video processing code failed

[MengHao666]

the code of processing video code is as

VideoLLaMA3/videollama3/train.py

Line 248 in 22a53e3

elif 'video' in data_dict and data_dict['video'] is not None:

It is inconsistent with the instructions to build dataset in readme file. In reademe file , the "video" is not a list but a string object.

[
    {
        "video": "images/xxx.jpg",
        "conversations": [
            {
                "from": "human",
                "value": "<image>\nWhat are the colors of the bus in the image?"
            },
            {
                "from": "gpt",
                "value": "The bus in the image is white and red."
            },
            ...
        ],
    }
    {
        "video": "videos/xxx.mp4",
        "conversations": [
            {
                "from": "human",
                "value": "<video>\nWhat are the main activities that take place in the video?"
            },
            {
                "from": "gpt",
                "value": "The main activities that take place in the video are the preparation of camera equipment by a man, a group of men riding a helicopter, and a man sailing a boat through the water."
            },
            ...
        ],
    },
    ...
]

[lkhl]

Hi @MengHao666. Thanks for the reminder!

The "video" item should be a list. We have fixed this error in the instruction.