LiyuanLucasLiu / RAdam
On the Variance of the Adaptive Learning Rate and Beyond
☆2,535Updated 3 years ago
Related projects ⓘ
Alternatives and complementary repositories for RAdam
- Ranger - a synergistic optimizer using RAdam (Rectified Adam), Gradient Centralization and LookAhead in one codebase☆1,194Updated 10 months ago
- An optimizer that trains as fast as Adam and as good as SGD.☆2,907Updated last year
- Neural network graphs and training metrics for PyTorch, Tensorflow, and Keras.☆1,800Updated 9 months ago
- Model summary in PyTorch similar to `model.summary()` in Keras☆4,020Updated 8 months ago
- PyTorch implementation of "Efficient Neural Architecture Search via Parameters Sharing"☆2,707Updated last year
- tensorboard for pytorch (and chainer, mxnet, numpy, ...)☆7,871Updated this week
- torch-optimizer -- collection of optimizers for Pytorch☆3,043Updated 7 months ago
- Implementation of LambdaNetworks, a new approach to image recognition that reaches SOTA with less compute☆1,532Updated 4 years ago
- A lightweight library for PyTorch training tools and utilities☆1,665Updated this week
- Train AI models efficiently on medical images using any framework☆1,866Updated 5 months ago
- Official Implementation of 'Fast AutoAugment' in PyTorch.☆1,596Updated 3 years ago
- Debug PyTorch code using PySnooper☆802Updated 3 years ago
- pip install antialiased-cnns to improve stability and accuracy☆1,661Updated 7 months ago
- Unsupervised Data Augmentation (UDA)☆2,178Updated 3 years ago
- Pretrained EfficientNet, EfficientNet-Lite, MixNet, MobileNetV3 / V2, MNASNet A1 and B1, FBNet, Single-Path NAS☆1,566Updated 5 months ago
- Codebase for Image Classification Research, written in PyTorch.☆2,139Updated 8 months ago
- Code for visualizing the loss landscape of neural nets☆2,840Updated 2 years ago
- Repository for NeurIPS 2020 Spotlight "AdaBelief Optimizer: Adapting stepsizes by the belief in observed gradients"☆1,050Updated 3 months ago
- Official Repository for "Mish: A Self Regularized Non-Monotonic Neural Activation Function" [BMVC 2020]☆1,291Updated this week
- A CV toolkit for my papers.☆2,041Updated 5 months ago
- Source code for "On the Relationship between Self-Attention and Convolutional Layers"☆1,085Updated last year
- Single Headed Attention RNN - "Stop thinking with your head"☆1,178Updated 2 years ago
- High-level library to help with training and evaluating neural networks in PyTorch flexibly and transparently.☆4,528Updated last week
- ☆1,135Updated last year
- A PyTorch implementation of the NIPS 2017 paper "Dynamic Routing Between Capsules".☆1,730Updated 6 years ago
- My best practice of training large dataset using PyTorch.☆1,086Updated 6 months ago
- A (PyTorch) imbalanced dataset sampler for oversampling low frequent classes and undersampling high frequent ones.☆2,275Updated last month
- ResNeSt: Split-Attention Networks☆3,238Updated last year
- Differentiable architecture search for convolutional and recurrent networks☆3,920Updated 3 years ago
- A learning rate range test implementation in PyTorch☆924Updated last month