Hon-Wong
Hon-Wong
> Please refer to this branch: https://github.com/LLaVA-VL/LLaVA-NeXT/tree/video_inference Thanks for your reply! However, the link you provided seems like a private one, as I have no access to it. It reports:...
Very good question! Sorry that we did not give enough instructions. I just uploaded the script for merging clips and updated the readme for better instructions. Please merge short clips...
> Is this problem solved? I meet the same error, does it mean that we should set tokenizer item to a specific value? Try setting tokenizer as your llm path.
Hi, it is actually in jsonline format. Try `data = [json.loads(line) for line in f]`
> thanks for you reply. > > by the way, in the paper, Table 5 presents "The results of the RSOT and SOT tasks on the evaluation split of ElysiumTrack...