GRU - 文本情感分类

代码在 给一个拥抱 上
网络结构

inp = Input(shape=(maxlen,))
x = Embedding(max_features, embed_size)(inp)
x = Bidirectional(CuDNNGRU(64, return_sequences=True))(x)
x = GlobalMaxPool1D()(x)
x = Dense(16, activation="relu")(x)
x = Dropout(0.1)(x)
x = Dense(1, activation="sigmoid")(x)
model = Model(inputs=inp, outputs=x)
model.compile(loss='binary_crossentropy', optimizer='adam', metrics=[auc])
print(model.summary())

Layer (type)	Output Shape	Param #
input_1 (InputLayer)	(None, 70)	0
embedding_1 (Embedding)	(None, 70, 300)	28500000
bidirectional_1 (Bidirectional)	(None, 70, 128)	140544
global_max_pooling1d_1(GlobalMaxPool1D)	(None, 128)	0
dense_1 (Dense)	(None, 16)	2064
dropout_1 (Dropout)	(None, 16)	0
dense_2 (Dense)	(None, 1)	17
Total params		28,642,625
Trainable params		28,642,625
Non-trainable params		0