Upload 8 files

model/config.json

@@ -0,0 +1,66 @@
+{
+  "_name_or_path": "IDEA-Research/grounding-dino-tiny",
+  "activation_dropout": 0.0,
+  "activation_function": "relu",
+  "architectures": [
+    "GroundingDinoForObjectDetection"
+  ],
+  "attention_dropout": 0.0,
+  "auxiliary_loss": false,
+  "backbone": null,
+  "backbone_config": {
+    "model_type": "swin",
+    "out_features": [
+      "stage2",
+      "stage3",
+      "stage4"
+    ],
+    "out_indices": [
+      2,
+      3,
+      4
+    ]
+  },
+  "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-05,
+  "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": "4.45.2",
+  "two_stage": true,
+  "two_stage_bbox_embed_share": false,
+  "use_pretrained_backbone": false,
+  "use_timm_backbone": false
+}

model/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1a2412ef99bd74bcd3c2a246fa1e48581f8889a1300c9051974741314fc042f3
+size 689359096

processor/preprocessor_config.json

@@ -0,0 +1,27 @@
+{
+  "do_convert_annotations": true,
+  "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
+  ],
+  "pad_size": null,
+  "processor_class": "GroundingDinoProcessor",
+  "resample": 2,
+  "rescale_factor": 0.00392156862745098,
+  "size": {
+    "longest_edge": 1333,
+    "shortest_edge": 800
+  }
+}

processor/special_tokens_map.json

@@ -0,0 +1,37 @@
+{
+  "cls_token": {
+    "content": "[CLS]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "mask_token": {
+    "content": "[MASK]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "[PAD]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "sep_token": {
+    "content": "[SEP]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "[UNK]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

processor/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]"
+}

script.py

@@ -0,0 +1,120 @@
+import requests
+
+import torch
+from PIL import Image, ImageDraw
+from transformers import AutoProcessor, AutoModelForZeroShotObjectDetection
+
+from tqdm import tqdm
+import os
+import pandas as pd
+
+
+def run_inference(image_path, model, save_path, prompt, box_threshold, text_threshold,
+                  visualize_results, visualization_path, device):
+    
+    test_images = os.listdir(image_path)
+    test_images.sort()
+    
+    bboxes = []
+    category_ids = []
+    test_images_names = []
+    
+    for image_name in tqdm(test_images):
+        
+        test_images_names.append(image_name)
+        bbox = []
+        category_id = []
+        
+        img = Image.open(os.path.join(image_path, image_name))
+        
+        inputs = processor(images=img, text=prompt, return_tensors="pt").to(device)
+        
+        with torch.no_grad():
+            outputs = model(**inputs)
+            
+        results = processor.post_process_grounded_object_detection(
+            outputs,
+            inputs.input_ids,
+            threshold=box_threshold,
+            text_threshold=text_threshold,
+            target_sizes=[img.size[::-1]]
+        )
+        
+        # visualize results
+        if visualize_results:
+            draw = ImageDraw.Draw(img)
+            print(image_name)
+            print(results)
+            
+            for result in results:
+                boxes = result["boxes"]
+                for i, _ in enumerate(range(len(boxes))):
+                    box = boxes[i].tolist()
+                    label = result["labels"][i]
+                    draw.rectangle(box, outline="red", width=3, )
+            img.save(os.path.join(visualization_path, image_name))
+        
+        for result in results:
+            boxes = result["boxes"]
+            labels = result["labels"]
+            
+            for i, box in enumerate(boxes):
+                xmin, ymin, xmax, ymax = box.tolist()
+                width = xmax - xmin
+                height = ymax - ymin
+                bbox.append([xmin, ymin, width, height])
+                category_id.append(0)
+        
+        bboxes.append(bbox)
+        category_ids.append(category_id)
+    
+    df_predictions = pd.DataFrame(columns=["file_name", "bbox", "category_id"])
+    
+    for i in range(len(test_images_names)):
+        file_name = test_images_names[i]
+        new_row = pd.DataFrame({"file_name": file_name,
+                                "bbox": str(bboxes[i]),
+                                "category_id": str(category_ids[i]),
+                                }, index=[0])
+        df_predictions = pd.concat([df_predictions, new_row], ignore_index=True)
+        
+    df_predictions.to_csv(save_path, index=False)
+
+
+if __name__ == "__main__":
+
+    # The following environment variables are required for offline mode during HuggingFace Submission
+    os.environ["HF_ENDPOINT"] = "https://hf-mirror.com"
+    os.environ["HF_HUB_OFFLINE"] = "1"
+    os.environ["HF_DATASETS_OFFLINE"] = "1"
+    
+    current_directory = os.path.dirname(os.path.abspath(__file__))
+    TEST_IMAGE_PATH = "/tmp/data/test_images"
+    SUBMISSION_SAVE_PATH = os.path.join(current_directory, "submission.csv")
+    
+    # Configure the model. More information here: https://huggingface.co/docs/transformers/model_doc/grounding-dino
+    # If you want to use another model - you need to make it avaible for offline usage. More information here: https://huggingface.co/docs/transformers/installation#offline-mode
+    model_id = "IDEA-Research/grounding-dino-tiny"
+    device = "cuda"
+    processor = AutoProcessor.from_pretrained(os.path.join(current_directory, "processor"))
+    model = AutoModelForZeroShotObjectDetection.from_pretrained(os.path.join(current_directory, "model"))
+    
+    model.to(device)
+    
+    BOX_THRESHOLD = 0.4
+    TEXT_THRESHOLD = 0.3
+    PROMPT = "surgical instrument."
+    
+    # If you want to test out your model on training images and visualize the results, set visualize_results to True - Visualization images will be saved in the "outputs" folder
+    parent_directory = os.path.dirname(current_directory)
+    PATH_TO_TRAINING_IMAGES_FOR_FOR_VISUALIZATION = os.path.join(parent_directory, "images")
+    visualization_path = os.path.join(parent_directory, "outputs")
+    visualize_results = False
+    if visualize_results:
+        if os.path.exists(visualization_path):
+            os.system("rm -rf " + visualization_path)
+        os.makedirs(visualization_path, exist_ok=True)
+        run_inference(PATH_TO_TRAINING_IMAGES_FOR_FOR_VISUALIZATION, model, SUBMISSION_SAVE_PATH, PROMPT, BOX_THRESHOLD, TEXT_THRESHOLD, visualize_results, visualization_path, device)
+    
+    else:    
+        run_inference(TEST_IMAGE_PATH, model, SUBMISSION_SAVE_PATH, PROMPT, BOX_THRESHOLD, TEXT_THRESHOLD, visualize_results, visualization_path, device)