python 3 中 tensorflow 中的多输出和多损失函数的问题

Question

I want to train LSTM autoencoder. I have N observations with 2 features, one of them is continuous and one is binary: I want to predict continuous by linear + MAE loss and binary by sigmoid + BCE loss. In preprocessing phase I have created sequences, as sliding window of 3 observations. This is how the model looks like

input_ae = Input(shape=(X_train.shape[1], X_train.shape[2]))
print(input_ae.shape)
LSTM1 = keras.layers.LSTM(units=6, return_sequences=True, activation = 'selu')(input_ae)
LSTM2 = keras.layers.LSTM(units=1, activation= 'tanh')(LSTM1)
bottleneck = keras.layers.RepeatVector(n=X_train.shape[1])(LSTM2) # bottleneck layer
LSTM3 = keras.layers.LSTM(units=1, return_sequences=True)(bottleneck)
LSTM4 = keras.layers.LSTM(units=6, return_sequences=True, activation = 'selu')(LSTM3)

out1 = keras.layers.TimeDistributed(
    keras.layers.Dense(units=1, activation = 'linear')
  )(LSTM4)

out2 = keras.layers.TimeDistributed(
    keras.layers.Dense(units=1, activation = 'sigmoid')
  )(LSTM4)

model = Model(input_ae, outputs=[out1, out2]) 
model.compile(optimizer='adam', loss=["mae","binary_crossentropy"],
    loss_weights=[1.0, 1.0],) # this is trainable
history = model.fit(X_train, [X_train[:,:,0,np.newaxis], X_train[:,:,1,np.newaxis]],
                epochs=50,
                batch_size=3,
                shuffle=False) # observations are sorted by date !

However I am still getting the following errors regarding topology of the graph of my model. I am new to python and now I do not know whether my coding is wrong or there is some conceptual mistake. Predicted values of variable2 (binary) are still around 0.5 (between 0.4 and 0.6) and they are not pushed towards 0 or 1.

2020-05-25 13:44:33.862501: I tensorflow/core/platform/cpu_feature_guard.cc:142] Your CPU supports instructions that this TensorFlow binary was not compiled to use: AVX AVX2
2020-05-25 13:44:33.882555: I tensorflow/core/common_runtime/process_util.cc:147] Creating new thread pool with default inter op setting: 2. Tune using inter_op_parallelism_threads for best performance.
Epoch 1/50
2020-05-25 13:44:39.191662: E tensorflow/core/grappler/optimizers/meta_optimizer.cc:561] remapper failed: Invalid argument: MutableGraphView::MutableGraphView error: node 'loss/time_distributed_2_loss/binary_crossentropy/weighted_loss/concat' has self cycle fanin 'loss/time_distributed_2_loss/binary_crossentropy/weighted_loss/concat'.
2020-05-25 13:44:39.229395: E tensorflow/core/grappler/optimizers/dependency_optimizer.cc:717] Iteration = 0, topological sort failed with message: The graph couldn't be sorted in topological order.
2020-05-25 13:44:39.247559: E tensorflow/core/grappler/optimizers/dependency_optimizer.cc:717] Iteration = 1, topological sort failed with message: The graph couldn't be sorted in topological order.
2020-05-25 13:44:39.345620: E tensorflow/core/grappler/optimizers/meta_optimizer.cc:561] arithmetic_optimizer failed: Invalid argument: The graph couldn't be sorted in topological order.
2020-05-25 13:44:39.363350: E tensorflow/core/grappler/optimizers/meta_optimizer.cc:561] remapper failed: Invalid argument: MutableGraphView::MutableGraphView error: node 'loss/time_distributed_2_loss/binary_crossentropy/weighted_loss/concat' has self cycle fanin 'loss/time_distributed_2_loss/binary_crossentropy/weighted_loss/concat'.
2020-05-25 13:44:39.383818: E tensorflow/core/grappler/optimizers/dependency_optimizer.cc:717] Iteration = 0, topological sort failed with message: The graph couldn't be sorted in topological order.
2020-05-25 13:44:39.399577: E tensorflow/core/grappler/optimizers/dependency_optimizer.cc:717] Iteration = 1, topological sort failed with message: The graph couldn't be sorted in topological order.
2020-05-25 13:44:39.432358: W tensorflow/core/common_runtime/process_function_library_runtime.cc:697] Ignoring multi-device function optimization failure: Invalid argument: The graph couldn't be sorted in topological order.
36/36 [==============================] - 3s 82ms/step - loss: 0.9305 - time_distributed_1_loss: 0.2378 - time_distributed_2_loss: 0.6927
Epoch 2/50
36/36 [==============================] - 0s 2ms/step - loss: 0.8997 - time_distributed_1_loss: 0.2085 - time_distributed_2_loss: 0.6912

The error is each time only in first epoch, later not.

Answer 1

That's not an error, but it's definitely annoying. You can silence this with this line of code before your Tensorflow import :

import os
os.environ['TF_CPP_MIN_LOG_LEVEL'] = '3'

from tensorflow import keras # etc