Create coco_format.py

coco_format.py

@@ -0,0 +1,163 @@
+from glob import glob
+import pandas as pd
+import json
+import os
+import shutil
+
+def jsons_to_dataframe(json_dir):
+    # Initialize lists to store data
+    filename_list = []
+    image_id_list = []
+    width_list = []
+    height_list = []
+    category_name_list = []
+    bbox_list = []
+
+    # Iterate over each JSON file in the directory
+    for filename in os.listdir(json_dir):
+        image_id = int(filename.split('/')[-1].split('.')[0])
+        if (filename.endswith('.json') and image_id>=1700):
+            image_dir = json_dir.replace('annots', 'images')
+            image_filename = filename.split('/')[-1].replace('.json', '.png')
+            shutil.copy2(f"{image_dir}/{image_filename}", "/content/drive/MyDrive/final/circuit/val/")
+            json_file = os.path.join(json_dir, filename)
+
+            # Load JSON data from file
+            with open(json_file, 'r') as f:
+                data = json.load(f)
+
+            # Extract relevant data from JSON
+            filename_value = image_filename#data['filename']
+            width_value = int(data['size']['width'])
+            height_value = int(data['size']['height'])
+
+            # Process each object in the JSON data
+            for obj in data['object']:
+                category_name = obj['name']
+                xmin = int(float(obj['bndbox']['xmin']))
+                ymin = int(float(obj['bndbox']['ymin']))
+                xmax = int(float(obj['bndbox']['xmax']))
+                ymax = int(float(obj['bndbox']['ymax']))
+
+                # Calculate width and height of the bbox
+                bbox_width = xmax - xmin
+                bbox_height = ymax - ymin
+
+                # Create bbox dictionary
+                bbox_dict = {
+                    "xmin": xmin,
+                    "ymin": ymin,
+                    "width": bbox_width,
+                    "height": bbox_height
+                }
+
+                # Append data to lists
+                filename_list.append(filename_value)
+                image_id_list.append(image_id)
+                width_list.append(width_value)
+                height_list.append(height_value)
+                category_name_list.append(category_name)
+                bbox_list.append(bbox_dict)
+
+    # Create DataFrame
+    df = pd.DataFrame({
+        'filename': filename_list,
+        'image_id': image_id_list,
+        'width': width_list,
+        'height': height_list,
+        'category_name': category_name_list,
+        'bbox': bbox_list
+    })
+
+    return df
+
+
+categories = [
+    {'id': 1, 'name': 'Active_IC'},
+    {'id': 2, 'name': 'capacitor'},
+    {'id': 3, 'name': 'connector'},
+    {'id': 4, 'name': 'crystal'},
+    {'id': 5, 'name': 'diode'},
+    {'id': 6, 'name': 'gnd'},
+    {'id': 7, 'name': 'inductor'},
+    {'id': 8, 'name': 'led'},
+    {'id': 9, 'name': 'misc'},
+    {'id': 10, 'name': 'nmos'},
+    {'id': 11, 'name': 'npn'},
+    {'id': 12, 'name': 'pmos'},
+    {'id': 13, 'name': 'pnp'},
+    {'id': 14, 'name': 'pwr'},
+    {'id': 15, 'name': 'pwr_connector'},
+    {'id': 16, 'name': 'resistor'},
+    {'id': 17, 'name': 'switch'}
+]
+
+def dataframe_to_coco_format(df):
+    # Initialize COCO format dictionary
+    coco_format = {
+        "info": {
+            "description": "COCO format dataset",
+            "version": "1.0",
+            "year": 2024,
+            "contributor": "Anonymous",
+            "date_created": "2024/06/30"
+        },
+        "licenses": [],
+        "categories": categories,
+        "images": [],
+        "annotations": []
+    }
+
+    # Track image IDs to ensure uniqueness
+    image_id_map = {}
+
+    # Iterate over DataFrame rows
+    for idx, row in df.iterrows():
+        image_id = row['image_id']
+        filename = row['filename']
+        width = row['width']
+        height = row['height']
+        category_name = row['category_name']
+        bbox = row['bbox']
+
+        # Add image information if not already added
+        if image_id not in image_id_map:
+            image_id_map[image_id] = len(coco_format['images']) + 1  # COCO image ID starts from 1
+            coco_format['images'].append({
+                'id': image_id_map[image_id],
+                'file_name': filename,
+                'width': width,
+                'height': height
+            })
+
+        # Find category ID
+        category_id = [cat['id'] for cat in categories if cat['name'] == category_name][0]
+
+        # Add annotation information
+        coco_format['annotations'].append({
+            'id': len(coco_format['annotations']) + 1,  # COCO annotation ID starts from 1
+            'image_id': image_id_map[image_id],
+            'category_id': category_id,
+            'bbox': [bbox['xmin'], bbox['ymin'], bbox['width'], bbox['height']],
+            'area': bbox['width'] * bbox['height'],
+            'iscrowd': 0  # Assuming no crowds in the dataset
+        })
+
+    return coco_format
+
+
+
+# Example usage:
+# json_directory = '/content/drive/MyDrive/final/full_bboxcnn_data/annots'  # Replace with the directory containing your JSON files
+# df = jsons_to_dataframe(json_directory)
+# # Example usage:
+# # Assuming `df` is your pandas DataFrame obtained from `jsons_to_dataframe` function
+
+# # Convert DataFrame to COCO format
+# coco_data = dataframe_to_coco_format(df)
+
+# # Save COCO format JSON to a file
+# output_json_file = '/content/drive/MyDrive/final/circuit/val/val_coco_format.json'
+# with open(output_json_file, 'w') as f:
+#     json.dump(coco_data, f)
+