BayesWatch / deficient-efficient
Successfully training approximations to full-rank matrices for efficiency in deep learning.
☆16Updated 3 years ago
Related projects ⓘ
Alternatives and complementary repositories for deficient-efficient
- Code for BlockSwap (ICLR 2020).☆33Updated 3 years ago
- ☆23Updated 5 years ago
- Stochastic Downsampling for Cost-Adjustable Inference and Improved Regularization in Convolutional Networks☆18Updated 5 years ago
- Exploiting Uncertainty of Loss Landscape for Stochastic Optimization☆15Updated 5 years ago
- Implementation of Kronecker Attention in Pytorch☆17Updated 4 years ago
- SplitNet implemented based on ResNet-50 trained on ImageNet-22K☆16Updated 6 years ago
- ☆13Updated 6 years ago
- "Learning Rate Dropout" in PyTorch☆34Updated 4 years ago
- Unofficial pytorch implementation of ReZero in ResNet☆23Updated 4 years ago
- Implementation of our ECCV '18 paper " Deep Expander Networks: Efficient Deep Networks from Graph Theory".☆41Updated 4 years ago
- ☆34Updated 5 years ago
- ☆22Updated 6 years ago
- Repository for the code of the paper "Neural Networks Regularization Through Class-wise Invariant Representation Learning".☆12Updated 7 years ago
- Training neural networks with 8-bit computations☆29Updated 8 years ago
- Code for "Training Generative Adversarial Networks with Binary Neurons by End-to-end Backpropagation"☆26Updated 5 years ago
- Implementation of the LOSSGRAD optimization algorithm☆15Updated 5 years ago
- Generalized Compressed Network Search with PyTorch☆26Updated 7 years ago
- Code base for SRSGD.☆28Updated 4 years ago
- A fast data loader for ImageNet on PyTorch.☆17Updated 5 years ago
- ☆13Updated 6 years ago
- ☆21Updated 4 years ago
- Training wide residual networks for deployment using a single bit for each weight☆36Updated 4 years ago
- Tensors and Dynamic neural networks in Python with strong GPU acceleration☆17Updated 10 months ago
- Code for our paper: "Regularity Normalization: Neuroscience-Inspired Unsupervised Attention across Neural Network Layers".☆21Updated 2 years ago
- Code for paper "SWALP: Stochastic Weight Averaging forLow-Precision Training".☆62Updated 5 years ago
- Partially Adaptive Momentum Estimation method in the paper "Closing the Generalization Gap of Adaptive Gradient Methods in Training Deep …☆39Updated last year
- Code for "Aggregated Momentum: Stability Through Passive Damping", Lucas et al. 2018☆34Updated 6 years ago
- ☆35Updated 5 years ago