M2cai16-tool-locations Info

def __len__(self): return len(self.samples)

def __getitem__(self, idx): img_path, ann = self.samples[idx] image = Image.open(img_path).convert('RGB') # Parse annotations: list of [x1, y1, x2, y2, class_id] boxes = [] labels = [] for obj in ann.get('objects', []): x1, y1, x2, y2 = obj['bbox'] # absolute pixel coords label = self.CLASSES.index(obj['class_name']) boxes.append([x1, y1, x2, y2]) labels.append(label) boxes = torch.as_tensor(boxes, dtype=torch.float32) labels = torch.as_tensor(labels, dtype=torch.int64) image_id = torch.tensor([idx]) area = (boxes[:, 3] - boxes[:, 1]) * (boxes[:, 2] - boxes[:, 0]) iscrowd = torch.zeros((len(boxes),), dtype=torch.int64) target = { 'boxes': boxes, 'labels': labels, 'image_id': image_id, 'area': area, 'iscrowd': iscrowd } if self.transform: image, target = self.transform(image, target) return image, target Use matplotlib and torchvision.utils.draw_bounding_boxes : m2cai16-tool-locations

import json import os from PIL import Image import torch from torch.utils.data import Dataset from torchvision.ops import box_convert class M2CAI16ToolLocations(Dataset): """Dataset for m2cai16-tool-locations bounding box annotations.""" def __len__(self): return len(self

m2cai16-tool-locations/ annotations/ video01.json # or .xml / .txt video02.json frames/ video01/ frame_000001.jpg ... Here’s a robust parser using and torchvision : y2]) labels.append(label) boxes = torch.as_tensor(boxes