materight/RepNet-pytorch
A PyTorch port with pre-trained weights of RepNet, from "Counting Out Time: Class Agnostic Video Repetition Counting in the Wild".
This tool helps you automatically count repetitive actions in any video, like exercises or industrial processes. You input a video file or URL, and it outputs a count of the repetitions, along with a visual breakdown of the periodicity. It's ideal for analysts in sports, manufacturing, or human factors looking to quantify repetitive movements.
No commits in the last 6 months.
Use this if you need to quickly and accurately count how many times an action occurs within a video without manual review.
Not ideal if your videos contain highly erratic or non-repetitive actions, or if you need to identify specific, complex actions rather than just repetitions.
Stars
40
Forks
5
Language
Python
License
—
Category
Last pushed
Nov 19, 2024
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/materight/RepNet-pytorch"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
Jittor/jittor
Jittor is a high-performance deep learning framework based on JIT compiling and meta-operators.
zhanghang1989/ResNeSt
ResNeSt: Split-Attention Networks
berniwal/swin-transformer-pytorch
Implementation of the Swin Transformer in PyTorch.
NVlabs/FasterViT
[ICLR 2024] Official PyTorch implementation of FasterViT: Fast Vision Transformers with...
ViTAE-Transformer/ViTPose
The official repo for [NeurIPS'22] "ViTPose: Simple Vision Transformer Baselines for Human Pose...