BR-IDL/PaddleViT
:robot: PaddleViT: State-of-the-art Visual Transformer and MLP Models for PaddlePaddle 2.0+
This collection of computer vision models helps researchers and engineers quickly implement and experiment with cutting-edge image recognition techniques. You can input various image datasets and readily get pre-trained models for tasks like image classification, object detection, or semantic segmentation. It is designed for deep learning practitioners working on advanced vision AI applications.
1,241 stars. No commits in the last 6 months.
Use this if you need to build or customize state-of-the-art vision transformer and MLP models for tasks like image classification, object detection, or semantic segmentation using the PaddlePaddle framework.
Not ideal if you are not using PaddlePaddle or if you need to deploy models to mobile or edge devices with very strict computational constraints.
Stars
1,241
Forks
328
Language
Python
License
Apache-2.0
Category
Last pushed
Sep 07, 2022
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/computer-vision/BR-IDL/PaddleViT"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Related tools
pathak22/unsupervised-video
[CVPR 2017] Unsupervised deep learning using unlabelled videos on the web
IBM/CrossViT
Official implementation of CrossViT. https://arxiv.org/abs/2103.14899
NVlabs/GCVit
[ICML 2023] Official PyTorch implementation of Global Context Vision Transformers
ViTAE-Transformer/ViTDet
Unofficial implementation for [ECCV'22] "Exploring Plain Vision Transformer Backbones for Object...
bytedance/SPTSv2
The official implementation of SPTS v2: Single-Point Text Spotting