preprocessor_config.json

{
  "_valid_processor_keys": [
    "images",
    "do_resize",
    "size",
    "resample",
    "do_center_crop",
    "crop_size",
    "do_rescale",
    "rescale_factor",
    "do_normalize",
    "image_mean",
    "image_std",
    "do_convert_rgb",
    "return_tensors",
    "data_format",
    "input_data_format"
  ],
  "crop_size": {
    "height": 768,
    "width": 768
  },
  "do_center_crop": false,
  "do_convert_rgb": null,
  "do_normalize": true,
  "do_rescale": true,
  "do_resize": true,
  "image_mean": [
    0.485,
    0.456,
    0.406
  ],
  "image_processor_type": "CLIPImageProcessor",
  "image_seq_length": 577,
  "image_std": [
    0.229,
    0.224,
    0.225
  ],
  "processor_class": "Florence2Processor",
  "resample": 3,
  "rescale_factor": 0.00392156862745098,
  "size": {
    "height": 768,
    "width": 768
  },
  "tasks_answer_post_processing_type": {
    "<OCR>": "pure_text",
    "<OCR_WITH_REGION>": "ocr",
    "<CAPTION>": "pure_text",
    "<DETAILED_CAPTION>": "pure_text",
    "<MORE_DETAILED_CAPTION>": "pure_text",
    "<OD>": "description_with_bboxes",
    "<DENSE_REGION_CAPTION>": "description_with_bboxes",
    "<CAPTION_TO_PHRASE_GROUNDING>": "phrase_grounding",
    "<REFERRING_EXPRESSION_SEGMENTATION>": "polygons",
    "<REGION_TO_SEGMENTATION>": "polygons",
    "<OPEN_VOCABULARY_DETECTION>": "description_with_bboxes_or_polygons",
    "<REGION_TO_CATEGORY>": "pure_text",
    "<REGION_TO_DESCRIPTION>": "pure_text",
    "<REGION_TO_OCR>": "pure_text",
    "<REGION_PROPOSAL>": "bboxes"
  },
  "task_prompts_without_inputs": {
    "<OCR>": "What is the text in the image?",
    "<OCR_WITH_REGION>": "What is the text in the image, with regions?",
    "<CAPTION>": "What does the image describe?",
    "<DETAILED_CAPTION>": "Describe in detail what is shown in the image.",
    "<MORE_DETAILED_CAPTION>": "Describe with a paragraph what is shown in the image.",
    "<OD>": "Locate the objects with category name in the image.",
    "<DENSE_REGION_CAPTION>": "Locate the objects in the image, with their descriptions.",
    "<REGION_PROPOSAL>": "Locate the region proposals in the image."
  },
  "task_prompts_with_input": {
    "<CAPTION_TO_PHRASE_GROUNDING>": "Locate the phrases in the caption: {input}",
    "<REFERRING_EXPRESSION_SEGMENTATION>": "Locate {input} in the image with mask",
    "<REGION_TO_SEGMENTATION>": "What is the polygon mask of region {input}",
    "<OPEN_VOCABULARY_DETECTION>": "Locate {input} in the image.",
    "<REGION_TO_CATEGORY>": "What is the region {input}?",
    "<REGION_TO_DESCRIPTION>": "What does the region {input} describe?",
    "<REGION_TO_OCR>": "What text is in the region {input}?"
  }
}