sdoria / SimpleSelfAttention
A simpler version of the self-attention layer from SAGAN, and some image classification results.
☆212Updated 5 years ago
Alternatives and similar repositories for SimpleSelfAttention:
Users that are interested in SimpleSelfAttention are comparing it to the libraries listed below
- Mish Deep Learning Activation Function for PyTorch / FastAI☆161Updated 5 years ago
- Unofficial PyTorch Implementation of EvoNorm☆121Updated 3 years ago
- Repo to build on / reproduce the record breaking Ranger-Mish-SelfAttention setup on FastAI ImageWoof dataset 5 epochs☆116Updated 5 years ago
- High-level batteries-included neural network training library for Pytorch☆400Updated 3 years ago
- Simple Tensorflow implementation of "On The Variance Of The Adaptive Learning Rate And Beyond"☆97Updated 5 years ago
- homura is a library for fast prototyping DL research☆107Updated 2 years ago
- Semi-supervised ImageNet1K models☆243Updated 5 years ago
- Implementations of ideas from recent papers☆393Updated 4 years ago
- Using the CLR algorithm for training (https://arxiv.org/abs/1506.01186)☆108Updated 6 years ago
- PyTorch code for the "Deep Neural Networks with Box Convolutions" paper☆510Updated 5 years ago
- A PyTorch implementation of " EfficientNet: Rethinking Model Scaling for Convolutional Neural Networks."☆311Updated 5 years ago
- A Pytorch implementation of Fast AutoAugment and EfficientNet☆119Updated 5 years ago
- Implements the unsupervised pre-training of convolutional neural networks☆250Updated 3 years ago
- ☆35Updated 5 years ago
- Smooth Loss Functions for Deep Top-k Classification☆253Updated 3 years ago
- Useful PyTorch functions and modules that are not implemented in PyTorch by default☆187Updated last year
- Implementation of OctConv in Pytorch (https://arxiv.org/abs/1904.05049)☆214Updated 6 years ago
- Standardizing weights to accelerate micro-batch training☆547Updated 3 years ago
- Test Time Augmentation (TTA) wrapper for computer vision tasks: segmentation, classification, super-resolution, ... etc.☆123Updated 3 years ago
- PyTorch implementation of shake-shake regularization☆48Updated 5 years ago
- Pytorch notebook with One Cycle Policy implementation (https://arxiv.org/abs/1803.09820)☆74Updated 2 years ago
- Keras implementation of Octave Convolutions☆53Updated 6 years ago
- Tensorflow implementation of "Compounding the Performance Improvements of Assembled Techniques in a Convolutional Neural Network"☆327Updated 4 years ago
- Utilities for Pytorch☆89Updated 2 years ago
- Over9000 optimizer☆426Updated 2 years ago
- Keras implementation of Attention Augmented Convolutional Neural Networks☆121Updated 5 years ago
- A pytorch dataset sampler for always sampling balanced batches.☆114Updated 4 years ago
- Code for https://arxiv.org/abs/1810.04622☆141Updated 5 years ago
- A specially designed light version of Fast AutoAugment☆171Updated 4 years ago
- Implementing Lambda Networks using Pytorch☆139Updated 4 years ago