lromul / argus-tgs-salt Goto Github PK

first, I run make_inpaint_images.py, I get images148 and masks148;
then, I run train_folds.py from mos-fpn-lovase-se-resnext50-001, I get this error:
`2018-11-12 08:59:01,756 ERROR Traceback (most recent call last):
File "/home/szx/Software/anaconda3/envs/torch-py3.7/lib/python3.7/site-packages/torch/utils/data/dataloader.py", line 106, in _worker_loop
samples = collate_fn([dataset[i] for i in batch_indices])
File "/home/szx/Software/anaconda3/envs/torch-py3.7/lib/python3.7/site-packages/torch/utils/data/dataloader.py", line 106, in
samples = collate_fn([dataset[i] for i in batch_indices])
File "/media/files/szx/argus-tgs-salt-master/src/dataset.py", line 57, in getitem
input = self.depth_transform(image, depth)
File "/media/files/szx/argus-tgs-salt-master/src/transforms.py", line 332, in call
input = np.stack([image, image, image], axis=2)
File "/home/szx/Software/anaconda3/envs/torch-py3.7/lib/python3.7/site-packages/numpy/core/shape_base.py", line 356, in stack
axis = normalize_axis_index(axis, result_ndim)
numpy.core._internal.AxisError: axis 2 is out of bounds for array of dimension 1
Traceback (most recent call last):
File "/media/files/szx/argus-tgs-salt-master/argus/engine/engine.py", line 69, in run
for batch in data_loader:
File "/home/szx/Software/anaconda3/envs/torch-py3.7/lib/python3.7/site-packages/torch/utils/data/dataloader.py", line 336, in next
return self._process_next_batch(batch)
File "/home/szx/Software/anaconda3/envs/torch-py3.7/lib/python3.7/site-packages/torch/utils/data/dataloader.py", line 357, in _process_next_batch
raise batch.exc_type(batch.exc_msg)
numpy.core._internal.AxisError: Traceback (most recent call last):
File "/home/szx/Software/anaconda3/envs/torch-py3.7/lib/python3.7/site-packages/torch/utils/data/dataloader.py", line 106, in _worker_loop
samples = collate_fn([dataset[i] for i in batch_indices])
File "/home/szx/Software/anaconda3/envs/torch-py3.7/lib/python3.7/site-packages/torch/utils/data/dataloader.py", line 106, in
samples = collate_fn([dataset[i] for i in batch_indices])
File "/media/files/szx/argus-tgs-salt-master/src/dataset.py", line 57, in getitem
input = self.depth_transform(image, depth)
File "/media/files/szx/argus-tgs-salt-master/src/transforms.py", line 332, in call
input = np.stack([image, image, image], axis=2)
File "/home/szx/Software/anaconda3/envs/torch-py3.7/lib/python3.7/site-packages/numpy/core/shape_base.py", line 356, in stack
axis = normalize_axis_index(axis, result_ndim)
numpy.core._internal.AxisError: axis 2 is out of bounds for array of dimension 1

Traceback (most recent call last):
File "train_folds.py", line 100, in
train_fold(save_fold_dir, train_folds, val_folds)
File "train_folds.py", line 78, in train_fold
metrics=['crop_iout'])
File "/media/files/szx/argus-tgs-salt-master/argus/model/model.py", line 95, in fit
self.validate(val_loader, metrics, val_callbacks)
File "/media/files/szx/argus-tgs-salt-master/argus/model/model.py", line 154, in validate
return val_engine.run(val_loader).metrics
File "/media/files/szx/argus-tgs-salt-master/argus/engine/engine.py", line 86, in run
raise e
File "/media/files/szx/argus-tgs-salt-master/argus/engine/engine.py", line 69, in run
for batch in data_loader:
File "/home/szx/Software/anaconda3/envs/torch-py3.7/lib/python3.7/site-packages/torch/utils/data/dataloader.py", line 336, in next
return self._process_next_batch(batch)
File "/home/szx/Software/anaconda3/envs/torch-py3.7/lib/python3.7/site-packages/torch/utils/data/dataloader.py", line 357, in _process_next_batch
raise batch.exc_type(batch.exc_msg)
numpy.core._internal.AxisError: Traceback (most recent call last):
File "/home/szx/Software/anaconda3/envs/torch-py3.7/lib/python3.7/site-packages/torch/utils/data/dataloader.py", line 106, in _worker_loop
samples = collate_fn([dataset[i] for i in batch_indices])
File "/home/szx/Software/anaconda3/envs/torch-py3.7/lib/python3.7/site-packages/torch/utils/data/dataloader.py", line 106, in
samples = collate_fn([dataset[i] for i in batch_indices])
File "/media/files/szx/argus-tgs-salt-master/src/dataset.py", line 57, in getitem
input = self.depth_transform(image, depth)
File "/media/files/szx/argus-tgs-salt-master/src/transforms.py", line 332, in call
input = np.stack([image, image, image], axis=2)
File "/home/szx/Software/anaconda3/envs/torch-py3.7/lib/python3.7/site-packages/numpy/core/shape_base.py", line 356, in stack
axis = normalize_axis_index(axis, result_ndim)
numpy.core._internal.AxisError: axis 2 is out of bounds for array of dimension 1
`
Can you give me some advice? Thank you very much!