Ubuntu下面的Keras可视化+权重维度获取-Netron的安装使用

环境:

Ubuntu	19.10
Python	3.6.10
Keras	2.3.1

#---------------------------------------------------------------------------------------------------------------------------------------

操作过程如下:

$ snap install netron

$ netron
Serving at http://localhost:8080

然后在浏览器打开http://localhost:8080

在Open Model上传自己的.h5模型即可。

 

#---------------------------------------------------------------------------------------------------------------------------------------

准备好数据集:

tsocks wget https://s3.amazonaws.com/img-datasets/mnist.npz

mv mnist.npz ~/.keras/datasets

#---------------------------------------------------------------------------------------------------------------------------------------

运行如下代码(来自[1]):

from keras.models import Model
from keras.layers import Input, Dense
from keras.datasets import mnist
from keras.utils import np_utils
 
 
(x_train, y_train), (x_test, y_test) = mnist.load_data()
x_train=x_train.reshape(x_train.shape[0],-1)/255.0
x_test=x_test.reshape(x_test.shape[0],-1)/255.0
y_train=np_utils.to_categorical(y_train,num_classes=10)
y_test=np_utils.to_categorical(y_test,num_classes=10)
 
inputs = Input(shape=(784, ))
x = Dense(64, activation='relu')(inputs)
x = Dense(64, activation='relu')(x)
y = Dense(10, activation='softmax')(x)
 
model = Model(inputs=inputs, outputs=y)
 
model.save('m1.h5')
model.summary()
model.compile(loss='categorical_crossentropy', optimizer='sgd', metrics=['accuracy'])
model.fit(x_train, y_train, batch_size=32, epochs=10)
#loss,accuracy=model.evaluate(x_test,y_test)
 
model.save('m2.h5')
model.save_weights('m3.h5')

运行后我们得到m1,m2,m3三个文件

文件名	保存的函数	保存了图结构	保存了模型参数	可否用Neutron打开
m1.h5	save()	√	X	√
m2.h5	save()	√	√	√
m3.h5	save_weights()	X	√	√

m1.h5打开结果

m2.h5打开结果

 

m3.h5打开结果

从上面可以看到权重的维度。

所以如[1]所说，没啥事儿的话，尽量使用save()而不是save_weights()

#---------------------------------------------------------------------------------------------------------------------------------------

Reference:

[1]keras保存模型中的save()和save_weights()