#Coco
Showing 23 of 23 repositories tagged #coco, ranked by stars
We write your reusable computer vision tools. 💜
Framework agnostic sliced/tiled inference + interactive ui + error analysis plots
:pencil2: Web-based image segmentation tool for object detection, localization, and keypoints
Implementation EfficientDet: Scalable and Efficient Object Detection in PyTorch
Real-time and accurate open-vocabulary end-to-end object detection
[ICLR 2024] Official PyTorch implementation of FasterViT: Fast Vision Transformers with Hierarchical Attention
The official implementation of [CVPR2022] Decoupled Knowledge Distillation https://arxiv.org/abs/2203.08679 and [ICCV2023] DOT: A Distillation-Oriented Trainer https://openaccess.thecvf.com/content/ICCV2023/papers/Zhao_DOT_A_Distillation-Oriented_Trainer_ICCV_2023_paper.pdf
Helper functions to create COCO datasets
Visual Question Answering in Pytorch
Dataset Management Framework, a Python library and a CLI tool to build, analyze and manage Computer Vision datasets.
Computer vision based ML training data generation tool :rocket:
Python library for computer vision labeling tasks. The core functionality is to translate bounding box annotations between different formats-for example, from coco to yolo.
Packaged version of ultralytics/yolov5 + many extra features
A collection of some awesome public object detection and recognition datasets.
[NeurIPS 2021] Official implementation of the paper "One Loss for All: Deep Hashing with a Single Cosine Similarity based Learning Objective"
🔨🔨🔨(mmplot)used to draw graphs of multiple index parameters such as algorithm accuracy and speed of multiple deep learning models.
VisDrone aerial object detection toolkit with 33 models (Torchvision + YOLO), training, evaluation, video inference, benchmarking, and annotation conversion.
Codes for "DANCE: A Deep Attentive Contour Model for Efficient Instance Segmentation", WACV2021
SORDI dataset has per frame annotation file in json format. Following tools create a COCO style annotation out of it. Thus the SORDI data can be easily fed into COCO style training pipelines.
An image recognition/object detection model that detects handwritten digits and simple math operators. The output of the predicted objects (numbers & math operators) is then evaluated and solved.
A Clone version from Original SegCaps source code with enhancements on MS COCO dataset.
[NeurIPS'23] DropPos: Pre-Training Vision Transformers by Reconstructing Dropped Positions
Object-detection dataset analyze