usryokousha Goto Github PK

custom_ops

Deformable Convolution Networks(deformable conv2D TF_implementation)

dinov2

PyTorch code and models for the DINOv2 self-supervised learning method.

fourier-deconvolution-network

Code for ICCV 2017 paper "Learning to Push the Limits of Efficient FFT-based Image Deconvolution" (Jakob Kruse, Carsten Rother, and Uwe Schmidt)

hydra-video

ijepa

Official codebase for I-JEPA, the Image-based Joint-Embedding Predictive Architecture. First outlined in the CVPR paper, "Self-supervised learning from images with a joint-embedding predictive architecture."

imagereconstruction

A repository of MATLAB code for understanding simple phase retrieval and image reconstruction algorithms as well as extracting the point spread functions of real data. Also, a relatively simple example that uses a steepest descent approach to minimize an error metric in a large parameter space.

memory-efficient-attention-pytorch

Implementation of a memory efficient multi-head attention as proposed in the paper, "Self-attention Does Not Need O(n²) Memory"

models

Models and examples built with TensorFlow

muse-maskgit-pytorch

Implementation of Muse: Text-to-Image Generation via Masked Generative Transformers, in Pytorch

odl

Operator Discretization Library https://odlgroup.github.io/odl/

perceiver-ar

perceiver-io

A PyTorch implementation of DeepMind's Perceiver IO with PyTorch Lightning scripts for distributed training

phase_retrieval

Implement Phase Retrieval

score_sde

Official code for Score-Based Generative Modeling through Stochastic Differential Equations (ICLR 2021, Oral)

score_sde_pytorch

PyTorch implementation for Score-Based Generative Modeling through Stochastic Differential Equations (ICLR 2021, Oral)

simmim

This is an official implementation for "SimMIM: A Simple Framework for Masked Image Modeling".

slowfast

PySlowFast: video understanding codebase from FAIR for reproducing state-of-the-art video models.

torchscale

Transformers at any scale

usryokousha.github.io

My personal static website

vit-pytorch

Implementation of Vision Transformer, a simple way to achieve SOTA in vision classification with only a single transformer encoder, in Pytorch

vmod