Exception: Layer timedistributeddense_1 requires to know the length of its input, but it could not be inferred automatically.

[andrenajp]

Using TensorFlow backend.
Loading training data
Finished loading training data
/usr/lib/python2.7/dist-packages/keras/layers/core.py:1112: UserWarning: TimeDistributedDense is deprecated, please use TimeDistributed(Dense(...)) instead.
warnings.warn('TimeDistributedDense is deprecated, '
Traceback (most recent call last):
File "train.py", line 27, in
model = network_utils.create_lstm_network(num_frequency_dimensions=freq_space_dims, num_hidden_dimensions=hidden_dims)
File "/home/andrena/Bureau/GRUV-master/nn_utils/network_utils.py", line 8, in create_lstm_network
model.add(TimeDistributedDense(input_dim=num_frequency_dimensions, output_dim=num_hidden_dimensions))
File "/usr/lib/python2.7/dist-packages/keras/models.py", line 276, in add
layer.create_input_layer(batch_input_shape, input_dtype)
File "/usr/lib/python2.7/dist-packages/keras/engine/topology.py", line 370, in create_input_layer
self(x)
File "/usr/lib/python2.7/dist-packages/keras/engine/topology.py", line 514, in call
self.add_inbound_node(inbound_layers, node_indices, tensor_indices)
File "/usr/lib/python2.7/dist-packages/keras/engine/topology.py", line 572, in add_inbound_node
Node.create_node(self, inbound_layers, node_indices, tensor_indices)
File "/usr/lib/python2.7/dist-packages/keras/engine/topology.py", line 149, in create_node
output_tensors = to_list(outbound_layer.call(input_tensors[0], mask=input_masks[0]))
File "/usr/lib/python2.7/dist-packages/keras/layers/core.py", line 1185, in call
' requires to know the length of its input, '
Exception: Layer timedistributeddense_1 requires to know the length of its input, but it could not be inferred automatically. Specify it manually by passing an input_shape argument to the first layer in your model.

[piteight]

Hi, I have the same error :(
dataset is 3 files, two of them are 1 hour long, and one have 3 minutes

[piteight]

My output:
Using TensorFlow backend.
I tensorflow/stream_executor/dso_loader.cc:111] successfully opened CUDA library libcublas.so locally
I tensorflow/stream_executor/dso_loader.cc:111] successfully opened CUDA library libcudnn.so locally
I tensorflow/stream_executor/dso_loader.cc:111] successfully opened CUDA library libcufft.so locally
I tensorflow/stream_executor/dso_loader.cc:111] successfully opened CUDA library libcuda.so.1 locally
I tensorflow/stream_executor/dso_loader.cc:111] successfully opened CUDA library libcurand.so locally
Loading training data
Finished loading training data
/home/basia/keras/keras/layers/core.py:1112: UserWarning: TimeDistributedDense is deprecated, please use TimeDistributed(Dense(...)) instead.
warnings.warn('TimeDistributedDense is deprecated, '
I tensorflow/stream_executor/cuda/cuda_gpu_executor.cc:925] successful NUMA node read from SysFS had negative value (-1), but there must be at least one NUMA node, so returning NUMA node zero
I tensorflow/core/common_runtime/gpu/gpu_device.cc:951] Found device 0 with properties:
name: GeForce GTX 750
major: 5 minor: 0 memoryClockRate (GHz) 1.137
pciBusID 0000:01:00.0
Total memory: 1.95GiB
Free memory: 1.72GiB
I tensorflow/core/common_runtime/gpu/gpu_device.cc:972] DMA: 0
I tensorflow/core/common_runtime/gpu/gpu_device.cc:982] 0: Y
I tensorflow/core/common_runtime/gpu/gpu_device.cc:1041] Creating TensorFlow device (/gpu:0) -> (device: 0, name: GeForce GTX 750, pci bus id: 0000:01:00.0)
Traceback (most recent call last):
File "train.py", line 27, in
model = network_utils.create_lstm_network(num_frequency_dimensions=freq_space_dims, num_hidden_dimensions=hidden_dims)
File "/media/basia/4e262056-f01f-4d05-a453-9e58b9a1a8da/GRUV/nn_utils/network_utils.py", line 8, in create_lstm_network
model.add(TimeDistributedDense(input_dim=num_frequency_dimensions, output_dim=num_hidden_dimensions))
File "/home/basia/keras/keras/models.py", line 276, in add
layer.create_input_layer(batch_input_shape, input_dtype)
File "/home/basia/keras/keras/engine/topology.py", line 370, in create_input_layer
self(x)
File "/home/basia/keras/keras/engine/topology.py", line 514, in call
self.add_inbound_node(inbound_layers, node_indices, tensor_indices)
File "/home/basia/keras/keras/engine/topology.py", line 572, in add_inbound_node
Node.create_node(self, inbound_layers, node_indices, tensor_indices)
File "/home/basia/keras/keras/engine/topology.py", line 149, in create_node
output_tensors = to_list(outbound_layer.call(input_tensors[0], mask=input_masks[0]))
File "/home/basia/keras/keras/layers/core.py", line 1185, in call
' requires to know the length of its input, '
Exception: Layer timedistributeddense_1 requires to know the length of its input, but it could not be inferred automatically. Specify it manually by passing an input_shape argument to the first layer in your model.

[piteight]

Solution is downgrading keras to version 0.1.0 . :)
Newest keras have some changes in naming and using timedistributedense and other stuff. I'm new to keras stuff, but i think it might be easily changed in nn_utils, where this network parameters are described.

[akgun1]

I am setting up my system and currently having the same issue.
@piteight Are you using Theano or TensorFlow with keras version 0.1.0 ? I have TensorFlow installed but after doing the "sudo python setup.py install" I get an import error saying no module named keras.modules.

[piteight]

Meybe this will work pip install https://github.com/fchollet/keras/tarball/0.1.0
Im using Theano, beacuse I read, that GRUV isnt compatibile with TensorFlow right now.

[akgun1]

@piteight Thank you, it seems to be working now.

I uninstalled keras and re-installed using piteight's solution. Also, I switched Keras's backend from the default TensorFlow to Theano (instructions here: https://keras.io/backend/).

[mattpearson]

For those who want to use Keras version 1.1.1 (currently the latest, as of 11/12/16) then you can adopt the changes in my repo: https://github.com/mattpearson/GRUV