image-utilities
Guides agents through keras-vis image utilities for data formats, overlays, labels, optional image dependencies, and diagnostics.
- License 许可
- MIT
- 最近更新
- 2026-09-03
- Stars
- ★ 351
- Forks
- 27
01 前言 Front Matter
- name
- image-utilities
- license
- MIT
- metadata
- { "disco-role": "operating" }
- description
- Guides agents through keras-vis image utilities for data formats, overlays, labels, optional image dependencies, and diagnostics.
- disable-model-invocation
- true
02 资源文件 4
- 参考文档references/api-reference.md8.9 KB
- 参考文档references/data-and-format-guide.md5.7 KB
- 参考文档references/troubleshooting.md6.6 KB
- 脚本scripts/check_image_utilities.py10.9 KB
03 SKILL.md 正文
keras-vis image utilities
Use this sub-skill when a task needs keras-vis utility behavior rather than visualization semantics: image/data-format shape handling, channel-order helpers, synthetic arrays, overlays, label lookup, text drawing, image loading, model-layer lookup, model graph refresh after activation edits, or optional Pillow/imageio diagnostics.
Route first
- For activation-maximization recipes, loss weighting, seed images, or softmax-to-linear visualization advice, use the
activation-maximizationsub-skill instead. - For saliency, guided saliency, Grad-CAM, heatmap interpretation, or map-overlay workflow semantics, use the
saliency-and-camsub-skill instead; return here only for low-level array overlays and shape checks. - For custom losses, regularizers, optimizer callbacks, gradient modifiers, input modifiers, or backprop modifier internals, use the
optimization-building-blockssub-skill instead.
Runtime workflow
-
Decide the array contract: Keras backend
image_data_format, tensor rank, and whether the array is channels-first tensor data or channels-last display image data. Use data-and-format-guide.md. -
Pick the helper and exact import path from api-reference.md. Most helpers live under
vis.utils.utils;overlaylives undervis.visualization. -
For environment or compatibility questions, run the bundled deterministic diagnostic script from this sub-skill tree:
python scripts/check_image_utilities.pyThe script uses only synthetic arrays and reports optional Pillow/imageio availability without requiring original images.
-
If a failure involves missing optional image packages, package data, array shape mismatch, graph refresh, or legacy Keras/TensorFlow behavior, use troubleshooting.md.
Keep outputs self-contained
When giving future instructions, copy or generate any tiny image data needed for demonstrations. Do not depend on repository-local sample assets or external data to explain these utilities.
04 同仓库更多 Skills
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.
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.
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.
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.
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.
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).