Can I do it this way: from detectron2.data import DatasetCatalog, MetadataCatalog from…
- User
Can I do it this way: from detectron2.data import DatasetCatalog, MetadataCatalog from datasets import load_dataset, DatasetDict import numpy as np
hf_dataset_path ="OneFormer/datasets/hf_furnace_tubes" def register_huggingface_dataset(dataset_name, hf_dataset_name, split="train"): # Load dataset from HuggingFace # dataset = load_dataset(hf_dataset_name, split=split) dataset = DatasetDict.load_from_disk(hf_dataset_path)
def get_data_dicts(): data_dicts = [] for idx, example in enumerate(dataset): # Adapt this to match your dataset structure record = { "file_name": example["image_path"] if "image_path" in example else example["image"], "image_id": idx, "height": example["height"] if "height" in example else example["image"].height, "width": example["width"] if "width" in example else example["image"].width, } # Add annotations - adjust based on your dataset format annotations = [] for mask, category_id in zip(example["masks"], example["category_ids"]): # Convert mask to binary if needed binary_mask = mask if isinstance(mask, np.ndarray) else np.array(mask) # Find contours for segmentation import cv2 contours, _ = cv2.findContours( binary_mask.astype(np.uint8), cv2.RETR_EXTERNAL, cv2.CHAIN_APPROX_SIMPLE ) # Convert contours to COCO format segmentation = [] for contour in contours: contour = contour.flatten().tolist() if len(contour) > 4: # Valid polygons have at least 3 points segmentation.append(contour) if segmentation: annotations.append({ "bbox": cv2.boundingRect(binary_mask.astype(np.uint8)), "bbox_mode": 0, # XYXY_ABS "segmentation": segmentation, "category_id": category_id, }) record["annotations"] = annotations data_dicts.append(record) return data_dicts # Register dataset DatasetCatalog.register(dataset_name, get_data_dicts) # Register metadata (adjust class names based on your dataset) class_names = dataset.features["category_ids"].feature.names if "category_ids" in dataset.features else ["class_0", "class_1", ...] MetadataCatalog.get(dataset_name).set( thing_classes=class_names, evaluator_type="coco" )Register your datasets
register_huggingface_dataset("my_dataset_train", "your/huggingface_dataset_name", split="train") register_huggingface_dataset("my_dataset_val", "your/huggingface_dataset_name", split="validation")
- Assistant
Your approach is close, but there are a few modifications needed when using
DatasetDict.load_from_disk():from detectron2.data import DatasetCatalog, MetadataCatalog from datasets import DatasetDict import numpy as np hf_dataset_path = "OneFormer/datasets/hf_furnace_tubes" def register_huggingface_dataset(dataset_name, hf_dataset_path, split="train"): # Load dataset from disk dataset = DatasetDict.load_from_disk(hf_dataset_path) # Select the specific split dataset = dataset[split] def get_data_dicts(): data_dicts = [] for idx, example in enumerate(dataset): record = { "file_name": example["image_path"] if "image_path" in example else example["image"], "image_id": idx, "height": example["height"] if "height" in example else example["image"].height, "width": example["width"] if "width" in example else example["image"].width, } annotations = [] for mask, category_id in zip(example["masks"], example["category_ids"]): binary_mask = mask if isinstance(mask, np.ndarray) else np.array(mask) import cv2 contours, _ = cv2.findContours( binary_mask.astype(np.uint8), cv2.RETR_EXTERNAL, cv2.CHAIN_APPROX_SIMPLE ) segmentation = [] for contour in contours: contour = contour.flatten().tolist() if len(contour) > 4: # Valid polygons have at least 3 points segmentation.append(contour) if segmentation: annotations.append({ "bbox": cv2.boundingRect(binary_mask.astype(np.uint8)), "bbox_mode": 0, # XYXY_ABS "segmentation": segmentation, "category_id": category_id, }) record["annotations"] = annotations data_dicts.append(record) return data_dicts # Register dataset DatasetCatalog.register(dataset_name, get_data_dicts) # Register metadata class_names = dataset.features["category_ids"].feature.names MetadataCatalog.get(dataset_name).set( thing_classes=class_names, evaluator_type="coco" ) # Register your datasets register_huggingface_dataset("my_dataset_train", hf_dataset_path, split="train") register_huggingface_dataset("my_dataset_val", hf_dataset_path, split="validation")Key changes:
- Use
dataset[split]to select the specific split - Directly use
dataset.features["category_ids"].feature.namesfor class names - Passed
hf_dataset_pathinstead of a HuggingFace dataset name
A few things to double-check:
- Ensure your dataset has the expected keys: "image_path", "masks", "category_ids"
- Verify the structure of your saved dataset matches the code assumptions
- Make sure you have OpenCV (
cv2) installed for contour processing
Would you like me to elaborate on any part of the code?
- Use
Other models, same or similar prompt
Responses were produced in different, uncontrolled contexts (system prompts, settings, prior turns). This is not a benchmark.