PyTorch-based TAO image classification. Supports a wide range of backbones (FAN, EfficientNet, ResNet, etc.) with distillation and quantization for deployment. Use when training, evaluating, distilling, quantizing, exporting, or running inference for a TAO image-classification (PyT) model.
安装
npx skills add NVIDIA/skills --skill tao-train-image-classificationnpx skills add NVIDIA/skills --skill tao-train-image-classification -a claude-code -gnpx skills add NVIDIA/skills --skill tao-train-image-classification -a codex -ggemini skills install https://github.com/NVIDIA/skills.git --path skills/tao-train-image-classificationgh skill install NVIDIA/skills tao-train-image-classificationgit clone --depth 1 https://github.com/NVIDIA/skills /tmp/NVIDIA__skills
mkdir -p ~/.claude/skills ~/.agents/skills
cp -R /tmp/NVIDIA__skills/skills/tao-train-image-classification ~/.claude/skills/tao-train-image-classification # Claude Code
cp -R /tmp/NVIDIA__skills/skills/tao-train-image-classification ~/.agents/skills/tao-train-image-classification # Codex, Cursor, Gemini CLI, Copilot, OpenCode