onnx-community/Florence-2-base

1{2  "_valid_processor_keys": [3    "images",4    "do_resize",5    "size",6    "resample",7    "do_center_crop",8    "crop_size",9    "do_rescale",10    "rescale_factor",11    "do_normalize",12    "image_mean",13    "image_std",14    "do_convert_rgb",15    "return_tensors",16    "data_format",17    "input_data_format"18  ],19  "crop_size": {20    "height": 768,21    "width": 76822  },23  "do_center_crop": false,24  "do_convert_rgb": null,25  "do_normalize": true,26  "do_rescale": true,27  "do_resize": true,28  "image_mean": [29    0.485,30    0.456,31    0.40632  ],33  "image_processor_type": "CLIPImageProcessor",34  "image_seq_length": 577,35  "image_std": [36    0.229,37    0.224,38    0.22539  ],40  "processor_class": "Florence2Processor",41  "resample": 3,42  "rescale_factor": 0.00392156862745098,43  "size": {44    "height": 768,45    "width": 76846  },47  "tasks_answer_post_processing_type": {48    "<OCR>": "pure_text",49    "<OCR_WITH_REGION>": "ocr",50    "<CAPTION>": "pure_text",51    "<DETAILED_CAPTION>": "pure_text",52    "<MORE_DETAILED_CAPTION>": "pure_text",53    "<OD>": "description_with_bboxes",54    "<DENSE_REGION_CAPTION>": "description_with_bboxes",55    "<CAPTION_TO_PHRASE_GROUNDING>": "phrase_grounding",56    "<REFERRING_EXPRESSION_SEGMENTATION>": "polygons",57    "<REGION_TO_SEGMENTATION>": "polygons",58    "<OPEN_VOCABULARY_DETECTION>": "description_with_bboxes_or_polygons",59    "<REGION_TO_CATEGORY>": "pure_text",60    "<REGION_TO_DESCRIPTION>": "pure_text",61    "<REGION_TO_OCR>": "pure_text",62    "<REGION_PROPOSAL>": "bboxes"63  },64  "task_prompts_without_inputs": {65    "<OCR>": "What is the text in the image?",66    "<OCR_WITH_REGION>": "What is the text in the image, with regions?",67    "<CAPTION>": "What does the image describe?",68    "<DETAILED_CAPTION>": "Describe in detail what is shown in the image.",69    "<MORE_DETAILED_CAPTION>": "Describe with a paragraph what is shown in the image.",70    "<OD>": "Locate the objects with category name in the image.",71    "<DENSE_REGION_CAPTION>": "Locate the objects in the image, with their descriptions.",72    "<REGION_PROPOSAL>": "Locate the region proposals in the image."73  },74  "task_prompts_with_input": {75    "<CAPTION_TO_PHRASE_GROUNDING>": "Locate the phrases in the caption: {input}",76    "<REFERRING_EXPRESSION_SEGMENTATION>": "Locate {input} in the image with mask",77    "<REGION_TO_SEGMENTATION>": "What is the polygon mask of region {input}",78    "<OPEN_VOCABULARY_DETECTION>": "Locate {input} in the image.",79    "<REGION_TO_CATEGORY>": "What is the region {input}?",80    "<REGION_TO_DESCRIPTION>": "What does the region {input} describe?",81    "<REGION_TO_OCR>": "What text is in the region {input}?"82  }83}84