Time Distributed wrapper: You must feed a value for tensor for dtype=bool, Invalid argument error

[Rhuax]

I'm trying to build a network with both convolutional and lstm layers. I'm wrapping the Convolutional,activation,max pooling, drop out and flatten layer in a TimeDistributed() layer. When my code reaches the train_on_batch() method I have a illegal argument exception thrown by tensorflow, so I think it is some keras problem. Here it is my code:

def get_model(): 
    model=Sequential()
    model.add(TimeDistributed(Conv2D(10,(3,3)),input_shape=(100,60,80,1)))
    model.add(TimeDistributed(Activation('tanh')))
    model.add(TimeDistributed(Conv2D(10,(3,3))))
    model.add(TimeDistributed(Activation('tanh')))
    model.add(TimeDistributed(MaxPooling2D(pool_size=(2,2))))
    model.add(TimeDistributed(Dropout(0.25)))
    model.add(TimeDistributed(Flatten()))
    model.add(LSTM(1000,return_sequences=True))
    model.add(TimeDistributed(Dense(1,activation='relu')))
    return model
    model=get_model()
model.summary()
rms=RMSprop(lr=0.001)
model.compile(optimizer=rms,loss='mean_squared_error')
for e in range(10):#epoch
    for X,Y in gen('data/train.mp4','train'):#<- this is my custom batch generator
        l=model.train:_on_batch(X,Y)
    model.reset_states()

It gives me :

