Running inference on video with pre-trained weights is stuck in "converting to TensorRT" step

[marcoluis97]

Describe the bug
Running inference on video with pre-trained weights is stuck in "converting to TensorRT" step

Full logs
Log while running comand: !python3 ./yolact_edge/eval.py --trained_model=./yolact_edge/weights/yolact_edge/yolact_edge_54_800000.pth --score_threshold=0.3 --top_k=100 --video={file_path}:{output_path} --calib_images {calib}

After killing the script:

Environment:
Colab jupyter file from yolact_edge github (slightly modified to accomodate gdrive imports and some other stuff, but with same working and instalation procedure):