pabloppp / pytorch-tools
Useful PyTorch functions and modules that are not implemented in PyTorch by default
☆187Updated 4 months ago
Related projects: ⓘ
- Implementing Lambda Networks using Pytorch☆138Updated 3 years ago
- Implements https://arxiv.org/abs/1711.05101 AdamW optimizer, cosine learning rate scheduler and "Cyclical Learning Rates for Training Neu…☆148Updated 5 years ago
- Unofficial PyTorch Implementation of EvoNorm☆121Updated 3 years ago
- Example code showing how to use Nvidia DALI in pytorch, with fallback to torchvision. Contains a few differences to the official Nvidia …☆195Updated 4 years ago
- Pre-trained NFNets with 99% of the accuracy of the official paper "High-Performance Large-Scale Image Recognition Without Normalization".☆159Updated 3 years ago
- A PyTorch implementation of " EfficientNet: Rethinking Model Scaling for Convolutional Neural Networks."☆309Updated 4 years ago
- Collection of the latest, greatest, deep learning optimizers (for Pytorch) - CNN, NLP suitable☆212Updated 3 years ago
- 🛠 Toolbox to extend PyTorch functionalities☆416Updated 4 months ago
- A simpler version of the self-attention layer from SAGAN, and some image classification results.☆210Updated 5 years ago
- Over9000 optimizer☆424Updated last year
- lookahead optimizer (Lookahead Optimizer: k steps forward, 1 step back) for pytorch☆333Updated 5 years ago
- Semi-supervised ImageNet1K models☆241Updated 4 years ago
- Seamless analysis of your PyTorch models (RAM usage, FLOPs, MACs, receptive field, etc.)☆207Updated last week
- Feature extraction made simple with torchextractor☆100Updated 3 years ago
- homura is a library for fast prototyping DL research☆104Updated 2 years ago
- Mish Deep Learning Activation Function for PyTorch / FastAI☆160Updated 4 years ago
- NFNets and Adaptive Gradient Clipping for SGD implemented in PyTorch. Find explanation at tourdeml.github.io/blog/☆343Updated 8 months ago
- Official implementation of 'FMix: Enhancing Mixed Sample Data Augmentation'☆331Updated 3 years ago
- Accelerate training by storing parameters in one contiguous chunk of memory.☆291Updated 3 years ago
- Labels and other data for the paper "Are we done with ImageNet?"☆181Updated 2 years ago
- Standardizing weights to accelerate micro-batch training☆546Updated 2 years ago
- How to use Cross Replica / Synchronized Batchnorm in Pytorch☆247Updated 5 years ago
- ☆179Updated last year
- Implements the unsupervised pre-training of convolutional neural networks☆247Updated 3 years ago
- Compute receptive fields of your favorite convnets☆431Updated 3 years ago
- Gradient based receptive field estimation for Convolutional Neural Networks☆331Updated 4 years ago
- Implementation of the 😇 Attention layer from the paper, Scaling Local Self-Attention For Parameter Efficient Visual Backbones☆199Updated 3 years ago
- Is the attention layer even necessary? (https://arxiv.org/abs/2105.02723)☆480Updated 3 years ago
- Provides everything needed for high performance data loading and augmentation in pytorch.☆315Updated 8 months ago
- Official Pytorch Implementation of "TResNet: High-Performance GPU-Dedicated Architecture" (WACV 2021)☆469Updated last year