xxayt

GrabCut

C++ implementation for 《"GrabCut" — Interactive Foreground Extraction using Iterated Graph Cuts》

CS231n-2023-Assignments

Stanford University CS231n Spring 2023 - Assignment Solutions

CET6

六级真题总结

Classic-CNN

经典CNN模型复现

e-wardrobe

数据库设计大作业

Image-Matting

Three DIP Methods for Alpha Matting

mindspore-GAN

GAN based on MindSpore

ViT-for-Cifar100

Pytorch reimplementation of the Vision Transformer (An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale)

Boosted-Multi-View

Multi-View (Multi-Modal) Learning based on Boosting thinking (like AdaBoost)

MACA

Discussion about the Influence of Multi-Head Attention In Cross-Attention

2023BrithdayShow-for-yt

Classic-Transformer

DynamicMLP

Official Codes and Pretrained Models for Dynamic MLP, CVPR2022, https://arxiv.org/abs/2203.03253

LXMERT

PyTorch code for EMNLP 2019 paper "LXMERT: Learning Cross-Modality Encoder Representations from Transformers".

MetaFormer

A PyTorch implementation of "MetaFormer: A Unified Meta Framework for Fine-Grained Recognition". A reference PyTorch implementation of “CoAtNet: Marrying Convolution and Attention for All Data Sizes”

scnni

Simple Convolution Neural Network Inference Framework

ViLBERT

ViLT

Code for the ICML 2021 (long talk) paper: "ViLT: Vision-and-Language Transformer Without Convolution or Region Supervision"

ConvNeXt

Code release for ConvNeXt model

drawio

MCAN

Deep Modular Co-Attention Networks for Visual Question Answering（VQA）

NLP-Interview-Notes

该仓库主要记录 NLP 算法工程师相关的面试题

nothing

PromptSwitch

pytorch-image-models

PyTorch image models, scripts, pretrained weights -- ResNet, ResNeXT, EfficientNet, EfficientNetV2, NFNet, Vision Transformer, MixNet, MobileNet-V3/V2, RegNet, DPN, CSPNet, and more

Swin-Transformer-Object-Detection

This is an official implementation for Swin Transformer on Object Detection and Instance Segmentation. Besides, xzj add ConvNeXt model

TeachCLIP

Source code of our CVPR2024 paper TeachCLIP for Text-to-Video Retrieval

UT-CMVMR

ViLBERT-Multi-Task

Multi Task Vision and Language

xxayt.github.io