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 ShapeParam #input_1 (InputLayer)(None, 70)0embedding_1 (Embedding)(None, 70, 300)28500000bidirectional_1 (Bidirectional)(None, 70, 128)140544global_max_pooling1d_1(GlobalMaxPool1D)(None, 128)0dense_1 (Dense)(None, 16)2064dropout_1 (Dropout)(None, 16)0dense_2 (Dense)(None, 1)17Total params28,642,625Trainable params28,642,625Non-trainable params0