search

Media-Smart / vedadet

A single stage object detection toolbox based on PyTorch
Apache License 2.0
498 stars 128 forks source link

RuntimeError: CUDA error: no kernel image is available for execution on the device #18

Closed juliusyang97 closed 3 years ago

juliusyang97 commented 3 years ago

python configs/trainval/tinaface/test_widerface.py configs/trainval/tinaface/tinaface.py data/tinaface_r50_fpn_widerface.pth

loading annotations into memory... Done (t=0.00s) creating index... index created! [ ] 0/55, elapsed: 0s, ETA:Traceback (most recent call last): File "configs/trainval/tinaface/test_widerface.py", line 101, in <module> main() File "configs/trainval/tinaface/test_widerface.py", line 96, in main results = test(engine, data_loader, args.outdir) File "configs/trainval/tinaface/test_widerface.py", line 77, in test result = engine(data)[0] File "/home/yjq/miniconda3/envs/vedadet/lib/python3.8/site-packages/torch/nn/modules/module.py", line 727, in _call_impl result = self.forward(*input, **kwargs) File "/home/yjq/Research_traning/vedadet/vedacore/parallel/data_parallel.py", line 30, in forward return self.module(*inputs[0], **kwargs[0]) File "/home/yjq/miniconda3/envs/vedadet/lib/python3.8/site-packages/torch/nn/modules/module.py", line 727, in _call_impl result = self.forward(*input, **kwargs) File "/home/yjq/Research_traning/vedadet/vedadet/engines/val_engine.py", line 15, in forward return self.forward_impl(**data) File "/home/yjq/Research_traning/vedadet/vedadet/engines/val_engine.py", line 18, in forward_impl dets = self.infer(img, img_metas) File "/home/yjq/Research_traning/vedadet/vedadet/engines/infer_engine.py", line 115, in infer return self._simple_infer(img[0], img_metas[0]) File "/home/yjq/Research_traning/vedadet/vedadet/engines/infer_engine.py", line 57, in _simple_infer dets = self._get_raw_dets(img, img_metas) File "/home/yjq/Research_traning/vedadet/vedadet/engines/infer_engine.py", line 36, in _get_raw_dets feats = self.extract_feats(img) File "/home/yjq/Research_traning/vedadet/vedadet/engines/infer_engine.py", line 24, in extract_feats feats = self.model(img, train=False) File "/home/yjq/miniconda3/envs/vedadet/lib/python3.8/site-packages/torch/nn/modules/module.py", line 727, in _call_impl result = self.forward(*input, **kwargs) File "/home/yjq/Research_traning/vedadet/vedadet/models/detectors/single_stage_detector.py", line 48, in forward feats = self.forward_impl(x) File "/home/yjq/Research_traning/vedadet/vedadet/models/detectors/single_stage_detector.py", line 35, in forward_impl feats = self.backbone(x) File "/home/yjq/miniconda3/envs/vedadet/lib/python3.8/site-packages/torch/nn/modules/module.py", line 727, in _call_impl result = self.forward(*input, **kwargs) File "/home/yjq/Research_traning/vedadet/vedadet/models/backbones/resnet.py", line 624, in forward x = self.norm1(x) File "/home/yjq/miniconda3/envs/vedadet/lib/python3.8/site-packages/torch/nn/modules/module.py", line 727, in _call_impl result = self.forward(*input, **kwargs) File "/home/yjq/miniconda3/envs/vedadet/lib/python3.8/site-packages/torch/nn/modules/normalization.py", line 245, in forward return F.group_norm( File "/home/yjq/miniconda3/envs/vedadet/lib/python3.8/site-packages/torch/nn/functional.py", line 2111, in group_norm return torch.group_norm(input, num_groups, weight, bias, eps, RuntimeError: CUDA error: no kernel image is available for execution on the device

hxcai commented 3 years ago

@juliusyang97 It may be pytorch and cuda problem, see this for details.

juliusyang97 commented 3 years ago

@juliusyang97 It may be pytorch and cuda problem, see this for details.

thanks ,