Deep-Residual-Shrinkage-Networks模型

https://github.com/zhao62/Deep-Residual-Shrinkage-Networks
安装tensorflow版本为1.15.0（1.14会报错importorror:没有名为“tensorflow.core”的模块）
tensorflow1.10开始集成了keras
1.运行DRSN_Keras.py
使用tensorflow中的keras，不需要单独下载keras，需要更改DRSN_Keras.py中的部分代码

from tensorflow import keras
from tensorflow.keras.datasets import mnist
from tensorflow.keras.layers import Dense, Conv2D, BatchNormalization, Activation
from tensorflow.keras.layers import AveragePooling2D, Input, GlobalAveragePooling2D 
from tensorflow.keras.optimizers import Adam
from tensorflow.keras.regularizers import l2
from tensorflow.keras import backend as K
from tensorflow.keras.models import Model
from tensorflow_core.python.keras.layers import Lambda

2.运行DRSN_TFLearn.py
运行路径报错
需要加一层路径即可