Python 使用Keras TimeDistributed层时拓扑排序失败

我试图通过使用keras时间分布层，在4D张量（样本、时间步长、回望、特征）上，将回望维度的最后一列点到之前的回望周期。该模型可以正常运行，但在我运行model.fit（）时，它会发出一个警告，即图形无法按拓扑顺序排序

说它会搞砸模特训练。那么我能做些什么来防止这种情况发生呢

环境：

Tensorflow GPU 1.15.0

CUDA V10.0.130

python 3.6.5

Keras 2.3.1

Keras应用程序1.0.8

Keras预处理1.1.0

警告日志

2020-03-05 08:36:17.558396: E tensorflow/core/grappler/optimizers/dependency_optimizer.cc:697] Iteration = 1, topological sort failed with message: The graph couldn't be sorted in topological order.
2020-03-05 08:36:17.558777: E tensorflow/core/grappler/optimizers/meta_optimizer.cc:533] layout failed: Invalid argument: The graph couldn't be sorted in topological order.
2020-03-05 08:36:17.559302: E tensorflow/core/grappler/optimizers/meta_optimizer.cc:533] model_pruner failed: Invalid argument: MutableGraphView::MutableGraphView error: node 'loss/time_distributed_1_loss/mean_squared_error/weighted_loss/concat' has self cycle fanin 'loss/time_distributed_1_loss/mean_squared_error/weighted_loss/concat'.
2020-03-05 08:36:17.560121: E tensorflow/core/grappler/optimizers/meta_optimizer.cc:533] remapper failed: Invalid argument: MutableGraphView::MutableGraphView error: node 'loss/time_distributed_1_loss/mean_squared_error/weighted_loss/concat' has self cycle fanin 'loss/time_distributed_1_loss/mean_squared_error/weighted_loss/concat'.
2020-03-05 08:36:17.560575: E tensorflow/core/grappler/optimizers/meta_optimizer.cc:533] arithmetic_optimizer failed: Invalid argument: The graph couldn't be sorted in topological order.
2020-03-05 08:36:17.560853: E tensorflow/core/grappler/optimizers/dependency_optimizer.cc:697] Iteration = 0, topological sort failed with message: The graph couldn't be sorted in topological order.
2020-03-05 08:36:17.561141: E tensorflow/core/grappler/optimizers/dependency_optimizer.cc:697] Iteration = 1, topological sort failed with message: The graph couldn't be sorted in topological order.

---

可以考虑使用TysFooSo.x版本。

我已经迁移/升级了您的代码，并验证它是否可以在google colab上运行。 您可以尝试查找有关如何将代码迁移到Tensorflow 2.x的更多信息

请参考下面的代码

import numpy as np
import tensorflow as tf
from tensorflow.keras.models import Model
from tensorflow.keras.layers import Input, TimeDistributed
#import keras
# Dot layer
class Dot(tf.keras.layers.Layer):
    def __init__(self, **kwargs):
        super(Dot, self).__init__(**kwargs)

    def call(self, x):

        ht, hT = x[:,:-1,:],x[:,-1:,:]
        ml = tf.multiply(ht, hT)

        # I believe problem come from reduce_sum
        dot = tf.reduce_sum(ml, axis=-1)
        return dot

    def compute_output_shape(self, input_shape):

        return (None,input_shape[1]-1)

num_fea = 11
num_lookback = 5
time_step = 3
sample = 2

# create model
input = Input(shape=(time_step,num_lookback,num_fea))
dot = Dot()
output = TimeDistributed(dot)(input)

M = Model(inputs=[input], outputs=[output])
M.compile(optimizer='adam', loss='mse')

# create test data
data = np.arange(num_lookback*num_fea).reshape((num_lookback,num_fea))
data = np.broadcast_to(data,shape=(sample,time_step,num_lookback,num_fea))
y = np.ones(shape=(sample,time_step,num_lookback-1))

# fit model to demonstrate error
M.fit(x=data,y=y, batch_size=2, epochs=10)

---

谢谢你的代码，但这只是我代码的一部分。如果我更改TF版本，我必须将所有1000行代码更改为TF2并再次调试它。嗨@RonakritW。您可以参考下面关于该警告的解释。我已经看到了这篇文章，但我不明白这个实现中的循环在哪里。问题可能是这个

ml=tf.multiply（ht，ht）

。你也可以查看链接，我也看到了这一点，但它没有帮助，我花了1周的时间来寻找解决方案，我看到了几乎所有可用的答案，但没有一个建议有解决方案。第二，乘法ht和ht不会创建循环，如果它在后端创建循环，请向我展示代码或其他东西来证明它。

import numpy as np
import tensorflow as tf
from tensorflow.keras.models import Model
from tensorflow.keras.layers import Input, TimeDistributed
#import keras
# Dot layer
class Dot(tf.keras.layers.Layer):
    def __init__(self, **kwargs):
        super(Dot, self).__init__(**kwargs)

    def call(self, x):

        ht, hT = x[:,:-1,:],x[:,-1:,:]
        ml = tf.multiply(ht, hT)

        # I believe problem come from reduce_sum
        dot = tf.reduce_sum(ml, axis=-1)
        return dot

    def compute_output_shape(self, input_shape):

        return (None,input_shape[1]-1)

num_fea = 11
num_lookback = 5
time_step = 3
sample = 2

# create model
input = Input(shape=(time_step,num_lookback,num_fea))
dot = Dot()
output = TimeDistributed(dot)(input)

M = Model(inputs=[input], outputs=[output])
M.compile(optimizer='adam', loss='mse')

# create test data
data = np.arange(num_lookback*num_fea).reshape((num_lookback,num_fea))
data = np.broadcast_to(data,shape=(sample,time_step,num_lookback,num_fea))
y = np.ones(shape=(sample,time_step,num_lookback-1))

# fit model to demonstrate error
M.fit(x=data,y=y, batch_size=2, epochs=10)