hongyi-zhang / Fixup
A Re-implementation of Fixed-update Initialization
☆152Updated 5 years ago
Alternatives and similar repositories for Fixup:
Users that are interested in Fixup are comparing it to the libraries listed below
- Utilities for Pytorch☆89Updated 2 years ago
- Code for "EigenDamage: Structured Pruning in the Kronecker-Factored Eigenbasis" https://arxiv.org/abs/1905.05934☆112Updated 4 years ago
- A plug-in replacement for DataLoader to load Imagenet disk-sequentially in PyTorch.☆238Updated 3 years ago
- Code for https://arxiv.org/abs/1810.04622☆140Updated 5 years ago
- "Layer-wise Adaptive Rate Scaling" in PyTorch☆86Updated 3 years ago
- PyTorch implementation of Wide Residual Networks with 1-bit weights by McDonnell (ICLR 2018)☆124Updated 6 years ago
- A PyTorch implementation of shake-shake☆111Updated 4 years ago
- ☆182Updated last year
- Code release for paper "Random Search and Reproducibility for NAS"☆167Updated 5 years ago
- [ICLR 2020] NAS evaluation is frustratingly hard☆149Updated last year
- Code for paper "SWALP: Stochastic Weight Averaging forLow-Precision Training".☆62Updated 5 years ago
- A PyTorch implementation of "Incremental Network Quantization: Towards Lossless CNNs with Low-Precision Weights"☆166Updated 4 years ago
- Implementation and experiments for AdamW on Pytorch☆93Updated 5 years ago
- PyTorch implementation of shake-drop regularization☆54Updated 4 years ago
- Implementations of ideas from recent papers☆391Updated 4 years ago
- ☆213Updated 6 years ago
- Unofficial PyTorch Implementation of EvoNorm☆121Updated 3 years ago
- Code for the NuerIPS'19 paper "Gate Decorator: Global Filter Pruning Method for Accelerating Deep Convolutional Neural Networks"☆196Updated 4 years ago
- Discovering Neural Wirings (https://arxiv.org/abs/1906.00586)☆138Updated 4 years ago
- ☆180Updated last year
- A drop-in replacement for CIFAR-10.☆237Updated 3 years ago
- Batch normalization fusion for PyTorch☆195Updated 4 years ago
- Code used to generate the results appearing in "Train longer, generalize better: closing the generalization gap in large batch training o…☆148Updated 7 years ago
- Single-Path NAS: Designing Hardware-Efficient ConvNets in less than 4 Hours☆396Updated 4 years ago
- Implements pytorch code for the Accelerated SGD algorithm.☆215Updated 6 years ago
- SNIP: SINGLE-SHOT NETWORK PRUNING BASED ON CONNECTION SENSITIVITY☆112Updated 5 years ago
- An implementation of shampoo☆74Updated 6 years ago
- Bridging the gap Between Stability and Scalability in Neural Architecture Search☆141Updated 3 years ago
- Code for "Picking Winning Tickets Before Training by Preserving Gradient Flow" https://openreview.net/pdf?id=SkgsACVKPH☆102Updated 4 years ago
- CuPy fused PyTorch neural networks ops☆274Updated 6 years ago