preprocessor_config.json

{
  "auto_map": {
    "AutoProcessor": "processing_nvila.NVILAProcessor"
  },
  "do_convert_rgb": null,
  "do_normalize": true,
  "do_rescale": true,
  "do_resize": true,
  "image_mean": [
    0.5,
    0.5,
    0.5
  ],
  "image_processor_type": "SiglipImageProcessor",
  "image_std": [
    0.5,
    0.5,
    0.5
  ],
  "processor_class": "NVILAProcessor",
  "resample": 3,
  "rescale_factor": 0.00392156862745098,
  "size": {
    "height": 392,
    "width": 392
  },
  "autogaze_model_id": "bfshi/AutoGaze",
  "gazing_ratio_tile": 0.75,
  "gazing_ratio_thumbnail": 0.75,
  "task_loss_requirement_tile": 0.7,
  "task_loss_requirement_thumbnail": 0.7,
  "target_scales": [56, 112, 196, 392],
  "target_patch_size": 16,
  "num_video_frames": 8,
  "max_tiles_video": 8,
  "num_video_frames_thumbnail": 8,
  "mm_projector_shuffle_num": 9,
  "max_batch_size_autogaze": 32
}