Pytorch implementation of MaskGIT: Masked Generative Image Transformer (https://arxiv.org/pdf/2202.04200.pdf) Note: this is work in progress MaskGIT is an extension to the VQGAN paper which improves the second stage transformer part (and leaves the first stage untouched). It switches the unidirectional transformer for a bidirectional transformer. The (second stage) training is pretty similar to BERT by randomly masking out tokens and trying to predict these using the bidirectional transformer (the original work used a GPT architecture randomly replaced tokens by other […]

PyTorch implementation of the Sharpened Cosine Distance operator. The core idea came from Brandon Rohrer(@brohrer) and the implementationis based on the tf/keras implementation of Raphael Pisoni. This implementation supports 2D operation only asymmetric kernels, any shape CUDA / GPU If you find this implementation useful please give it a star. Open issues for bugs/ideas. If you are planning to build something on top of it let me know, I am always up for some good collaborations 😉 GitHub View Github […]

CMSEA Architecture Requirements

Introduction This project uses ViT to perform image classification tasks on DATA set CIFAR10. The implement of Vit and pretrained weight are from https://github.com/asyml/vision-transformer-pytorch. Installation Create environment: conda create –name vit –file requirements.txt conda activate vit Datasets Download the CIFAR10 from http://www.cs.toronto.edu/~kriz/cifar.html, creat data floder and unzip the cifar-10-python.tar.gz in ‘data/’. python main.py GitHub View Github    

This project is a PyTorch implementation for Transition Matrix Representation of Trees with Transposed Convolutions, published as a conference proceeding atSDM 2022. The paper proposes TART (Transition Matrix Representation withTransposed Convolutions), a novel framework for generalizing tree models with aunifying view. Requirements The repository is written by Python 3.7 with the packages listed inrequirements.txt. A GPU environment is strongly recommended for efficienttraining and inference of our model. You can type the following command toinstall the required packages: pip install -r […]