Epoch 1 average training loss = 8.500

  0%|          | 0/40 [00:00<?, ?it/s]/home/s.starace/.conda/envs/condaEnv/lib/python3.6/site-packages/numpy/core/fromnumeric.py:58: UserWarning: This overload of nonzero is deprecated:
	nonzero()
Consider using one of the following signatures instead:
	nonzero(*, bool as_tuple) (Triggered internally at  /opt/conda/conda-bld/pytorch_1603729128610/work/torch/csrc/utils/python_arg_parser.cpp:882.)
  return bound(*args, **kwds)

  0%|          | 0/40 [00:00<?, ?it/s]
Traceback (most recent call last):
  File "/home/s.starace/.conda/envs/condaEnv/lib/python3.6/site-packages/numpy/core/fromnumeric.py", line 58, in _wrapfunc
    return bound(*args, **kwds)
TypeError: transpose() received an invalid combination of arguments - got (NoneType), but expected one of:
 * (name dim0, name dim1)
 * (int dim0, int dim1)


During handling of the above exception, another exception occurred:

Traceback (most recent call last):
  File "KITTI_ft.py", line 172, in <module>
    main()
  File "KITTI_ft.py", line 151, in main
    test_loss = test(imgL, imgR, disp_L)
  File "KITTI_ft.py", line 115, in test
    index = np.argwhere(true_disp > 0)
  File "<__array_function__ internals>", line 6, in argwhere
  File "/home/s.starace/.conda/envs/condaEnv/lib/python3.6/site-packages/numpy/core/numeric.py", line 584, in argwhere
    return transpose(nonzero(a))
  File "<__array_function__ internals>", line 6, in transpose
  File "/home/s.starace/.conda/envs/condaEnv/lib/python3.6/site-packages/numpy/core/fromnumeric.py", line 653, in transpose
    return _wrapfunc(a, 'transpose', axes)
  File "/home/s.starace/.conda/envs/condaEnv/lib/python3.6/site-packages/numpy/core/fromnumeric.py", line 67, in _wrapfunc
    return _wrapit(obj, method, *args, **kwds)
  File "/home/s.starace/.conda/envs/condaEnv/lib/python3.6/site-packages/numpy/core/fromnumeric.py", line 44, in _wrapit
    result = getattr(asarray(obj), method)(*args, **kwds)
  File "/home/s.starace/.conda/envs/condaEnv/lib/python3.6/site-packages/numpy/core/_asarray.py", line 83, in asarray
    return array(a, dtype, copy=False, order=order)
  File "/home/s.starace/.conda/envs/condaEnv/lib/python3.6/site-packages/torch/tensor.py", line 630, in __array__
    return self.numpy()
TypeError: can't convert cuda:0 device type tensor to numpy. Use Tensor.cpu() to copy the tensor to host memory first.