faster-coco-eval
Faster interpretation of the original COCOEval
Decision gist · record as of 2026-08-14
Yes, with conditions. Install if you use COCO-format evaluation and want measurable speedup without rewriting code—the compatible API and prebuilt wheels make adoption low-friction. Verify the license from the repository first, especially in commercial contexts. The package is actively maintained, has no known vulnerabilities, and passes extensive test coverage, but the unclear license treatment requires a prerequisite check.AI-flagged interpretation of the facts on this page — verify before relying
Before you install
- Requires numpy as a runtime dependency; prebuilt wheels exist for Python 3.7–3.13 on major platforms, but older or exotic architectures may require compilation.
- Medium install friction due to platform-specific compiled wheels, but prebuilt binaries are available for Python 3.10–3.13 across macOS (ARM), Linux (x86_64, aarch64), and Windows (x64, ARM64).
- Maintenance is active with recent commits and no known vulnerabilities.
License · maintenance · safety
(unclear) — License treatment is unclear—no SPDX identifier or raw license text is recorded in the fact sheet. Before adopting this package in a commercial or copyleft-sensitive context, verify the actual license from the repository.
last release 2026-02-22 (173 days) · last repo commit 2026-08-13 · 145 stars
0 known vulnerabilities (OSV.dev, 2026-08-14) · 681,274 downloads/mo, #5,363 on PyPI
Alternatives
Verify before relying
pip install faster-coco-eval
import faster_coco_eval
faster_coco_eval.init_as_pycocotools()
# Now use standard COCO evaluation API
# Load annotations and predictions, then evaluate
val.evaluate()
val.accumulate()
val.summarize()- Exact performance improvement (3-4x claimed) on your specific hardware and dataset size.
- Whether the [extra] installation variant has additional dependencies beyond numpy.
- Compatibility with custom IoU types and alternative dataset formats in practice.
What it is and what it does
Faster-COCO-Eval is a drop-in replacement for COCO metric evaluation that accelerates computation through C++ optimizations. It computes standard object detection, instance segmentation, and keypoint detection metrics while maintaining a compatible API, so existing code can switch with a single initialization call. The package depends only on numpy and is distributed as prebuilt wheels for Python 3.7–3.13 across common platforms.
The library is actively maintained with recent commits and supports Python 3.7–3.13. It claims significant speedup on large datasets and includes support for extended metrics, alternative dataset formats, and visualization tools available via the [extra] install variant. The fact sheet records no known security vulnerabilities.
Use it for
- Accelerate evaluation loops during model training or hyperparameter tuning when using COCO-format annotations.
- Replace existing COCO evaluation in detection pipelines without code changes.
- Evaluate instance segmentation or keypoint detection tasks where metric computation is a bottleneck.
- Generate error visualizations and metric analysis for model debugging.
- Run large-scale evaluations where computation time directly impacts iteration speed.
Worth the install?
AI-flagged interpretation of the facts on this page. Verify before relying on it.
Yes, with conditions.
Install if you use COCO-format evaluation and want measurable speedup without rewriting code—the compatible API and prebuilt wheels make adoption low-friction. Verify the license from the repository first, especially in commercial contexts. The package is actively maintained, has no known vulnerabilities, and passes extensive test coverage, but the unclear license treatment requires a prerequisite check.
Install
faster-coco-eval on PyPI
Before you install
Medium install friction due to platform-specific compiled wheels, but prebuilt binaries are available for Python 3.10–3.13 across macOS (ARM), Linux (x86_64, aarch64), and Windows (x64, ARM64). Maintenance is active with recent commits and no known vulnerabilities.
Requires numpy as a runtime dependency; prebuilt wheels exist for Python 3.7–3.13 on major platforms, but older or exotic architectures may require compilation.
License in practice
License treatment is unclear—no SPDX identifier or raw license text is recorded in the fact sheet. Before adopting this package in a commercial or copyleft-sensitive context, verify the actual license from the repository.
Quickstart
pip install faster-coco-eval
import faster_coco_eval
faster_coco_eval.init_as_pycocotools()
# Now use standard COCO evaluation API
# Load annotations and predictions, then evaluate
val.evaluate()
val.accumulate()
val.summarize()Verify before relying
- Exact performance improvement (3-4x claimed) on your specific hardware and dataset size.
- Whether the [extra] installation variant has additional dependencies beyond numpy.
- Compatibility with custom IoU types and alternative dataset formats in practice.
