OCDNet for scene text detection. Detects arbitrary-oriented text regions in natural images using a differentiable binarization approach. Use when training, evaluating, exporting, pruning, quantizing, retraining, or running inference for a TAO OCDNet model. Trigger phrases include "train OCDNet", "scene text detection", "arbitrary-oriented text boxes", "differentiable binarization detector".
安装
npx skills add NVIDIA/skills --skill tao-train-ocdnetnpx skills add NVIDIA/skills --skill tao-train-ocdnet -a claude-code -gnpx skills add NVIDIA/skills --skill tao-train-ocdnet -a codex -ggemini skills install https://github.com/NVIDIA/skills.git --path skills/tao-train-ocdnetgh skill install NVIDIA/skills tao-train-ocdnetgit 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-ocdnet ~/.claude/skills/tao-train-ocdnet # Claude Code
cp -R /tmp/NVIDIA__skills/skills/tao-train-ocdnet ~/.agents/skills/tao-train-ocdnet # Codex, Cursor, Gemini CLI, Copilot, OpenCode