Question

我有2个Keras子模型（model_1，model_2），其中我通过使用model逻辑上按“系列”进行堆叠来形成完整的keras.models.Model()。我的意思是，model_2接受model_1的输出加上一个额外的输入张量，而model_2的输出就是我完整model的输出。完整的model已创建成功，我也可以使用compile/train/predict。

但是，我想通过在2个GPU上运行model来并行化训练，因此我使用multi_gpu_model()，但失败并出现错误：

AssertionError: Could not compute output Tensor("model_2/Dense_Decoder/truediv:0", shape=(?, 33, 22), dtype=float32)

我尝试使用multi_gpu_model(model_1, gpus=2)和multi_gpu_model(model_1, gpus=2)分别并行化两个子模型，但都成功。对于完整模型，该问题仅仅出现。

我正在使用 Tensorflow 1.12.0 和 Keras 2.2.4 。演示该问题的代码段（至少在我的计算机上）为：

from keras.layers import Input, Dense,TimeDistributed, BatchNormalization
from keras.layers import CuDNNLSTM as LSTM
from keras.models import Model
from keras.utils import multi_gpu_model


dec_layers = 2
codelayer_dim = 11
bn_momentum = 0.9
lstm_dim = 128
td_dense_dim = 0
output_dims = 22
dec_input_shape = [33, 44]


# MODEL 1
latent_input = Input(shape=(codelayer_dim,), name="Latent_Input")

# Initialize list of state tensors for the decoder
decoder_state_list = []

for dec_layer in range(dec_layers):
    # The tensors for the initial states of the decoder
    name = "Dense_h_" + str(dec_layer)
    h_decoder = Dense(lstm_dim, activation="relu", name=name)(latent_input)

    name = "BN_h_" + str(dec_layer)
    decoder_state_list.append(BatchNormalization(momentum=bn_momentum, name=name)(h_decoder))

    name = "Dense_c_" + str(dec_layer)
    c_decoder = Dense(lstm_dim, activation="relu", name=name)(latent_input)

    name = "BN_c_" + str(dec_layer)
    decoder_state_list.append(BatchNormalization(momentum=bn_momentum, name=name)(c_decoder))

# Define model_1
model_1 = Model(latent_input, decoder_state_list)


# MODEL 2
inputs = []

decoder_inputs = Input(shape=dec_input_shape, name="Decoder_Inputs")
inputs.append(decoder_inputs)

xo = decoder_inputs

for dec_layer in range(dec_layers):
    name = "Decoder_State_h_" + str(dec_layer)
    state_h = Input(shape=[lstm_dim], name=name)
    inputs.append(state_h)

    name = "Decoder_State_c_" + str(dec_layer)
    state_c = Input(shape=[lstm_dim], name=name)
    inputs.append(state_c)

    # RNN layer
    decoder_lstm = LSTM(lstm_dim,
                   return_sequences=True,
                   name="Decoder_LSTM_" + str(dec_layer))

    xo = decoder_lstm(xo, initial_state=[state_h, state_c])
    xo = BatchNormalization(momentum=bn_momentum, name="BN_Decoder_" + str(dec_layer))(xo)
    if td_dense_dim > 0: # Squeeze LSTM interconnections using Dense layers
        xo = TimeDistributed(Dense(td_dense_dim), name="Time_Distributed_" + str(dec_layer))(xo)

# Final Dense layer to return probabilities
outputs = Dense(output_dims, activation='softmax', name="Dense_Decoder")(xo)

# Define model_2
model_2 = Model(inputs=inputs, outputs=[outputs])


# FULL MODEL
latent_input = Input(shape=(codelayer_dim,), name="Latent_Input")
decoder_inputs = Input(shape=dec_input_shape, name="Decoder_Inputs")

# Stack the two models
# Propagate tensors through 1st model
x = model_1(latent_input)
# Insert decoder_inputs as the first input of the 2nd model
x.insert(0, decoder_inputs)
# Propagate tensors through 2nd model
x = model_2(x)

# Define full model
model = Model(inputs=[latent_input, decoder_inputs], outputs=[x])

# Parallelize the model
parallel_model = multi_gpu_model(model, gpus=2)
parallel_model.summary()

非常感谢您的帮助/提示。

Answer 1

我找到了解决我问题的方法，我不确定该如何辩解。

该问题是由我用x.insert(0, decoder_inputs)代替的x = [decoder_inputs] + x引起的。两者似乎都产生相同的张量列表，但是multi_gpu_model在第一种情况下会抱怨。

AssertionError：在Keras中使用multi_gpu_model（）时无法计算输出张量

1 个答案: