Bastien Rigaud's starred repositories
vit-pytorch
Implementation of Vision Transformer, a simple way to achieve SOTA in vision classification with only a single transformer encoder, in Pytorch
pytorch-image-models
The largest collection of PyTorch image encoders / backbones. Including train, eval, inference, export scripts, and pretrained weights -- ResNet, ResNeXT, EfficientNet, NFNet, Vision Transformer (ViT), MobileNetV4, MobileNet-V3 & V2, RegNet, DPN, CSPNet, Swin Transformer, MaxViT, CoAtNet, ConvNeXt, and more
pytorch-deep-learning
Materials for the Learn PyTorch for Deep Learning: Zero to Mastery course.
hdl_graph_slam
3D LIDAR-based Graph SLAM
TopologyLayer
A Topology Layer for Machine Learning : Persistent Homology + Features for PyTorch
Spade-Normalization-Tensorflow-keras-layer
Spade Normalization as tensorflow keras layer
pixel2style2pixel
Official Implementation for "Encoding in Style: a StyleGAN Encoder for Image-to-Image Translation" (CVPR 2021) presenting the pixel2style2pixel (pSp) framework
approachingalmost
Approaching (Almost) Any Machine Learning Problem
RangerOptimizerTensorflow
This repository provides a class which can be used for the optimization of a tf.keras model. It combines the two optimizers Lookahead and RAdam to form the optimizer Ranger. According to published papers and competition results this optimizer is relatively good at training models quickly.