karolpiczak / paper-2017-dcase Goto Github PK

root@e82b83a2c15c:/data/paper-2017-DCASE/Code# python ./run_amb.py -D gpu
Using Theano backend.
WARNING (theano.sandbox.cuda): The cuda backend is deprecated and will be removed in the next release (v0.10). Please switch to the gpuarray backend. You can get more information about how to switch at this URL:
https://github.com/Theano/Theano/wiki/Converting-to-the-new-gpu-back-end%28gpuarray%29

Using gpu device 0: GeForce 840M (CNMeM is disabled, cuDNN Mixed dnn version. The header is from one version, but we link with a different version (5110, 6021))
/opt/conda/envs/py35/lib/python3.5/site-packages/IPython/html.py:14: ShimWarning: The IPython.html package has been deprecated since IPython 4.0. You should import from notebook instead. IPython.html.widgets has moved to ipywidgets.
"IPython.html.widgets has moved to ipywidgets.", ShimWarning)
100%|███████████████████████████████████████████████████████████████████████████████████████████████████| 3110/3110 [00:00<00:00, 30326.38it/s]
100%|█████████████████████████████████████████████████████████████████████████████████████████████████████| 400/400 [00:00<00:00, 88027.79it/s]
100%|███████████████████████████████████████████████████████████████████████████████████████████████████| 1170/1170 [00:00<00:00, 87392.23it/s]
Input data parameters: mean = -46.0799, std = 18.322
/opt/conda/envs/py35/lib/python3.5/site-packages/keras/layers/core.py:630: UserWarning: output_shape argument not specified for layer softmax and cannot be automatically inferred with the Theano backend. Defaulting to output shape (None, 15, 1, 451) (same as input shape). If the expected output shape is different, specify it via the output_shape argument.
.format(self.name, input_shape))
Model layers / shapes / parameters:

• input_1 (None, 1, 200, 500) 0
• conv2d_1 (None, 1, 200, 500) 1,000,100
• batch_normalization_1(None, 100, 1, 451) 400
• leaky_re_lu_1 (None, 100, 1, 451) 0
• dropout_1 (None, 100, 1, 451) 0
• conv2d_2 (None, 100, 1, 451) 10,100
• batch_normalization_2(None, 100, 1, 451) 400
• leaky_re_lu_2 (None, 100, 1, 451) 0
• dropout_2 (None, 100, 1, 451) 0
• conv2d_3 (None, 100, 1, 451) 1,515
• softmax (None, 15, 1, 451) 0
• global_average_pooling2d_1(None, 15, 1, 451) 0
  Total: 1,012,515
  Epoch 1/500
  Traceback (most recent call last):
  File "./run_amb.py", line 94, in
  max_queue_size=10)
  File "/opt/conda/envs/py35/lib/python3.5/site-packages/keras/legacy/interfaces.py", line 87, in wrapper
  return func(*args, **kwargs)
  File "/opt/conda/envs/py35/lib/python3.5/site-packages/keras/engine/training.py", line 2147, in fit_generator
  class_weight=class_weight)
  File "/opt/conda/envs/py35/lib/python3.5/site-packages/keras/engine/training.py", line 1833, in train_on_batch
  check_batch_axis=True)
  File "/opt/conda/envs/py35/lib/python3.5/site-packages/keras/engine/training.py", line 1418, in _standardize_user_data
  exception_prefix='target')
  File "/opt/conda/envs/py35/lib/python3.5/site-packages/keras/engine/training.py", line 153, in _standardize_input_data
  str(array.shape))
  ValueError: Error when checking target: expected global_average_pooling2d_1 to have shape (None, 15) but got array with shape (32, 1)

But still I did not get where went wrong.