Eric-mingjie/network-slimming
Network Slimming (Pytorch) (ICCV 2017)
This project helps machine learning engineers and researchers make their image classification models smaller and faster without losing accuracy. You provide an existing convolutional neural network (like VGG, ResNet, or DenseNet) trained on image datasets such as CIFAR-10 or CIFAR-100. The output is a significantly more compact version of your model that retains high classification performance, making it more efficient for deployment.
919 stars. No commits in the last 6 months.
Use this if you need to reduce the size and computational demands of your image classification models for deployment on resource-constrained devices or to speed up inference.
Not ideal if your primary goal is to improve the accuracy of a model rather than optimize its size or speed, or if you are working with non-image data.
Stars
919
Forks
217
Language
Python
License
MIT
Category
Last pushed
Nov 06, 2020
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/Eric-mingjie/network-slimming"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Related frameworks
open-mmlab/mmengine
OpenMMLab Foundational Library for Training Deep Learning Models
Xilinx/brevitas
Brevitas: neural network quantization in PyTorch
fastmachinelearning/qonnx
QONNX: Arbitrary-Precision Quantized Neural Networks in ONNX
google/qkeras
QKeras: a quantization deep learning library for Tensorflow Keras
tensorflow/model-optimization
A toolkit to optimize ML models for deployment for Keras and TensorFlow, including quantization...