{ "image_processor": { "auto_map": { "AutoProcessor": "processing_florence2.Florence2Processor" }, "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 ], "resample": 3, "rescale_factor": 0.00392156862745098, "size": { "height": 768, "width": 768 } }, "num_additional_image_tokens": 0, "post_processor_config": { "bboxes": {}, "description_with_bboxes": {}, "description_with_bboxes_or_polygons": {}, "description_with_polygons": {}, "ocr": { "area_threshold": 0.0, "pattern": "(.+?)" }, "phrase_grounding": { "banned_grounding_tokens": [ "it", "I", "me", "mine", "you", "your", "yours", "he", "him", "his", "she", "her", "hers", "they", "them", "their", "theirs", "one", "oneself", "we", "us", "our", "ours", "you", "your", "yours", "they", "them", "their", "theirs", "mine", "yours", "his", "hers", "its", "ours", "yours", "theirs", "myself", "yourself", "himself", "herself", "itself", "ourselves", "yourselves", "themselves", "this", "that", "these", "those", "who", "whom", "whose", "which", "what", "who", "whom", "whose", "which", "that", "all", "another", "any", "anybody", "anyone", "anything", "each", "everybody", "everyone", "everything", "few", "many", "nobody", "none", "one", "several", "some", "somebody", "someone", "something", "each other", "one another", "myself", "yourself", "himself", "herself", "itself", "ourselves", "yourselves", "themselves", "the image", "image", "images", "the", "a", "an", "a group", "other objects", "lots", "a set" ] }, "polygons": {}, "pure_text": {} }, "processor_class": "Florence2Processor" }