Caught RuntimeError in DataLoader worker process 0 while running test.py for COCO

[alyssa121]

command: python test.py --weights_path yolov3.weights

error: Namespace(batch_size=8, class_path='data/coco.names', conf_thres=0.001, data_config='config/coco.data', img_size=416, iou_thres=0.5, model_def='config/yolov3.cfg', n_cpu=8, nms_thres=0.5, weights_path='yolov3.weights') Compute mAP... Detecting objects: 0%| | 0/625 [00:00<?, ?it/s]Traceback (most recent call last): File "test.py", line 99, in batch_size=8, File "test.py", line 36, in evaluate for batch_i, (_, imgs, targets) in enumerate(tqdm.tqdm(dataloader, desc="Detecting objects")): File "/home/bobo/anaconda3/envs/detectron/lib/python3.6/site-packages/tqdm/_tqdm.py", line 1022, in iter for obj in iterable: File "/home/bobo/anaconda3/envs/detectron/lib/python3.6/site-packages/torch/utils/data/dataloader.py", line 819, in next return self._process_data(data) File "/home/bobo/anaconda3/envs/detectron/lib/python3.6/site-packages/torch/utils/data/dataloader.py", line 846, in _process_data data.reraise() File "/home/bobo/anaconda3/envs/detectron/lib/python3.6/site-packages/torch/_utils.py", line 369, in reraise raise self.exc_type(msg) RuntimeError: Caught RuntimeError in DataLoader worker process 0. Original Traceback (most recent call last): File "/home/bobo/anaconda3/envs/detectron/lib/python3.6/site-packages/torch/utils/data/_utils/worker.py", line 178, in _worker_loop data = fetcher.fetch(index) File "/home/bobo/anaconda3/envs/detectron/lib/python3.6/site-packages/torch/utils/data/_utils/fetch.py", line 47, in fetch return self.collate_fn(data) File "/home/bobo/dxx/PyTorch-YOLOv3/utils/datasets.py", line 149, in collate_fn targets = torch.cat(targets, 0) RuntimeError: expected a non-empty list of Tensors

[hanrui15765510320]

i have same problem,how do you solve this problem?

[wydonglove]

i have same problem,how do you solve this problem?

[JingshanXu]

hey, have u guys solved the problem yet?

[QZ-cmd]

hey, have u guys solved the problem yet?

[ss32]

I think it might actually be a memory issue but haven't confirmed it yet. I'm seeing this when I load a large number of training samples in at once, but my code runs fine on smaller sets.

This is definitely a PyTorch issue though, not unique to this repo.

[ss32]

I think it might actually be a memory issue but haven't confirmed it yet. I'm seeing this when I load a large number of training samples in at once, but my code runs fine on smaller sets.

This is definitely a PyTorch issue though, not unique to this repo.

Confirmed it's a memory issue. Once training starts I see my available memory drop steadily as the epoch progresses. I'm training using the GPU but something is being stored in regular memory during each epoch.

[osaka004]

doing on colab but still getting error

[anas-zafar]

Has anyone been able to solve this issue?