我尝试构建一个看起来像编码器/解码器模型的模型，但是区别在于，我在两个for循环中都使用了相同的LSTM模型。
要合并t-1和t-2的隐藏状态，我建立了一个中间层MyLayer。但是总是会出现以下错误：
ValueError: Graph disconnected: cannot obtain value for tensor Tensor("lstm_layer_18/Identity_1:0", shape=(8, 128), dtype=float32) at layer "my_layer". The following previous layers were accessed without issue: ['input_1', 'embedding', 'input_3', 'input_2', 'lambda1', 'reshape1']
我尝试了整个下午的调试，但找不到。
我发现大多数答案都是关于避免中间参数的输入层名称。但是这种方法对我不起作用。
我尝试打印出错误中的"lstm_layer_18/Identity_1:0"，这是第二个for循环中的state_h。但是我无法解决。谁能帮我发现错误？我的代码如下所示。
class MyLayer(Layer):
def __init__(self, output_dim, **kwargs):
self.output_dim = output_dim
super(MyLayer, self).__init__(**kwargs)
def build(self, input_shape):
assert isinstance(input_shape, list)
# 为该层创建一个可训练的权重
self.kernel_1 = self.add_weight(name='kernel_1',
shape=input_shape[0],
initializer='uniform',
trainable=True)
self.kernel_2 = self.add_weight(name='kernel_2',
shape=input_shape[1],
initializer='uniform',
trainable=True)
super(MyLayer, self).build(input_shape) # 一定要在最后调用它
def call(self, v):
assert isinstance(v, list)
a, b = v
return Add()([Multiply()([a, self.kernel_1]),
Multiply()([b, self.kernel_2])])
def compute_output_shape(self, input_shape):
assert isinstance(input_shape, list)
shape_a, shape_b = input_shape
assert shape_a == shape_b
return shape_a
def cf_lstm_model(input_step, output_step, features=2, embed_dim=64, lstm_dim=128, batch_size=8):
# input_shape:(batch_size, input_step, features)
x = Input(batch_shape=(batch_size, input_step, features))
h_1 = Input(batch_shape=(batch_size, lstm_dim))
h_2 = Input(batch_shape=(batch_size, lstm_dim))
c = Input(batch_shape=(batch_size, lstm_dim))
state_c = c
embedding = Dense(embed_dim, activation='relu', name='embedding')
inverse_embedding = Dense(features, activation='relu', name='inverse_embedding')
lstm_layer = LSTM(lstm_dim, activation='relu', return_state=True, name='lstm_layer')
cascade = MyLayer(lstm_dim)
# decoder = LSTM(lstm_dim, activation='relu', return_state=True, name='decoder')
# embeding ---> (batch_size, input_step, embed_dim)
emb_x = embedding(x)
# cascade_input
cascade_input = [h_2, h_1]
# Observe
for i in range(input_step - 1):
h_star = cascade(cascade_input)
m = Lambda(lambda xx: xx[:, i, :], name='lambda1')(emb_x)
m1 = Reshape((1, embed_dim), name='reshape1')(m)
lstm1, state_h, state_c = lstm_layer(m1, [h_star, state_c])
cascade_input.pop()
cascade_input.append(state_h)
out = Lambda(lambda xx: xx[:, input_step - 1, :], name='lambda2')(emb_x)
out = Reshape((1, embed_dim), name='reshape2')(out)
# Predict
for j in range(output_step):
h_star = cascade(cascade_input)
out, state_h, state_c = lstm_layer(out, [h_star, state_c])
# print('state_h', state_h)
print('state_c', state_c)
out = inverse_embedding(out)
if j == 0:
all_outputs = Reshape((1, features), name='reshape3')(out)
# print('output shape:', out.shape, K.int_shape(out))
else:
# 注意axis的纬度
all_outputs = K.concatenate([all_outputs, Reshape((1, features))(out)], axis=1)
# print('output shape:', K.int_shape(outputs))
cascade_input.pop()
cascade_input.append(state_h)
out = embedding(out)
out = Reshape((1, embed_dim), name='reshape4')(out)
# print('out', out.shape)
return Model(inputs=[x, h_1, h_2, c], outputs=all_outputs)
cf_lstm = cf_lstm_model(input_step=8,
output_step=12,
embed_dim=64,
lstm_dim=128)
错误反馈
state_c Tensor("lstm_layer_7/Identity_2:0", shape=(8, 128), dtype=float32)
state_c Tensor("lstm_layer_8/Identity_2:0", shape=(8, 128), dtype=float32)
state_c Tensor("lstm_layer_9/Identity_2:0", shape=(8, 128), dtype=float32)
state_c Tensor("lstm_layer_10/Identity_2:0", shape=(8, 128), dtype=float32)
state_c Tensor("lstm_layer_11/Identity_2:0", shape=(8, 128), dtype=float32)
state_c Tensor("lstm_layer_12/Identity_2:0", shape=(8, 128), dtype=float32)
state_c Tensor("lstm_layer_13/Identity_2:0", shape=(8, 128), dtype=float32)
state_c Tensor("lstm_layer_14/Identity_2:0", shape=(8, 128), dtype=float32)
state_c Tensor("lstm_layer_15/Identity_2:0", shape=(8, 128), dtype=float32)
state_c Tensor("lstm_layer_16/Identity_2:0", shape=(8, 128), dtype=float32)
state_c Tensor("lstm_layer_17/Identity_2:0", shape=(8, 128), dtype=float32)
state_c Tensor("lstm_layer_18/Identity_2:0", shape=(8, 128), dtype=float32)
Traceback (most recent call last):
File "/Users/duoshaoshishi/Desktop/Pedestrian prediction/CF-lstm/model.py", line 105, in <module>
cf_lstm = cf_lstm_model(input_step=8,
File "/Users/duoshaoshishi/Desktop/Pedestrian prediction/CF-lstm/model.py", line 102, in cf_lstm_model
return Model(inputs=[x, h_1, h_2, c], outputs=all_outputs)
File "/Users/duoshaoshishi/opt/anaconda3/envs/tf2/lib/python3.8/site-packages/tensorflow/python/keras/engine/training.py", line 167, in __init__
super(Model, self).__init__(*args, **kwargs)
File "/Users/duoshaoshishi/opt/anaconda3/envs/tf2/lib/python3.8/site-packages/tensorflow/python/keras/engine/network.py", line 173, in __init__
self._init_graph_network(*args, **kwargs)
File "/Users/duoshaoshishi/opt/anaconda3/envs/tf2/lib/python3.8/site-packages/tensorflow/python/training/tracking/base.py", line 456, in _method_wrapper
result = method(self, *args, **kwargs)
File "/Users/duoshaoshishi/opt/anaconda3/envs/tf2/lib/python3.8/site-packages/tensorflow/python/keras/engine/network.py", line 306, in _init_graph_network
nodes, nodes_by_depth, layers, _ = _map_graph_network(
File "/Users/duoshaoshishi/opt/anaconda3/envs/tf2/lib/python3.8/site-packages/tensorflow/python/keras/engine/network.py", line 1787, in _map_graph_network
raise ValueError('Graph disconnected: '
ValueError: Graph disconnected: cannot obtain value for tensor Tensor("lstm_layer_18/Identity_1:0", shape=(8, 128), dtype=float32) at layer "my_layer". The following previous layers were accessed without issue: ['input_1', 'embedding', 'input_3', 'input_2', 'lambda1', 'reshape1']