vision_tower/internvideo2/preprocessor_config.json

{
    "Resize": {
        "size": 224,
        "interpolation": "bilinear"
    },
    "CenterCrop": {
        "size": [
            224,
            224
        ]
    },
    "ClipToTensor": {
        "channel_nb": 3,
        "div_255": true,
        "numpy": false
    },
    "Normalize": {
        "mean": [
            0.485,
            0.456,
            0.406
        ],
        "std": [
            0.229,
            0.224,
            0.225
        ]
    },
    "image_processor_type": "transforms"
}