search

tianzhi0549 / FCOS

FCOS: Fully Convolutional One-Stage Object Detection (ICCV'19)
https://arxiv.org/abs/1904.01355
Other
3.28k stars 630 forks source link

IndexError: list index out of range #79

Closed qianzhang2018 closed 5 years ago

qianzhang2018 commented 5 years ago

Traceback (most recent call last): File "tools/train_net.py", line 176, in main() File "tools/train_net.py", line 169, in main model = train(cfg, args.local_rank, args.distributed) File "tools/train_net.py", line 75, in train arguments, File "/home/administrator/USPIntern/zq/FCOS/maskrcnn_benchmark/engine/trainer.py", line 56, in dotrain for iteration, (images, targets, ) in enumerate(data_loader, start_iter): File "/home/administrator/.local/lib/python3.6/site-packages/torch/utils/data/dataloader.py", line 637, in next return self._process_next_batch(batch) File "/home/administrator/.local/lib/python3.6/site-packages/torch/utils/data/dataloader.py", line 658, in _process_next_batch raise batch.exc_type(batch.exc_msg) IndexError: Traceback (most recent call last): File "/home/administrator/.local/lib/python3.6/site-packages/torch/utils/data/dataloader.py", line 138, in _worker_loop samples = collate_fn([dataset[i] for i in batch_indices]) File "/home/administrator/.local/lib/python3.6/site-packages/torch/utils/data/dataloader.py", line 138, in samples = collate_fn([dataset[i] for i in batch_indices]) File "/home/administrator/.local/lib/python3.6/site-packages/torch/utils/data/dataset.py", line 81, in getitem return self.datasets[dataset_idx][sample_idx] File "/home/administrator/USPIntern/zq/FCOS/maskrcnn_benchmark/data/datasets/coco.py", line 107, in getitem target = target.clip_to_image(remove_empty=True) File "/home/administrator/USPIntern/zq/FCOS/maskrcnn_benchmark/structures/bounding_box.py", line 223, in clip_to_image return self[keep] File "/home/administrator/USPIntern/zq/FCOS/maskrcnn_benchmark/structures/bounding_box.py", line 208, in getitem bbox.add_field(k, v[item]) File "/home/administrator/USPIntern/zq/FCOS/maskrcnn_benchmark/structures/segmentation_mask.py", line 513, in getitem selected_instances = self.instances.getitem(item) File "/home/administrator/USPIntern/zq/FCOS/maskrcnn_benchmark/structures/segmentation_mask.py", line 422, in getitem selected_polygons.append(self.polygons[i]) IndexError: list index out of range

can you help me ?

tianzhi0549 commented 5 years ago

@qianzhang2018 We don't need mask annotations. You can remove this line https://github.com/tianzhi0549/FCOS/blob/928c610dbae256242a2514fe212f9b10cc6fe0fc/maskrcnn_benchmark/data/datasets/coco.py#L84 to avoid the error.

qianzhang2018 commented 5 years ago

@tianzhi0549 it works.Thanks,it is very kind of you.

Kongsea commented 5 years ago

In my case, line 83 and 84 both need to be removed to avoid this error:

masks = SegmentationMask(masks, img.size, mode='poly')
target.add_field("masks", masks)
imyhxy commented 5 years ago

@tianzhi0549 Why only some users will encounter this problem？

tianzhi0549 commented 5 years ago

@imyhxy It might be related to their torchvision version.

lucasjinreal commented 4 years ago

@tianzhi0549 I am training CenterMask and got this error, weired. And I do need mask annotation.