I'm running Ubuntu 16.04.1, CUDA 8.0.26, and CudNN 5.1.5 following the Python 2 directions here
wavenet$ python wavenet.py predict with models/run_2016-09-14_11:32:09/config.json predict_seconds=1
Using TensorFlow backend.
I tensorflow/stream_executor/dso_loader.cc:111] successfully opened CUDA library libcublas.so.8.0 locally
I tensorflow/stream_executor/dso_loader.cc:111] successfully opened CUDA library libcudnn.so.5.1.5 locally
I tensorflow/stream_executor/dso_loader.cc:111] successfully opened CUDA library libcufft.so.8.0 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.8.0 locally
WARNING - root - Changed type of config entry "run_dir" from NoneType to unicode
WARNING - root - Changed type of config entry "optimizer.epsilon" from NoneType to float
INFO - wavenet - Running command 'predict'
WARNING - wavenet - No observers have been added to this run
INFO - wavenet - Started
INFO - predict - Using checkpoint from epoch: 37
INFO - predict - Saving to "models/run_2016-09-14_11:32:09/samples/sample_epoch-00037_01s__sample_seed-920639969.wav"
I tensorflow/core/common_runtime/gpu/gpu_device.cc:951] Found device 0 with properties:
name: TITAN X (Pascal)
major: 6 minor: 1 memoryClockRate (GHz) 1.531
pciBusID 0000:03:00.0
Total memory: 11.90GiB
Free memory: 11.38GiB
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: TITAN X (Pascal), pci bus id: 0000:03:00.0)
ERROR - wavenet - Failed after 0:00:01!
Traceback (most recent calls WITHOUT Sacred internals):
File "wavenet.py", line 224, in predict
model = build_model()
File "wavenet.py", line 158, in build_model
out, skip_out = residual_block(out)
File "wavenet.py", line 141, in residual_block
name='dilated_conv_%d_tanh_s%d' % (2 ** i, s), activation='tanh')(x)
File "/usr/local/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/local/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/local/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/local/lib/python2.7/dist-packages/keras/layers/convolutional.py", line 655, in call
filter_dilation=self.atrous_rate)
File "/usr/local/lib/python2.7/dist-packages/keras/backend/tensorflow_backend.py", line 1575, in conv2d
assert filter_dilation[0] == filter_dilation[1]
AssertionError
I just pushed a fix to basveeling/keraswavenet that should solve this problem. Try reinstalling it via pip and please let me know if you run into any other errors.
I'm running Ubuntu 16.04.1, CUDA 8.0.26, and CudNN 5.1.5 following the Python 2 directions here