[1] will yeild acc in this example.
-            print "Pass %d, Batch %d, Cost %f" % (
-                event.step, event.epoch, event.metrics[0])
+            print("Pass %d, Batch %d, Cost %f" % (
+                event.step, event.epoch, event.metrics[0]))
 
     if isinstance(event, fluid.EndEpochEvent):
         avg_cost, acc = trainer.test(
@@ -474,7 +475,7 @@ Now we are ready to do inference.
 ```python
 results = inferencer.infer({'img': img})
 lab = np.argsort(results)  # probs and lab are the results of one batch data
-print "Label of image/infer_3.png is: %d" % lab[0][0][-1]
+print("Inference result of image/infer_3.png is: %d" % lab[0][0][-1])
 ```