sdoria / SimpleSelfAttentionLinks
A simpler version of the self-attention layer from SAGAN, and some image classification results.
☆212Updated 6 years ago
Alternatives and similar repositories for SimpleSelfAttention
Users that are interested in SimpleSelfAttention are comparing it to the libraries listed below
Sorting:
- Mish Deep Learning Activation Function for PyTorch / FastAI☆161Updated 5 years ago
- Repo to build on / reproduce the record breaking Ranger-Mish-SelfAttention setup on FastAI ImageWoof dataset 5 epochs☆116Updated 5 years ago
- Unofficial PyTorch Implementation of EvoNorm☆122Updated 4 years ago
- homura is a library for fast prototyping DL research☆106Updated 3 years ago
- ☆35Updated 6 years ago
- Utilities for Pytorch☆88Updated 2 years ago
- Test Time Augmentation (TTA) wrapper for computer vision tasks: segmentation, classification, super-resolution, ... etc.☆125Updated 3 years ago
- Pytorch notebook with One Cycle Policy implementation (https://arxiv.org/abs/1803.09820)☆73Updated 3 years ago
- Simple Tensorflow implementation of "On The Variance Of The Adaptive Learning Rate And Beyond"☆97Updated 5 years ago
- Visualisation tool for CNNs in pytorch☆253Updated 2 years ago
- Keras implementation of Octave Convolutions☆53Updated 6 years ago
- A PyTorch implementation of " EfficientNet: Rethinking Model Scaling for Convolutional Neural Networks."☆313Updated 5 years ago
- Using the CLR algorithm for training (https://arxiv.org/abs/1506.01186)☆108Updated 7 years ago
- Keras callback function for stochastic weight averaging☆56Updated 3 years ago
- Implementation of tools to control and monitor layer rotation in different DL libraries☆40Updated 6 years ago
- Implementation and experiments for AdamW on Pytorch☆94Updated 5 years ago
- Semi-supervised ImageNet1K models☆244Updated 5 years ago
- High-level batteries-included neural network training library for Pytorch☆401Updated 3 years ago
- Visualization of GAN training process☆93Updated 5 years ago
- Experiments with Adam/AdamW/amsgrad☆201Updated 7 years ago
- Useful PyTorch functions and modules that are not implemented in PyTorch by default☆188Updated last year
- Smooth Loss Functions for Deep Top-k Classification☆257Updated 4 years ago
- Robust Bi-Tempered Logistic Loss Based on Bregman Divergences. https://arxiv.org/pdf/1906.03361.pdf☆147Updated 3 years ago
- Discover augmentation strategies tailored for your dataset☆250Updated 5 years ago
- Implementation of OctConv in Pytorch (https://arxiv.org/abs/1904.05049)☆214Updated 6 years ago
- Over9000 optimizer☆425Updated 2 years ago
- Implementation of Octave Convolution from Drop an Octave: Reducing Spatial Redundancy in Convolutional Neural Networks with Octave Convol…☆57Updated 6 years ago
- Implements https://arxiv.org/abs/1711.05101 AdamW optimizer, cosine learning rate scheduler and "Cyclical Learning Rates for Training Neu…☆151Updated 6 years ago
- Torchélie is a set of utility functions, layers, losses, models, trainers and other things for PyTorch.☆110Updated 3 weeks ago
- Learning computer vision by striving to maximise accuracy on the Stanford Cars dataset☆57Updated 5 years ago