From abfa3f9c218cfd42858e00afb0dce86192d0de3e Mon Sep 17 00:00:00 2001 From: dangqingqing Date: Wed, 8 Mar 2017 15:53:27 +0800 Subject: [PATCH] shrink image --- recognize_digits/README.en.md | 2 +- recognize_digits/README.md | 2 +- recognize_digits/index.en.html | 2 +- recognize_digits/index.html | 2 +- 4 files changed, 4 insertions(+), 4 deletions(-) diff --git a/recognize_digits/README.en.md b/recognize_digits/README.en.md index 8e88d9a..9ae2d36 100644 --- a/recognize_digits/README.en.md +++ b/recognize_digits/README.en.md @@ -70,7 +70,7 @@ Fig. 3. Multilayer Perceptron network architecture
#### Convolutional Layer

-
+
Fig. 4. Convolutional layer

diff --git a/recognize_digits/README.md b/recognize_digits/README.md index a7cd484..2efb790 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。

-
+
图5. 卷积层图片

diff --git a/recognize_digits/index.en.html b/recognize_digits/index.en.html index 5a5c537..13e10a9 100644 --- a/recognize_digits/index.en.html +++ b/recognize_digits/index.en.html @@ -112,7 +112,7 @@ Fig. 3. Multilayer Perceptron network architecture
#### Convolutional Layer

-
+
Fig. 4. Convolutional layer

diff --git a/recognize_digits/index.html b/recognize_digits/index.html index 06fd705..329584e 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。

-
+
图5. 卷积层图片

-- GitLab