Production computer vision engineering skill for object detection, image segmentation, and visual AI system deployment.
| Frameworks | PyTorch, torchvision, timm | | Detection | Ultralytics (YOLO), Detectron2, MMDetection | | Segmentation | segment-anything, mmsegmentation | | Optimization | ONNX, TensorRT, OpenVINO, torch.compile | | Image Processing | OpenCV, Pillow, albumentations | | Annotation | CVAT, Label Studio, Roboflow |
| Experiment Tracking | MLflow, Weights & Biases | | Serving | Triton Inference Server, TorchServe |
用於目標偵測、影像分割和視覺人工智慧系統的電腦視覺工程技能。涵蓋 CNN 和 Vision Transformer 架構、YOLO/Faster R-CNN/DETR 偵測、Mask R-CNN/SAM 分割以及使用 ONNX/TensorRT 的生產部署。包括 PyTorch、torchvision、Ultralytics、Detectron2 和 MMDetection 框架。在建立檢測管道、訓練自訂模型、優化推理或部署視覺系統時使用。 來源:borghei/claude-skills。