xccds/chinese_wordseg_keras

基于深度学习的中文分词尝试

chinese_wordseg_keras's Issues

can you share your other codes?

thanks for your contribution,but I can't see you use keras to build the model, can you share the whole program

模型训练的时候有问题

在模型结构中出现问题：
model = Sequential()
model.add(Embedding(maxfeatures, 100,weights=init_weight))
model.add(Flatten())
model.add(Dense(700, 100))
model.add(Dropout(0.5))
model.add(Activation('relu'))
model.add(Dense(100, nb_classes))
model.add(Activation('softmax'))
model.compile(loss='categorical_crossentropy', optimizer='adam')

其中model.add(Flatten())有错：
Exception: The shape of the input to "Flatten" is not fully defined (got (None, 100). Make sure to pass a complete "input_shape" or "batch_input_shape" argument to the first layer in your model.

想参考一下您的代码

请问，能不能分享一下您的分词代码。