推理报错

[phpdancer]

使用下面命令推理报错，有的视频可以，有的视频不行？
python demo/restoration_video_demo.py configs/restorers/basicvsr_plusplus/basicvsr_plusplus_c128n25_600k_ntire_decompress_track1.py model_zoo/basicvsr_plusplus_c128n25_ntire_decompress_track1_20210223-7b2eba02.pth datasets/video_test/20221010161022414241665389223023_old.mp4 datasets/video_test/output/20221010161022414241665389223023_old_decompress_track1.mp4 --max-seq-len 12

报错信息：
Traceback (most recent call last):
File "demo/restoration_video_demo.py", line 97, in
main()
File "demo/restoration_video_demo.py", line 71, in main
output = restoration_video_inference(model, args.input_dir,
File "/home/fridayzhu/mmediting/mmedit/apis/restoration_video_inference.py", line 115, in restoration_video_inference
result.append(model(lq=data_i, test_mode=True)['output'].cpu())
File "/home/anaconda3/envs/mmedit/lib/python3.8/site-packages/torch/nn/modules/module.py", line 1130, in _call_impl
return forward_call(*input, **kwargs)
File "/home/anaconda3/envs/mmedit/lib/python3.8/site-packages/mmcv/runner/fp16_utils.py", line 116, in new_func
return old_func(*args, **kwargs)
File "/home/fridayzhu/mmediting/mmedit/models/restorers/basic_restorer.py", line 75, in forward
return self.forward_test(lq, gt, **kwargs)
File "/home/fridayzhu/mmediting/mmedit/models/restorers/basicvsr.py", line 173, in forward_test
output = self.forward_ensemble(lq, self.generator)
File "/home/anaconda3/envs/mmedit/lib/python3.8/site-packages/torch/nn/modules/module.py", line 1130, in _call_impl
return forward_call(*input, **kwargs)
File "/home/fridayzhu/mmediting/mmedit/models/common/ensemble.py", line 96, in forward
outputs = self.spatial_ensemble(imgs, model)
File "/home/fridayzhu/mmediting/mmedit/models/common/ensemble.py", line 71, in spatial_ensemble
output_list = [model(t.to(imgs.device)).cpu() for t in img_list]
File "/home/fridayzhu/mmediting/mmedit/models/common/ensemble.py", line 71, in
output_list = [model(t.to(imgs.device)).cpu() for t in img_list]
File "/home/anaconda3/envs/mmedit/lib/python3.8/site-packages/torch/nn/modules/module.py", line 1130, in _call_impl
return forward_call(*input, **kwargs)
File "/home/fridayzhu/mmediting/mmedit/models/backbones/sr_backbones/basicvsr_pp.py", line 347, in forward
feats = self.propagate(feats, flows, module)
File "/home/fridayzhu/mmediting/mmedit/models/backbones/sr_backbones/basicvsr_pp.py", line 228, in propagate
feat = torch.cat(feat, dim=1)
RuntimeError: Sizes of tensors must match except in dimension 1. Expected size 68 but got size 67 for tensor number 1 in the list.