This is an implementation of Visualizing and Understanding Convolutional Networks by Matthew D. Zeiler and Rob Fergus in tensorflow.keras

The base cnn model is vgg16 and the pre-trained model is just from keras's vgg16 model.

https://github.com/FHainzl/Visualizing_Understanding_CNN_Implementation

https://buptldy.github.io/2016/10/29/2016-10-29-deconv/

Visualizing and Understanding Convolutional Networks

https://zhuanlan.zhihu.com/p/48501100

https://github.com/vdumoulin/conv_arithmetic

guided_bp.py: https://blog.csdn.net/xys430381_1/article/details/90413169