gaohuang/MSDNet
Multi-Scale Dense Networks for Resource Efficient Image Classification （ICLR 2018 Oral）
This project helps quickly and efficiently classify images, particularly useful when computational resources are limited or real-time results are needed. It takes image data as input and produces categorized images as output. Researchers and engineers working on image processing applications who need fast, resource-efficient image classification will find this beneficial.
461 stars. No commits in the last 6 months.
Use this if you need to classify images and require the flexibility to get a prediction at any time, or if you have a fixed computational budget for classifying a batch of images and want to optimize its use.
Not ideal if your primary concern is absolute classification accuracy regardless of computational cost or prediction speed.
Stars
461
Forks
93
Language
Lua
License
MIT
Category
Last pushed
Apr 03, 2019
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/gaohuang/MSDNet"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Related frameworks
Jittor/jittor
Jittor is a high-performance deep learning framework based on JIT compiling and meta-operators.
berniwal/swin-transformer-pytorch
Implementation of the Swin Transformer in PyTorch.
zhanghang1989/ResNeSt
ResNeSt: Split-Attention Networks
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...