slim

tf.nn.conv2d和tf.contrib.slim.conv2d的区别

http://blog.sina.com.cn/s/blog_6ca0f5eb0102wsuu.html

tf.contrib.slim.conv2d (inputs,
                num_outputs,[卷积核个数]
                kernel_size,[卷积核的高度，卷积核的宽度]
                stride=1,
                padding='SAME',
)
tf.nn.conv2d(
    input,(与上述一致)
    filter,([卷积核的高度，卷积核的宽度，图像通道数，卷积核个数])
    strides,
    padding,
)

http://www.360doc.com/content/17/0418/10/10408243_646494562.shtml

https://www.2cto.com/kf/201706/649266.html

采用VGG16做图像分类与分割

http://geek.csdn.net/news/detail/126133

slim markdown 翻译

http://blog.csdn.net/guvcolie/article/details/77686555