> Using TensorFlow backend.
> _________________________________________________________________
> Layer (type)                 Output Shape              Param #   
> =================================================================
> time_distributed_1 (TimeDist (None, 100, 58, 78, 10)   100       
> _________________________________________________________________
> time_distributed_2 (TimeDist (None, 100, 58, 78, 10)   0         
> _________________________________________________________________
> time_distributed_3 (TimeDist (None, 100, 56, 76, 10)   910       
> _________________________________________________________________
> time_distributed_4 (TimeDist (None, 100, 56, 76, 10)   0         
> _________________________________________________________________
> time_distributed_5 (TimeDist (None, 100, 28, 38, 10)   0         
> _________________________________________________________________
> time_distributed_6 (TimeDist (None, 100, 28, 38, 10)   0         
> _________________________________________________________________
> time_distributed_7 (TimeDist (None, 100, 10640)        0         
> _________________________________________________________________
> lstm_1 (LSTM)                (None, 100, 1000)         46564000  
> _________________________________________________________________
> time_distributed_8 (TimeDist (None, 100, 1)            1001      
> =================================================================
> Total params: 46,566,011
> Trainable params: 46,566,011
> Non-trainable params: 0
> _________________________________________________________________
> epoca:0
> (1, 100, 60, 80, 1)
> (1, 100, 1)
> 2017-05-03 16:39:04.437304: W tensorflow/core/framework/op_kernel.cc:1152] Invalid argument: You must feed a value for placeholder tensor 'time_distributed_6/keras_learning_phase' with dtype bool
>    [[Node: time_distributed_6/keras_learning_phase = Placeholder[dtype=DT_BOOL, shape=[], _device="/job:localhost/replica:0/task:0/gpu:0"]()]]
> Traceback (most recent call last):
>   File "/usr/local/lib/python3.5/dist-packages/tensorflow/python/client/session.py", line 1039, in _do_call
>     return fn(*args)
>   File "/usr/local/lib/python3.5/dist-packages/tensorflow/python/client/session.py", line 1021, in _run_fn
>     status, run_metadata)
>   File "/usr/lib/python3.5/contextlib.py", line 66, in __exit__
>     next(self.gen)
>   File "/usr/local/lib/python3.5/dist-packages/tensorflow/python/framework/errors_impl.py", line 466, in raise_exception_on_not_ok_status
>     pywrap_tensorflow.TF_GetCode(status))
> tensorflow.python.framework.errors_impl.InvalidArgumentError: You must feed a value for placeholder tensor 'time_distributed_6/keras_learning_phase' with dtype bool
>    [[Node: time_distributed_6/keras_learning_phase = Placeholder[dtype=DT_BOOL, shape=[], _device="/job:localhost/replica:0/task:0/gpu:0"]()]]
>    [[Node: mul_1/_43 = _Recv[client_terminated=false, recv_device="/job:localhost/replica:0/task:0/cpu:0", send_device="/job:localhost/replica:0/task:0/gpu:0", send_device_incarnation=1, tensor_name="edge_1414_mul_1", tensor_type=DT_FLOAT, _device="/job:localhost/replica:0/task:0/cpu:0"]()]]
> 
> During handling of the above exception, another exception occurred:
> 
> Traceback (most recent call last):
>   File "/home/crow/PycharmProjects/Speed_challenge/main.py", line 78, in <module>
>     l=model.train_on_batch(X,Y)
>   File "/usr/local/lib/python3.5/dist-packages/keras/models.py", line 944, in train_on_batch
>     class_weight=class_weight)
>   File "/usr/local/lib/python3.5/dist-packages/keras/engine/training.py", line 1633, in train_on_batch
>     outputs = self.train_function(ins)
>   File "/usr/local/lib/python3.5/dist-packages/keras/backend/tensorflow_backend.py", line 2229, in __call__
>     feed_dict=feed_dict)
>   File "/usr/local/lib/python3.5/dist-packages/tensorflow/python/client/session.py", line 778, in run
>     run_metadata_ptr)
>   File "/usr/local/lib/python3.5/dist-packages/tensorflow/python/client/session.py", line 982, in _run
>     feed_dict_string, options, run_metadata)
>   File "/usr/local/lib/python3.5/dist-packages/tensorflow/python/client/session.py", line 1032, in _do_run
>     target_list, options, run_metadata)
>   File "/usr/local/lib/python3.5/dist-packages/tensorflow/python/client/session.py", line 1052, in _do_call
>     raise type(e)(node_def, op, message)
> tensorflow.python.framework.errors_impl.InvalidArgumentError: You must feed a value for placeholder tensor 'time_distributed_6/keras_learning_phase' with dtype bool
>    [[Node: time_distributed_6/keras_learning_phase = Placeholder[dtype=DT_BOOL, shape=[], _device="/job:localhost/replica:0/task:0/gpu:0"]()]]
>    [[Node: mul_1/_43 = _Recv[client_terminated=false, recv_device="/job:localhost/replica:0/task:0/cpu:0", send_device="/job:localhost/replica:0/task:0/gpu:0", send_device_incarnation=1, tensor_name="edge_1414_mul_1", tensor_type=DT_FLOAT, _device="/job:localhost/replica:0/task:0/cpu:0"]()]]
> 
> Caused by op 'time_distributed_6/keras_learning_phase', defined at:
>   File "/home/crow/PycharmProjects/Speed_challenge/main.py", line 65, in <module>
>     model=get_model()
>   File "/home/crow/PycharmProjects/Speed_challenge/main.py", line 57, in get_model
>     model.add(TimeDistributed(Dropout(0.25)))
>   File "/usr/local/lib/python3.5/dist-packages/keras/models.py", line 466, in add
>     output_tensor = layer(self.outputs[0])
>   File "/usr/local/lib/python3.5/dist-packages/keras/engine/topology.py", line 585, in __call__
>     output = self.call(inputs, **kwargs)
>   File "/usr/local/lib/python3.5/dist-packages/keras/layers/wrappers.py", line 177, in call
>     y = self.layer.call(inputs)  # (num_samples * timesteps, ...)
>   File "/usr/local/lib/python3.5/dist-packages/keras/layers/core.py", line 111, in call
>     training=training)
>   File "/usr/local/lib/python3.5/dist-packages/keras/backend/tensorflow_backend.py", line 2559, in in_train_phase
>     training = learning_phase()
>   File "/usr/local/lib/python3.5/dist-packages/keras/backend/tensorflow_backend.py", line 112, in learning_phase
>     name='keras_learning_phase')
>   File "/usr/local/lib/python3.5/dist-packages/tensorflow/python/ops/array_ops.py", line 1507, in placeholder
>     name=name)
>   File "/usr/local/lib/python3.5/dist-packages/tensorflow/python/ops/gen_array_ops.py", line 1997, in _placeholder
>     name=name)
>   File "/usr/local/lib/python3.5/dist-packages/tensorflow/python/framework/op_def_library.py", line 768, in apply_op
>     op_def=op_def)
>   File "/usr/local/lib/python3.5/dist-packages/tensorflow/python/framework/ops.py", line 2336, in create_op
>     original_op=self._default_original_op, op_def=op_def)
>   File "/usr/local/lib/python3.5/dist-packages/tensorflow/python/framework/ops.py", line 1228, in __init__
>     self._traceback = _extract_stack()
> 
> InvalidArgumentError (see above for traceback): You must feed a value for placeholder tensor 'time_distributed_6/keras_learning_phase' with dtype bool
>    [[Node: time_distributed_6/keras_learning_phase = Placeholder[dtype=DT_BOOL, shape=[], _device="/job:localhost/replica:0/task:0/gpu:0"]()]]
>    [[Node: mul_1/_43 = _Recv[client_terminated=false, recv_device="/job:localhost/replica:0/task:0/cpu:0", send_device="/job:localhost/replica:0/task:0/gpu:0", send_device_incarnation=1, tensor_name="edge_1414_mul_1", tensor_type=DT_FLOAT, _device="/job:localhost/replica:0/task:0/cpu:0"]()]]

• [x] Check that you are up-to-date with the master branch of Keras. You can update with: pip install git+git://github.com/fchollet/keras.git --upgrade --no-deps

• [x] If running on TensorFlow, check that you are up-to-date with the latest version. The installation instructions can be found here.

• [ ] If running on Theano, check that you are up-to-date with the master branch of Theano. You can update with: pip install git+git://github.com/Theano/Theano.git --upgrade --no-deps

• [x] Provide a link to a GitHub Gist of a Python script that can reproduce your issue (or just copy the script here if it is short).

[StefPac]

I think this is the same as https://github.com/fchollet/keras/issues/5934

[Rhuax]

I'm closing the issue because it is the same as #5934 .