深度学习框架---keras的层次示意图---方便直观理解---适用sklearn模型的展示

感觉keras确实比其他框架舒服一点，但是前期理解keras层的时候可能有点小问题，keras的层使用了原始神经网络层的概念，即先有上层的输出聚合，聚合后在进入激活函数。我的环境是python3.5+tensorflow+keras+graphviz+pydot_ng+pydotplus

其中

安装好Python3以及pip之后

执行： 

pip install tensorflow

pip install keras

下载(https://www.cnblogs.com/fengbohello/p/4689131.html，这篇作者提供了graphviz.msi下载地址，官网不好使，可以从作者提供的路径下到)graphviz.msi并配置好路径

执行 pip install pydot_ng

pip install pydotplus

修改文件

python\Lib\site-packages\pydot_ng\__init__.py

def find_graphviz()中的

# Method 3 (Windows only)if os.sys.platform == 'win32':    # Try and work out the equivalent of "C:\Program Files" on this    # machine (might be on drive D:, or in a different language)    if 'PROGRAMFILES' in os.environ:        # Note, we could also use the win32api to get this        # information, but win32api may not be installed.        path = os.path.join(os.environ['PROGRAMFILES'], 'ATT', 'GraphViz', 'bin')    else:        #Just in case, try the default...        path = r"....\Graphviz2.37\bin"   
Graphviz的路径
python\Lib\site-packages\pydotplus\相应的文件也做相应的修改

然后就可以测试下面的代码了

from keras.utils.vis_utils import plot_modelfrom keras.models import Sequentialfrom keras.layers.core import Dense, Dropout, Activationfrom keras.layers.embeddings import Embeddingfrom keras.layers import Input , Densefrom keras.models import Modelmodel = Sequential()model.add(Dense(4, input_dim=200))model.add(Activation('relu'))model.add(Dropout(0.5))model.add(Dense(200))model.add(Activation('relu'))model.add(Dropout(0.5))model.add(Dense(100))model.add(Activation('relu'))model.add(Dropout(0.5))model.add(Dense(50))model.add(Activation('relu'))model.add(Dropout(0.5))model.add(Dense(20, input_dim=3))model.add(Activation('softmax'))model.compile(loss='binary_crossentropy', optimizer='adam', class_mode="binary")plot_model(model, to_file='model1.png',show_shapes=True)

对应的结构图为：

sklearn中的模型展示（python3），在http://blog.csdn.net/shouwangzhelv/article/details/51163535基础上做了修改

from sklearn.datasets import load_irisfrom sklearn import treefrom sklearn.externals.six import StringIOimport pydot_ngiris = load_iris()clf = tree.DecisionTreeClassifier()clf = clf.fit(iris.data, iris.target)dot_data = StringIO()tree.export_graphviz(clf, out_file=dot_data)graph = pydot_ng.graph_from_dot_data(dot_data.getvalue())graph.write_pdf("iris.pdf")