diff --git a/recognize_digits/README.en.md b/recognize_digits/README.en.md
index 9bc4a2ba3e22af97eb0a9aecc87ca244850d4d25..8e88d9ad28dbfb3eb6f1116d1b66fb5b04804139 100644
--- a/recognize_digits/README.en.md
+++ b/recognize_digits/README.en.md
@@ -70,7 +70,7 @@ Fig. 3. Multilayer Perceptron network architecture<br/>
 #### Convolutional Layer
 
 <p align="center">
-<img src="image/conv_layer.png" width=500><br/>
+<img src="image/conv_layer.png" width='650'><br/>
 Fig. 4. Convolutional layer<br/>
 </p>
 
diff --git a/recognize_digits/README.md b/recognize_digits/README.md
index e0472b68dadd15ddea4d07b5a380918af711e331..a7cd484fda31e203955b3ad9eb68973e118c91c8 100644
--- a/recognize_digits/README.md
+++ b/recognize_digits/README.md
@@ -79,7 +79,7 @@ Softmax回归模型采用了最简单的两层神经网络，即只有输入层
 卷积层是卷积神经网络的核心基石。在图像识别里我们提到的卷积是二维卷积，即离散二维滤波器（也称作卷积核）与二维图像做卷积操作，简单的讲是二维滤波器滑动到二维图像上所有位置，并在每个位置上与该像素点及其领域像素点做内积。卷积操作被广泛应用与图像处理领域，不同卷积核可以提取不同的特征，例如边沿、线性、角等特征。在深层卷积神经网络中，通过卷积操作可以提取出图像低级到复杂的特征。
 
 <p align="center">
-<img src="image/conv_layer.png"><br/>
+<img src="image/conv_layer.png" width='650'><br/>
 图5. 卷积层图片<br/>
 </p>
 
diff --git a/recognize_digits/index.en.html b/recognize_digits/index.en.html
index e7fcf9de884b1ad981082426a169e2e706e0cb5f..5a5c53708f2bf66ad34afee301ef43220b54e3ed 100644
--- a/recognize_digits/index.en.html
+++ b/recognize_digits/index.en.html
@@ -112,7 +112,7 @@ Fig. 3. Multilayer Perceptron network architecture<br/>
 #### Convolutional Layer
 
 <p align="center">
-<img src="image/conv_layer.png" width=500><br/>
+<img src="image/conv_layer.png" width='650'><br/>
 Fig. 4. Convolutional layer<br/>
 </p>
 
diff --git a/recognize_digits/index.html b/recognize_digits/index.html
index 8260711a1f97ed842e920ce1f999262f06aae97a..06fd70557fbabd185d52811cf8aa6bc14118275a 100644
--- a/recognize_digits/index.html
+++ b/recognize_digits/index.html
@@ -121,7 +121,7 @@ Softmax回归模型采用了最简单的两层神经网络，即只有输入层
 卷积层是卷积神经网络的核心基石。在图像识别里我们提到的卷积是二维卷积，即离散二维滤波器（也称作卷积核）与二维图像做卷积操作，简单的讲是二维滤波器滑动到二维图像上所有位置，并在每个位置上与该像素点及其领域像素点做内积。卷积操作被广泛应用与图像处理领域，不同卷积核可以提取不同的特征，例如边沿、线性、角等特征。在深层卷积神经网络中，通过卷积操作可以提取出图像低级到复杂的特征。
 
 <p align="center">
-<img src="image/conv_layer.png"><br/>
+<img src="image/conv_layer.png" width='650'><br/>
 图5. 卷积层图片<br/>
 </p>