network-slimming and pytorch-slimming
These are competing implementations of the same ICCV 2017 Network Slimming paper for channel pruning in PyTorch, with the Eric-mingjie version being more actively maintained and popular based on star count.
About network-slimming
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.
About pytorch-slimming
foolwood/pytorch-slimming
Learning Efficient Convolutional Networks through Network Slimming, In ICCV 2017.
This tool helps machine learning engineers and researchers make their deep learning models smaller and faster. It takes a pre-trained convolutional neural network and reduces its size by identifying and removing less important parts of the network. The output is a more efficient model that maintains high accuracy, suitable for deployment in resource-constrained environments.
Related comparisons
Scores updated daily from GitHub, PyPI, and npm data. How scores work