AGENT SKILL

evaluation

Routes PyTorch Metric Learning questions about AccuracyCalculator, testers, and nearest-neighbor inference.

License 许可
MIT
最近更新
2026-09-03
Stars
★ 351
Forks
27

01 前言 Front Matter

name
evaluation
license
MIT
metadata
{ "disco-role": "operating" }
description
Routes PyTorch Metric Learning questions about AccuracyCalculator, testers, and nearest-neighbor inference.
disable-model-invocation
true

02 资源文件 3

03 SKILL.md 正文

Evaluation and inference

Use this sub-skill when the user wants to score an embedding space, compare query/reference splits, or perform nearest-neighbor lookup after training.

Typical triggers

  • "How do I compute precision@1, mAP, R-precision, NMI, or AMI?"
  • "How do I use GlobalEmbeddingSpaceTester or the other testers?"
  • "How do I do nearest-neighbor search on embeddings?"
  • "How do I save or reload the faiss index?"
  • "How do I compare query and reference splits or use a custom label-comparison function?"

In scope

  • Accuracy: AccuracyCalculator and its metric family (precision_at_1, r_precision, mean_average_precision, mean_average_precision_at_r, mean_reciprocal_rank, NMI, AMI).
  • Testers: GlobalEmbeddingSpaceTester, WithSameParentLabelTester, GlobalTwoStreamEmbeddingSpaceTester, and BaseTester.
  • Inference: InferenceModel, MatchFinder, FaissKNN, FaissKMeans, CustomKNN.
  • Tiny in-memory datasets for evaluation smoke checks, including EmbeddingDataset.

Out of scope

  • Choosing the loss/miner stack belongs in components.
  • Training loop, logging, and checkpointing belong in training.
  • Dataset download and sampler construction belong in data unless the question is purely about evaluation input shape.

How to use this sub-skill

  1. Read references/evaluation-and-inference.md for the metric map, tester usage, and inference search patterns.
  2. Run scripts/smoke_evaluation.py when you want a tiny confirmation that AccuracyCalculator, a tester, and InferenceModel still work together.
  3. Read references/troubleshooting.md when the failure mentions faiss, k, custom label comparison, or an untrained index.
  4. If the user is still deciding which loss/miner stack to train, route to components before finalizing the evaluation settings.

Common routing decisions

  • If the user only needs a metric definition or retrieval score, stay here.
  • If the user asks how to choose a validation hook or checkpoint policy, route to training.
  • If the user asks for the right dataset split or sampler input before evaluation, route to data.

Useful public facts

  • AccuracyCalculator can include or exclude metrics, and k can be None, a positive integer, or "max_bin_count".
  • ref_includes_query=True is the right choice when the query set is part of the reference set.
  • GlobalEmbeddingSpaceTester is the usual default tester for embedding retrieval tasks.
  • WithSameParentLabelTester expects hierarchical labels.
  • GlobalTwoStreamEmbeddingSpaceTester expects datasets that yield (anchor, positive, label).
  • InferenceModel defaults to a faiss-backed k-NN index if you do not override knn_func.

Read next

  • references/evaluation-and-inference.md for the metric, tester, and inference reference.
  • references/troubleshooting.md for faiss, k, and label-comparison failures.
  • scripts/smoke_evaluation.py for a tiny evaluation and inference smoke check.

04 同仓库更多 Skills

VectorSpaceLab
VectorSpaceLab/AREX-Skill

passnet-triton-opt

Make a single PassNet Triton kernel fast AND numerically faithful: performance model (when a replacement can win at all), block/grid/warp tuning, autotune policy, launch overhead, and per-op numeric recipes to pass the dtype baseline tolerances. Use when a pass matches and is correct but speedup below expected, or when correctness fails by small numeric margins.

★ 351
VectorSpaceLab
VectorSpaceLab/AREX-Skill

passnet-solve

END-TO-END playbook for solving one PassNet sample: analyze the computation graphs, decide the optimization strategy (what to fuse, what to replace, what to leave alone), drive the iteration loop, and maximize the sample score. This is the ENTRY skill — invoke it first for any PassNet optimization task; it tells you when to use passnet-pattern-fusion, passnet-triton-opt and passnet-feedback.

★ 351
VectorSpaceLab
VectorSpaceLab/AREX-Skill

passnet-skill

PassNet GPU kernel optimization via compiler passes. Design and implement Triton-based optimization passes, create pass files under ./pass_dir/, self-evaluate with pass_evaluator, and iterate to maximize GPU speedup.

★ 351
VectorSpaceLab
VectorSpaceLab/AREX-Skill

passnet-pattern-fusion

Author PassNet pass files: write patterns that actually MATCH the FX graph, pick fusion regions (which ops to absorb into one Triton kernel), and structure multi-pass submissions with the mandatory shared-dispatch architecture. Use when creating or fixing pattern()/replacement_args()/replacement_func() files, when a pass "failed to match", or when deciding how to fuse multiple kernels/ops.

★ 351
VectorSpaceLab
VectorSpaceLab/AREX-Skill

passnet-orchestrate

Round/batch planning and decision support for PassNet graph optimization. Use for multi-sample triage, worker allocation, eval-budget policy, and post-eval keep/revert decisions. For solving one concrete sample end to end, use passnet-solve as the entry skill; consult this skill only when you need broader planning or a specific decision gate.

★ 351
VectorSpaceLab
VectorSpaceLab/AREX-Skill

passnet-feedback

Fast, deterministic feedback for PassNet work: pre-flight pattern/match verification WITHOUT burning a GPU evaluation, per-node bottleneck analysis of a sample's graphs, and eval-log parsing into per-variant status + estimated score + failure classification. Use BEFORE every GPU evaluation (check_pattern), at the START of a sample (analyze_graph), and AFTER every evaluation (parse_eval_log).

★ 351