keras 模型可视化和遇到的坑

清疚 2022-05-25 10:46 221阅读 0赞

1.安装相应模块  
pip install pydot-ng  
pip install graphviz  
pip install pydot  
2.安装了以上模块，但是还是报错误,发现GraphViz的可执行文件没有:  
OSError: `pydot` failed to call GraphViz.Please install GraphViz ([https://www.graphviz.org/][https_www.graphviz.org]) and ensure that its executables are in the $PATH.  
3.百度搜索，下载graphviz-2.38.msi，安装完以后相应的d:/Graphviz2.38/bin目录地下就有可执行文件了。  
4.将d:/Graphviz2.38/bin目录加到系统环境变量中就OK啦  
5.代码

# coding=utf-8
    ''' @author: admin '''
    from keras.models import Sequential
    from keras.layers import Dense, Activation
    from keras.utils import plot_model
    
    import pydot
    
    model = Sequential()
    model.add(Dense(32, activation='relu', input_dim=100))
    model.add(Dense(1, activation='sigmoid'))
    model.compile(optimizer='rmsprop',
                  loss='binary_crossentropy',
                  metrics=['accuracy'])
    
    # Generate dummy data
    import numpy as np
    data = np.random.random((1000, 100))
    labels = np.random.randint(2, size=(1000, 1))
    plot_model(model, to_file='model.png',show_shapes=True)
    # Train the model, iterating on the data in batches of 32 samples
    # model.fit(data, labels, epochs=10, batch_size=32)

6.输出的模型图  
![这里写图片描述][70]  
7.[keras 模型可视化显示卷积conv和池化pooling kernel\_size][keras _conv_pooling kernel_size]

[https_www.graphviz.org]: https://www.graphviz.org/
[70]: /images/20220525/9b5aaf1eea32459fadcc763497bd2f72.png
[keras _conv_pooling kernel_size]: https://blog.csdn.net/u011311291/article/details/80375664