About problems that arise when running the test.py script #123
Description
Thanks for your great contribution, I have encountered some problems while using your script:
I changed the entry part of test.py to fix the use of config and checkpoint：
if name == 'main':
parser = argparse.ArgumentParser(description='Hyperparams')
parser.add_argument('--config', help='config file path', default='config/pan_pp/pan_pp_r18_ic15_736_det_only.py')
parser.add_argument('--checkpoint', nargs='?', type=str, default='checkpoints/pan_r18_ic15/panpp_r18_ic15_det.pth.tar')
parser.add_argument('--report_speed', action='store_true', default=True)
parser.add_argument('--vis', action='store_true')
parser.add_argument('--debug', action='store_true')
args = parser.parse_args()
main(args)
In addition, I have prepared the data set in a format, i got an error when i python test.py, the error message is as follows:
Traceback (most recent call last):
File "test.py", line 168, in
main(args)
File "test.py", line 156, in main
test(test_loader, model, cfg)
File "test.py", line 81, in test
for idx, data in enumerate(test_loader):
File "/opt/conda/lib/python3.8/site-packages/torch/utils/data/dataloader.py", line 530, in next
data = self._next_data()
File "/opt/conda/lib/python3.8/site-packages/torch/utils/data/dataloader.py", line 1224, in _next_data
return self._process_data(data)
File "/opt/conda/lib/python3.8/site-packages/torch/utils/data/dataloader.py", line 1250, in _process_data
data.reraise()
File "/opt/conda/lib/python3.8/site-packages/torch/_utils.py", line 457, in reraise
raise exception
TypeError: Caught TypeError in DataLoader worker process 0.
Original Traceback (most recent call last):
File "/opt/conda/lib/python3.8/site-packages/torch/utils/data/_utils/worker.py", line 287, in _worker_loop
data = fetcher.fetch(index)
File "/opt/conda/lib/python3.8/site-packages/torch/utils/data/_utils/fetch.py", line 49, in fetch
data = [self.dataset[idx] for idx in possibly_batched_index]
File "/opt/conda/lib/python3.8/site-packages/torch/utils/data/_utils/fetch.py", line 49, in
data = [self.dataset[idx] for idx in possibly_batched_index]
File "/data/project/pan_pp/dataset/pan_pp/pan_pp_ic15.py", line 482, in getitem
return self.prepare_test_data(index)
File "/data/project/pan_pp/dataset/pan_pp/pan_pp_ic15.py", line 465, in prepare_test_data
img = transform_pic(img)
File "/opt/conda/lib/python3.8/site-packages/torchvision/transforms/transforms.py", line 95, in call
img = t(img)
File "/opt/conda/lib/python3.8/site-packages/torchvision/transforms/transforms.py", line 135, in call
return F.to_tensor(pic)
File "/opt/conda/lib/python3.8/site-packages/torchvision/transforms/functional.py", line 147, in to_tensor
img = torch.from_numpy(np.array(pic, mode_to_nptype.get(pic.mode, np.uint8), copy=True))
TypeError: array() takes 1 positional argument but 2 were given
I checked img = transforms.ToTensor()(img) in dataset/pan_pp/pan_pp_ic15.py and there was no error in its type. I wondered what to do in this case.