snap-research / Panda-70M

[CVPR 2024] Panda-70M: Captioning 70M Videos with Multiple Cross-Modality Teachers
https://snap-research.github.io/Panda-70M/
528 stars 19 forks source link

RuntimeError: PytorchStreamReader failed reading zip archive: failed finding central directory #19

Open ZhangScream opened 8 months ago

ZhangScream commented 8 months ago

I run the captioning file. python inference.py --video-list inputs/video_list.txt --prompt-list inputs/prompt_list.txt and encountered the following issues

/root/anaconda3/envs/panda70m_captioning/lib/python3.9/site-packages/torchvision/transforms/_functional_video.py:6: UserWarning: The 'torchvision.transforms._functional_video' module is deprecated since 0.12 and will be removed in 0.14. Please use the 'torchvision.transforms.functional' module instead. warnings.warn( /root/anaconda3/envs/panda70m_captioning/lib/python3.9/site-packages/torchvision/transforms/_transforms_video.py:25: UserWarning: The 'torchvision.transforms._transforms_video' module is deprecated since 0.12 and will be removed in 0.14. Please use the 'torchvision.transforms' module instead. warnings.warn( You are using the default legacy behaviour of the <class 'transformers.models.llama.tokenization_llama.LlamaTokenizer'>. This is expected, and simply means that thelegacy(previous) behavior will be used so nothing changes for you. If you want to use the new behaviour, setlegacy=False. This should only be set if you understand what it means, and thoroughly read the reason why this was added as explained in https://github.com/huggingface/transformers/pull/24565 Loading checkpoint shards: 100%|████████████████████████████████████████████████████████████████████████████████████████████████████████████████| 2/2 [00:14<00:00, 7.02s/it] Load first Checkpoint: checkpoint/checkpoint_best.pth Traceback (most recent call last): File "/dfs/comicai/bo.lii/Code/panda-70M/captioning/inference.py", line 38, in <module> model = model_cls.from_config(model_config).to("cuda") File "/dfs/comicai/bo.lii/Code/panda-70M/captioning/video_llama/models/video_llama.py", line 648, in from_config ckpt = torch.load(ckpt_path, map_location="cpu") File "/root/anaconda3/envs/panda70m_captioning/lib/python3.9/site-packages/torch/serialization.py", line 705, in load with _open_zipfile_reader(opened_file) as opened_zipfile: File "/root/anaconda3/envs/panda70m_captioning/lib/python3.9/site-packages/torch/serialization.py", line 242, in __init__ super(_open_zipfile_reader, self).__init__(torch._C.PyTorchFileReader(name_or_buffer)) RuntimeError: PytorchStreamReader failed reading zip archive: failed finding central directory

tsaishien-chen commented 8 months ago

Hi @ZhangScream, could you check whether the checkpoint has been downloaded correctly? The file size should be 3.8GB. If not, please try to download the checkpoint manually.

ZhangScream commented 8 months ago

Thanks, the problem has been resolved