用CPU跑Deep-Residual-Shrinkage-Networks模型_深度残差cpu可以跑得动吗

用CPU跑Deep-Residual-Shrinkage-Networks模型

一、模型所在GitHub地址

https://github.com/zhao62/Deep-Residual-Shrinkage-Networks

二、环境配置

1. 软件环境

1. Python: Anaconda3
2. IDE: Pycharm

2. python库环境

1. tensorflow

   pip install -i https://pypi.tuna.tsinghua.edu.cn/simple tensorflow==1.15
   1

2. tflearn

   pip install -i https://pypi.tuna.tsinghua.edu.cn/simple tflearn
   1

三、代码运行

1. DRSN_TFLearn.py

1) 样本下载链接

因为代码自动下载速度太慢，所以直接手动下载

https://www.cs.toronto.edu/~kriz/cifar-10-python.tar.gz

2) 代码和样本所在文件夹结构

3) 运行结果

2. DRSN_Keras.py

1) 代码修改

1. 需修改的代码

   import keras
   from keras.datasets import mnist
   from keras.layers import Dense, Conv2D, BatchNormalization, Activation
   from keras.layers import AveragePooling2D, Input, GlobalAveragePooling2D
   from keras.optimizers import Adam
   from keras.regularizers import l2
   from keras import backend as K
   from keras.models import Model
   from keras.layers.core import Lambda
   1
   2
   3
   4
   5
   6
   7
   8
   9

2. 修改后代码

   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
   1
   2
   3
   4
   5
   6
   7
   8
   9

2）运行结果