VITA-Group/SLaK
[ICLR 2023] "More ConvNets in the 2020s: Scaling up Kernels Beyond 51x51 using Sparsity"; [ICML 2023] "Are Large Kernels Better Teachers than Transformers for ConvNets?"
This project helps machine learning practitioners build image classification models that are more accurate and efficient. It takes raw image datasets as input and produces optimized convolutional neural networks (ConvNets) capable of tasks like object detection and semantic segmentation. The primary users are researchers and engineers working on computer vision applications who want to improve the performance of their image recognition systems.
284 stars. No commits in the last 6 months.
Use this if you need to develop highly accurate image classification or object detection models using convolutional neural networks, especially when traditional large kernel ConvNets are too computationally intensive.
Not ideal if your primary goal is real-time inference on low-power devices, as these models can still be resource-intensive despite optimizations.
Stars
284
Forks
24
Language
HTML
License
MIT
Category
Last pushed
Jul 05, 2023
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/VITA-Group/SLaK"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
InterDigitalInc/CompressAI
A PyTorch library and evaluation platform for end-to-end compression research
quic/aimet
AIMET is a library that provides advanced quantization and compression techniques for trained...
tensorflow/compression
Data compression in TensorFlow
baler-collaboration/baler
Repository of Baler, a machine learning based data compression tool
thulab/DeepHash
An Open-Source Package for Deep Learning to Hash (DeepHash)