Yolov8 object tracking - strange behaviour with MP4 file

Question

I am doing computer vision inferences using Yolov8. The code was doing okay so far until a few days ago when I discovered it gives me error when it tried to read a mp4 file. I tried multiple mp4 files and the result is the same. Strangely, if I tried an older mp4 file, it works. The new mp4 files can all be opened without any problem and they also can be read if I use yolov5. So I am really puzzled what happened. Any advice is much appreciated ?


[2023-04-21 15:26:15,027][root.tracker][INFO] - Loading weights from deep_sort_pytorch/deep_sort/deep/checkpoint/ckpt.t7... Done!
Ultralytics YOLOv8.0.0  Python-3.9.16 torch-1.13.1+cu117 CUDA:0 (Tesla T4, 15110MiB)
Fusing layers... 
Model summary: 268 layers, 68124531 parameters, 0 gradients, 257.4 GFLOPs
Error executing job with overrides: ['model=best_yolov8x_v8.0.0_11April2023.pt', 'conf=0.01', 'source=/root/Yolov5_DeepSort_Pytorch/VideosForTracking/P69_IMG_1095.mp4']
Traceback (most recent call last):
  File "/root/ultralytics-main/ultralytics/yolo/v8/detect/tracking_fish_counting.py", line 321, in predict
    predictor()
  File "/opt/conda/lib/python3.9/site-packages/torch/autograd/grad_mode.py", line 27, in decorate_context
    return func(*args, **kwargs)
  File "/opt/conda/lib/python3.9/site-packages/ultralytics/yolo/engine/predictor.py", line 177, in __call__
    s += self.write_results(i, preds, (p, im, im0s))
  File "/root/ultralytics-main/ultralytics/yolo/v8/detect/tracking_fish_counting.py", line 303, in write_results
    outputs = deepsort.update(xywhs, confss, oids, im0)
  File "/root/ultralytics-main/ultralytics/yolo/v8/detect/deep_sort_pytorch/deep_sort/deep_sort.py", line 29, in update
    features = self._get_features(bbox_xywh, ori_img)
  File "/root/ultralytics-main/ultralytics/yolo/v8/detect/deep_sort_pytorch/deep_sort/deep_sort.py", line 110, in _get_features
    features = self.extractor(im_crops)
  File "/root/ultralytics-main/ultralytics/yolo/v8/detect/deep_sort_pytorch/deep_sort/deep/feature_extractor.py", line 43, in __call__
    im_batch = self._preprocess(im_crops)
  File "/root/ultralytics-main/ultralytics/yolo/v8/detect/deep_sort_pytorch/deep_sort/deep/feature_extractor.py", line 38, in _preprocess
    im_batch = torch.cat([self.norm(_resize(im, self.size)).unsqueeze(
  File "/root/ultralytics-main/ultralytics/yolo/v8/detect/deep_sort_pytorch/deep_sort/deep/feature_extractor.py", line 38, in <listcomp>
    im_batch = torch.cat([self.norm(_resize(im, self.size)).unsqueeze(
  File "/root/ultralytics-main/ultralytics/yolo/v8/detect/deep_sort_pytorch/deep_sort/deep/feature_extractor.py", line 36, in _resize
    return cv2.resize(im.astype(np.float32)/255., size)
cv2.error: OpenCV(4.7.0) /io/opencv/modules/imgproc/src/resize.cpp:4062: error: (-215:Assertion failed) !ssize.empty() in function 'resize'


Set the environment variable HYDRA_FULL_ERROR=1 for a complete stack trace.

Yolov8 object tracking - strange behaviour with MP4 file

0 Answers0