Evaluate model predictions against ground truth using COCO, Open Images, or custom protocols. Use when computing mAP, precision, recall, confusion matrices, or analyzing TP/FP/FN examples for detection, classification, segmentation, or regression tasks.
Install
npx skills add voxel51/fiftyone-skills --skill fiftyone-model-evaluationnpx skills add voxel51/fiftyone-skills --skill fiftyone-model-evaluation -a claude-code -gnpx skills add voxel51/fiftyone-skills --skill fiftyone-model-evaluation -a codex -ggemini skills install https://github.com/voxel51/fiftyone-skills.git --path skills/fiftyone-model-evaluationgh skill install voxel51/fiftyone-skills fiftyone-model-evaluationgit clone --depth 1 https://github.com/voxel51/fiftyone-skills /tmp/voxel51__fiftyone-skills
mkdir -p ~/.claude/skills ~/.agents/skills
cp -R /tmp/voxel51__fiftyone-skills/skills/fiftyone-model-evaluation ~/.claude/skills/fiftyone-model-evaluation # Claude Code
cp -R /tmp/voxel51__fiftyone-skills/skills/fiftyone-model-evaluation ~/.agents/skills/fiftyone-model-evaluation # Codex, Cursor, Gemini CLI, Copilot, OpenCode