Package facts
| License | Not declared unclear |
| Python support | Supports the current Python release >=3.7 |
| Install friction | Medium. Platform-specific wheel |
| Runtime dependencies | 1 packagenumpy |
| Maintenance | Actively maintained 173 days since the last release |
| Last repo commit | |
| First released | |
| Downloads | 681,274 / month, #5,363 on PyPI 30-day window, as of 2026-08-14 |
| Known vulnerabilities | None known OSV.dev, checked 2026-08-14 |
| Classifiers | Development Status :: 4 - BetaOperating System :: OS IndependentProgramming Language :: Python :: 3Programming Language :: Python :: 3.10Programming Language :: Python :: 3.11Programming Language :: Python :: 3.12Programming Language :: Python :: 3.13Programming Language :: Python :: 3.7Programming Language :: Python :: 3.8Programming Language :: Python :: 3.9Topic :: Scientific/Engineering :: Artificial Intelligence |
Evidence: faster_coco_eval-1.7.2-cp310-cp310-macosx_11_0_arm64.whl; faster_coco_eval-1.7.2-cp310-cp310-manylinux_2_17_aarch64.manylinux2014_aarch64.whl; faster_coco_eval-1.7.2-cp310-cp310-manylinux_2_17_x86_64.manylinux2014_x86_64.whl; faster_coco_eval-1.7.2-cp310-cp310-win_amd64.whl; faster_coco_eval-1.7.2-cp310-cp310-win_arm64.whl; faster_coco_eval-1.7.2-cp311-cp311-macosx_11_0_arm64.whl; faster_coco_eval-1.7.2-cp311-cp311-manylinux_2_17_aarch64.manylinux2014_aarch64.whl; faster_coco_eval-1.7.2-cp311-cp311-manylinux_2_17_x86_64.manylinux2014_x86_64.whl; faster_coco_eval-1.7.2-cp311-cp311-win_amd64.whl; faster_coco_eval-1.7.2-cp311-cp311-win_arm64.whl; faster_coco_eval-1.7.2-cp312-cp312-macosx_11_0_arm64.whl; faster_coco_eval-1.7.2-cp312-cp312-manylinux_2_17_aarch64.manylinux2014_aarch64.whl; faster_coco_eval-1.7.2-cp312-cp312-manylinux_2_17_x86_64.manylinux2014_x86_64.whl; faster_coco_eval-1.7.2-cp312-cp312-win_amd64.whl; faster_coco_eval-1.7.2-cp312-cp312-win_arm64.whl; faster_coco_eval-1.7.2-cp313-cp313-macosx_11_0_arm64.whl; faster_coco_eval-1.7.2-cp313-cp313-manylinux_2_17_aarch64.manylinux2014_aarch64.whl; faster_coco_eval-1.7.2-cp313-cp313-manylinux_2_17_x86_64.manylinux2014_x86_64.whl; faster_coco_eval-1.7.2-cp313-cp313-win_amd64.whl; faster_coco_eval-1.7.2-cp313-cp313-win_arm64.whl
Tags
Let your AI agent find packages like this
Example. Real query, live index.
You found this page by searching. An agent finds it by wishing: SkillFed indexes 14,416 PyPI packages by what they can do, searchable in plain language.
wish › “coco evaluation faster”
- faster-coco-evalFaster-COCO-Eval provides a high-performance replacement for COCO…
- pycocoevalcapEvaluates image captions using multiple automatic metrics (BLEU,…
- pycocotoolsProvides Python APIs for loading, parsing, and working with the…
Give your agent the search over MCP, or paste the wish link into any chat.
More Artificial Intelligence packages
LiteLLM provides a unified Python interface to call 100+ LLM providers (OpenAI, Anthropic, Gemini, Bedrock, Azure, and others) using OpenAI-compatible API format, available as both a Python SDK and a self-hosted AI Gateway proxy server.
Install it if you need to work with multiple LLM providers or want to centralize LLM routing in your organization.
Client library and CLI tool for downloading, uploading, and managing models, datasets, and repositories on the Hugging Face Hub platform.
Install it if you work with Hugging Face Hub models or datasets.
LangChain provides a framework for building agents and LLM-powered applications by composing language models, tools, and memory through a unified API that abstracts over multiple model providers.
hf-xet provides chunk-based deduplication and efficient file transfer for the Hugging Face Hub, enabling faster uploads and downloads of large files with local disk caching.
Tokenizers converts raw text into token sequences for NLP models, with support for training custom vocabularies and using pre-built tokenizers (BPE, WordPiece) optimized for speed via Rust.
Transformers provides a unified framework for loading, fine-tuning, and running state-of-the-art pretrained models across text, vision, audio, video, and multimodal tasks using PyTorch, JAX, or TensorFlow.
Install it if you need to run or train any transformer-based model for NLP, vision, audio, or multimodal tasks.
See also pycocotools · sahi · pycocoevalcap · clip-benchmark · ultralytics · rf100vl · effdet · pyiqa · lpips