def build_model(self, layers, compile={}):
"""根據配置項構建 `self.model`。
Args:
layers ([dict]): 層定義集合。集合中每一項為一層的定義。
層定義包含 `type`:(dense或lstm) 用來定義層的類型。
層定義中其他屬性參見 `Dense`_ 和 `LSTM`_ 構造函數參數定義。
compile (dict): 訓練配置模型定義。定義可用屬性參見 `compile`_ 函數定義。
Returns:
.. _Dense:
https://keras.io/zh/layers/core/#dense
.. _LSTM:
https://keras.io/zh/layers/recurrent/#lstm
.. _compile:
https://keras.io/zh/models/model/#compile
"""
for layer in layers:
t = layer.pop('type')
if t == 'dense':
# https://keras.io/zh/layers/core/
self.__model.add(Dense.from_config(layer))
elif t == 'lstm':
# https://keras.io/zh/layers/recurrent/#lstm
self.__model.add(LSTM.from_config(layer))
elif t == 'dropout':
# https://keras.io/zh/layers/recurrent/#Dropout
self.__model.add(Dropout.from_config(layer))
elif t == 'cudnnlstm':
# https://keras.io/zh/layers/recurrent/#Dropout
self.__model.add(CuDNNLSTM.from_config(layer))
# https://keras.io/zh/models/model/#compile
self.__model.compile(**compile)
# json_string = model.to_json()
# print(json_string)
# import json
# with open('s2s.json', 'w') as f:
# json.dump(json_string, f)
# #sys.exit()
else:
print('load model')
model = load_model(args.model_path)
num_encoder_tokens = model.layers[0].input_shape[2]
num_decoder_tokens = model.layers[1].input_shape[2]
encoder_inputs = Input(shape=(None, num_encoder_tokens))
encoder = LSTM.from_config(model.layers[2].get_config())
encoder_outputs, state_h, state_c = encoder(encoder_inputs)
# We discard `encoder_outputs` and only keep the states.
encoder_states = [state_h, state_c]
# Set up the decoder, using `encoder_states` as initial state.
decoder_inputs = Input(shape=(None, num_decoder_tokens))
# We set up our decoder to return full output sequences,
# and to return internal states as well. We don't use the
# return states in the training model, but we will use them in inference.
decoder_lstm = LSTM.from_config(model.layers[3].get_config())
decoder_outputs, _, _ = decoder_lstm(decoder_inputs,
initial_state=encoder_states)
decoder_dense = Dense.from_config(model.layers[4].get_config())
decoder_outputs = decoder_dense(decoder_outputs)
for layer in model.layers:
print("{}: {} => {}".format(layer.name, layer.input_shape,
layer.output_shape))
print()
model = load_model("./models/kuzushiji_cnn_lstm_1565827392.348016.h5")
print_model(model, title="Original model:")
encode_and_transform = Model(inputs=model.input,
outputs=model.get_layer('multiply_1').output)
print_model(encode_and_transform, title="Encoder:")
decoder_input_h = Input(shape=(max_seq_length, ))
decoder_input_c = Input(shape=(max_seq_length, ))
decoder_internal_state = [decoder_input_h, decoder_input_c]
decoder_lstm = LSTM.from_config(model.get_layer('lstm_1').get_config())
encoder_output_to_decoder_input = Input(
shape=model.get_layer('multiply_1').output_shape[1:])
lstm_outputs, state_h, state_c = decoder_lstm(
encoder_output_to_decoder_input, initial_state=decoder_internal_state)
decoder_states = [state_h, state_c]
decoder_outputs = model.get_layer('time_distributed_1')(lstm_outputs)
decoder_model = Model([encoder_output_to_decoder_input] +
decoder_internal_state,
[decoder_outputs] + decoder_states)
print_model(decoder_model, title="Modified decoder:")
# extract encoder & encode image
#image_tensor = encoder.predict(input_image)
# extract and setup decoder
