add groundingdino used for segmentation

grounding-dino-base/config.json

@@ -0,0 +1,61 @@
+{
+  "activation_dropout": 0.0,
+  "activation_function": "relu",
+  "architectures": ["GroundingDinoForObjectDetection"],
+  "attention_dropout": 0.0,
+  "auxiliary_loss": false,
+  "backbone": null,
+  "backbone_config": {
+    "depths": [2, 2, 18, 2],
+    "embed_dim": 128,
+    "hidden_size": 1024,
+    "image_size": 384,
+    "model_type": "swin",
+    "num_heads": [4, 8, 16, 32],
+    "out_features": ["stage2", "stage3", "stage4"],
+    "out_indices": [2, 3, 4],
+    "window_size": 12
+  },
+  "backbone_kwargs": null,
+  "bbox_cost": 5.0,
+  "bbox_loss_coefficient": 5.0,
+  "class_cost": 1.0,
+  "d_model": 256,
+  "decoder_attention_heads": 8,
+  "decoder_bbox_embed_share": true,
+  "decoder_ffn_dim": 2048,
+  "decoder_layers": 6,
+  "decoder_n_points": 4,
+  "disable_custom_kernels": false,
+  "dropout": 0.1,
+  "embedding_init_target": true,
+  "encoder_attention_heads": 8,
+  "encoder_ffn_dim": 2048,
+  "encoder_layers": 6,
+  "encoder_n_points": 4,
+  "focal_alpha": 0.25,
+  "fusion_dropout": 0.0,
+  "fusion_droppath": 0.1,
+  "giou_cost": 2.0,
+  "giou_loss_coefficient": 2.0,
+  "init_std": 0.02,
+  "is_encoder_decoder": true,
+  "layer_norm_eps": 1e-5,
+  "max_text_len": 256,
+  "model_type": "grounding-dino",
+  "num_feature_levels": 4,
+  "num_queries": 900,
+  "position_embedding_type": "sine",
+  "positional_embedding_temperature": 20,
+  "query_dim": 4,
+  "text_config": {
+    "model_type": "bert"
+  },
+  "text_enhancer_dropout": 0.0,
+  "torch_dtype": "float32",
+  "transformers_version": "4.40.0.dev0",
+  "two_stage": true,
+  "two_stage_bbox_embed_share": false,
+  "use_pretrained_backbone": false,
+  "use_timm_backbone": false
+}

grounding-dino-base/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5548f844c928c4b6f411fa8cbcc2bfa8dbbba437cb1d513975519f93c2a9ed21
+size 933400872

grounding-dino-base/preprocessor_config.json

@@ -0,0 +1,17 @@
+{
+  "do_normalize": true,
+  "do_pad": true,
+  "do_rescale": true,
+  "do_resize": true,
+  "format": "coco_detection",
+  "image_mean": [0.485, 0.456, 0.406],
+  "image_processor_type": "GroundingDinoImageProcessor",
+  "image_std": [0.229, 0.224, 0.225],
+  "processor_class": "GroundingDinoProcessor",
+  "resample": 2,
+  "rescale_factor": 0.00392156862745098,
+  "size": {
+    "longest_edge": 1333,
+    "shortest_edge": 800
+  }
+}

grounding-dino-base/special_tokens_map.json

@@ -0,0 +1,7 @@
+{
+  "cls_token": "[CLS]",
+  "mask_token": "[MASK]",
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "unk_token": "[UNK]"
+}

grounding-dino-base/tokenizer_config.json

@@ -0,0 +1,56 @@
+{
+  "added_tokens_decoder": {
+    "0": {
+      "content": "[PAD]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "100": {
+      "content": "[UNK]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "101": {
+      "content": "[CLS]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "102": {
+      "content": "[SEP]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "103": {
+      "content": "[MASK]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "clean_up_tokenization_spaces": true,
+  "cls_token": "[CLS]",
+  "do_lower_case": true,
+  "mask_token": "[MASK]",
+  "model_max_length": 512,
+  "pad_token": "[PAD]",
+  "processor_class": "GroundingDinoProcessor",
+  "sep_token": "[SEP]",
+  "strip_accents": null,
+  "tokenize_chinese_chars": true,
+  "tokenizer_class": "BertTokenizer",
+  "unk_token": "[UNK]"
+}