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 |
用于目标检测、图像分割和视觉人工智能系统的计算机视觉工程技能。涵盖 CNN 和 Vision Transformer 架构、YOLO/Faster R-CNN/DETR 检测、Mask R-CNN/SAM 分割以及使用 ONNX/TensorRT 的生产部署。包括 PyTorch、torchvision、Ultralytics、Detectron2 和 MMDetection 框架。在构建检测管道、训练自定义模型、优化推理或部署视觉系统时使用。 来源:borghei/claude-skills。