alfred-py: A deep learning utility library for **human**, more detail about the usage of lib to: https://zhuanlan.zhihu.com/p/341446046
-
Updated
Aug 2, 2026 - Python
alfred-py: A deep learning utility library for **human**, more detail about the usage of lib to: https://zhuanlan.zhihu.com/p/341446046
An Agnostic Computer Vision Framework - Pluggable to any Training Library: Fastai, Pytorch-Lightning with more to come
Continuation of an abandoned project fast-coco-eval
IceData: Datasets Hub for the *IceVision* Framework
Fast alternative to FiftyOne for creating a subset of the COCO dataset.
Clone of COCO API - Dataset @ http://cocodataset.org/ - with changes to support Windows build and python3
Perception evaluation toolkit in Rust with Python bindings. Drop-in pycocotools replacement, bit-identical and up to 113× faster, plus panoptic and semantic segmentation, TIDE error analysis, confusion matrices, calibration, model comparison, and a dataset browser.
This repo contains the process of getting started with Facebook FAIR's detectron2 project on windows 10 without any Nvidia GPU.
基于 torchvision 编写的针对 COCO 数据集的 Faster-RCNN 快速训练与推理框架,支持多 batchsize。
Simplify COCO dataset management with an intuitive GUI for visualization, merging, splitting, and updating. Perfect for ML and computer vision projects.
Fast COCO evaluation in Rust with Python compatibility and reproducible public benchmarks
This repository contains the code used to train and test a Mask R-CNN model for instance segmentation of transmission towers and electrical cables. We also implemented classic data augmentation techniques and a new method introduced in the paper "Simple Copy-Paste is a Strong Data Augmentation Method for Instance Segmentation".
Unofficial APIs for the MS-COCO dataset using PyTorch
图像标注格式转换器,能让你自由转换YOLO、COCO、VOC格式的图像标注文件
A computer vision application that detects a violation if construction workers do not wear safety jackets and helmets in its field of view.
MSCOCO data format details and how to evaluate mAP with pycocotools
Install and troubleshoot Alfred 5 on Windows with this configuration guide for setup, updates, and app performance issues.
ShelfSight: retail shelf product detection built at Hackology II. COCO-to-YOLO data prep, YOLO and RT-DETR training, tiled inference with ensembling, COCO-format predictions and local scoring. Public release without the competition data.
Uses a CNN Encoder and a RNN Decoder to generate captions for input images.
Object detection evaluation from scratch (IoU, matching, COCO mAP), verified against pycocotools and used on YOLO11 / VisDrone
To associate your repository with the pycocotools topic, visit your repo's landing page and select "manage topics."