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

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。

MSCOCO data format details and how to evaluate mAP with pycocotools

Uses a CNN Encoder and a RNN Decoder to generate captions for input images.

Computer Vision Nanodegree, Udacity, Project_2

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".

Python script generates colored masks from COCO-style annotations. It reads the COCO annotation files, creates masks for each annotation, colors the masks based on the annotation's category, and saves the colored masks as images. The script is designed to handle multiple categories and can be easily extended to support more categories if needed.