search

hujiecpp / YOSO

Code release for paper "You Only Segment Once: Towards Real-Time Panoptic Segmentation" [CVPR 2023]
MIT License
255 stars 20 forks source link

ADE20k demo test.Index out of range #24

Open Cuirundi opened 3 months ago

Cuirundi commented 3 months ago

python demo/demo.py --config-file projects/YOSO/configs/ade20k/panoptic-segmentation/YOSO-R50.yaml --video-input 123.mp4 --output output/ --opts MODEL.WEIGHTS weights/yoso_res50_ade20k.pth [07/31 22:58:16 detectron2]: Arguments: Namespace(config_file='projects/YOSO/configs/ade20k/panoptic-segmentation/YOSO-R50.yaml', webcam=False, video_input='123.mp4', input=None, output='output/', overlap_threshold=0.98, confidence_threshold=0.8, opts=['MODEL.WEIGHTS', 'weights/yoso_res50_ade20k.pth']) WARNING [07/31 22:58:16 fvcore.common.config]: Loading config projects/YOSO/configs/ade20k/panoptic-segmentation/Base-ADE20K-PanopticSegmentation.yaml with yaml.unsafe_load. Your machine may be at risk if the file contains malicious content. [07/31 22:58:17 fvcore.common.checkpoint]: [Checkpointer] Loading from weights/yoso_res50_ade20k.pth ... 512 256 [ERROR:0@4.554] global cap_ffmpeg_impl.hpp:3133 open Could not find encoder for codec_id=27, error: Encoder not found [ERROR:0@4.554] global cap_ffmpeg_impl.hpp:3211 open VIDEOIO/FFMPEG: Failed to initialize VideoWriter [ WARN:0@4.555] global cap.cpp:643 open VIDEOIO(CV_IMAGES): raised OpenCV exception:

OpenCV(4.10.0) /io/opencv/modules/videoio/src/cap_images.cpp:430: error: (-215:Assertion failed) !filename_pattern.empty() in function 'open'

0%| | 0/1723 [00:00<?, ?it/s]/home/iiau/anaconda3/envs/te/lib/python3.10/site-packages/torch/functional.py:507: UserWarning: torch.meshgrid: in an upcoming release, it will be required to pass the indexing argument. (Triggered internally at /opt/conda/conda-bld/pytorch_1704987394225/work/aten/src/ATen/native/TensorShape.cpp:3549.) return _VF.meshgrid(tensors, **kwargs) # type: ignore[attr-defined] 6%|██▌ | 108/1723 [00:20<05:13, 5.15it/s] Traceback (most recent call last): File "/media/iiau/a9633b88-037d-4a85-bc0e-d0ad9dbc9e28/yoso1/yoso1/demo/demo.py", line 189, in for vis_frame in tqdm.tqdm(demo.run_on_video(video), total=num_frames): File "/home/iiau/anaconda3/envs/te/lib/python3.10/site-packages/tqdm/std.py", line 1181, in iter for obj in iterable: File "/media/iiau/a9633b88-037d-4a85-bc0e-d0ad9dbc9e28/yoso1/yoso1/demo/predictor.py", line 130, in run_on_video yield process_predictions(frame, self.predictor(frame)) File "/media/iiau/a9633b88-037d-4a85-bc0e-d0ad9dbc9e28/yoso1/yoso1/demo/predictor.py", line 94, in process_predictions vis_frame = video_visualizer.draw_panoptic_seg_predictions( File "/media/iiau/a9633b88-037d-4a85-bc0e-d0ad9dbc9e28/yoso1/yoso1/detectron2/utils/video_visualizer.py", line 168, in draw_panoptic_seg_predictions labels = [self.metadata.thing_classes[k] for k in category_ids] File "/media/iiau/a9633b88-037d-4a85-bc0e-d0ad9dbc9e28/yoso1/yoso1/detectron2/utils/video_visualizer.py", line 168, in labels = [self.metadata.thing_classes[k] for k in category_ids] IndexError: list index out of range

Cuirundi commented 3 months ago

Hello, I encountered the problem when testing the demo with ade20k pretraining model. how to solve it？thank you!