Hello, thanks for your great work. but I have problem when I try to train this network with my data.
Here is the trace back:
Traceback (most recent call last):
File "E:\00_project\01_mouse_robot\01_code\detectInBlur\train.py", line 488, in
main(args)
File "E:\00_project\01_mouse_robot\01_code\detectInBlur\train.py", line 306, in main
train_one_epoch(model = model,
File "E:\00_project\01_mouse_robot\01_code\detectInBlur\engine.py", line 74, in train_one_epoch
for images_CPU, targets, blur_dicts in metric_logger.log_every(data_loader, print_freq, header):
File "E:\00_project\01_mouse_robot\01_code\detectInBlur\utils.py", line 670, in log_every
for obj in iterable:
File "D:\01_program_file\conda\envs\pytorch-env\lib\site-packages\torch\utils\data\dataloader.py", line 517, in next
data = self._next_data()
File "D:\01_program_file\conda\envs\pytorch-env\lib\site-packages\torch\utils\data\dataloader.py", line 557, in _next_data
data = self._dataset_fetcher.fetch(index) # may raise StopIteration
File "D:\01_program_file\conda\envs\pytorch-env\lib\site-packages\torch\utils\data_utils\fetch.py", line 48, in fetch
print("dataset = {}".format(self.dataset[idx]))
File "D:\01_program_file\conda\envs\pytorch-env\lib\site-packages\torch\utils\data\dataset.py", line 330, in getitem
return self.dataset[self.indices[idx]]
File "E:\00_project\01_mouse_robot\01_code\detectInBlur\coco_utils.py", line 239, in getitem
img, target, blur_dict = self._transforms(img, target)
File "E:\00_project\01_mouse_robot\01_code\detectInBlur\transforms.py", line 46, in call
image, target, blur_dict = t(image, target, blur_dict)
File "E:\00_project\01_mouse_robot\01_code\detectInBlur\coco_utils.py", line 73, in call
masks = convert_coco_poly_to_mask(segmentations, h, w)
File "E:\00_project\01_mouse_robot\01_code\detectInBlur\coco_utils.py", line 37, in convert_coco_poly_to_mask
rles = coco_mask.frPyObjects(polygons, height, width)
File "pycocotools_mask.pyx", line 293, in pycocotools._mask.frPyObjects
IndexError: list index out of range
Process finished with exit code 1
It works with standard coco2017 dataset, but failed with my own dataset. My data set has more than 1000 elements in the training set so I don't know why "list index out of range".
mohammed-amr
