Awesome

Slimmable Networks

An open source framework for slimmable training on tasks of ImageNet classification and COCO detection, which has enabled numerous projects. ^{1, 2, 3}

<strong id="snets">1. Slimmable Neural Networks</strong> _{ICLR 2019 Paper | OpenReview | Detection | Model Zoo}

Illustration of slimmable neural networks. The same model can run at different widths (number of active channels), permitting instant and adaptive accuracy-efficiency trade-offs.

<strong id="usnets">2. Universally Slimmable Networks and Improved Training Techniques</strong> _{ICCV 2019 Paper | Model Zoo}

Illustration of universally slimmable networks. The same model can run at arbitrary widths.

<strong id="autoslim">3. AutoSlim: Towards One-Shot Architecture Search for Channel Numbers</strong> _{NeurIPS 2019 Workshop Paper | Model Zoo}

<img src="https://user-images.githubusercontent.com/22609465/54886763-93309000-4e59-11e9-963a-c15bf49af3c0.gif" width=25%/><img src="https://user-images.githubusercontent.com/22609465/54886764-9592ea00-4e59-11e9-9541-924bbd9ff727.gif" width=25%/><img src="https://user-images.githubusercontent.com/22609465/54886766-97f54400-4e59-11e9-81bb-3b262df7c898.gif" width=25%/><img src="https://user-images.githubusercontent.com/22609465/54886768-9a579e00-4e59-11e9-9896-25e7eab7e2e0.gif" width=25%/>

AutoSlimming MobileNet v1, MobileNet v2, MNasNet and ResNet-50: the optimized number of channels under each computational budget (FLOPs).

Run

0. Requirements:
   • python3, pytorch 1.0, torchvision 0.2.1, pyyaml 3.13.
   • Prepare ImageNet-1k data following pytorch example.
1. Training and Testing:
   • The codebase is a general ImageNet training framework using yaml config under apps dir, based on PyTorch.
   • To test, download pretrained models to logs dir and directly run command.
   • To train, comment test_only and pretrained in config file. You will need to manage visible gpus by yourself.
   • Command: python train.py app:{apps/***.yml}. {apps/***.yml} is config file. Do not miss app: prefix.
   • Training and testing of MSCOCO benchmarks are released under branch detection.
2. Still have questions?
   • If you still have questions, please search closed issues first. If the problem is not solved, please open a new.

Slimmable Model Zoo

Slimmable Neural Networks

Universally Slimmable Networks and Improved Training Techniques

AutoSlim: Towards One-Shot Architecture Search for Channel Numbers

Technical Details

Implementing slimmable networks and slimmable training is straightforward:

• Switchable batchnorm and slimmable layers are implemented in models/slimmable_ops.
• Slimmable training is implemented in these lines in train.py.

License

CC 4.0 Attribution-NonCommercial International

The software is for educaitonal and academic research purpose only.