advancedeast

AdvancedEAST is an algorithm used for Scene image text detect, which is primarily based on EAST, and the significant improvement was also made, which make long text predictions more accurate.

alaska2

Code For ALASKA2

attack-imagenet-tianchi

天池对抗样本-黑盒攻击

beibuwandeluori

Config files for my GitHub profile.

birdclef2022

Code for BirdClef

chatglm-6b

ChatGLM-6B：开源双语对话语言模型 | An Open Bilingual Dialogue Language Model

cldc

Code for Kaggle 2020 Cassava Leaf Disease Classification

clip

code for RANZCR CLiP - Catheter and Line Position Challenge

convnext

Code release for ConvNeXt model

cov-pooling-steganalytic-network

A fast and effective global covariance pooling network for image steganalysis in spatial domain.

csig_audio

code for csig audio deepfake detection

dcgan-tensorflow

A tensorflow implementation of "Deep Convolutional Generative Adversarial Networks"

deeperforensicschallengesolution

The solution for the DeeperForensics Challenge 2020

deepfacelab

DeepFaceLab is a tool that utilizes machine learning to replace faces in videos. Includes prebuilt ready to work standalone Windows 7,8,10 binary (look readme.md).

deeplearningtutorials

Deep Learning与PyTorch入门实战视频教程

dfgc_detection

The 1st solution for the DeepFake Game Competition (DFGC) @ IJCB 2021 Detection track.

draggan

Official Code for DragGAN (SIGGRAPH 2023)

gaiic_track1

code

grounded-segment-anything

Marrying Grounding DINO with Segment Anything & Stable Diffusion & BLIP & Whisper & ChatBot - Automatically Detect , Segment and Generate Anything with Image, Text, and Audio Inputs

lama-cleaner

Image inpainting tool powered by SOTA AI Model. Remove any unwanted object, defect, people from your pictures or erase and replace(powered by stable diffusion) any thing on your pictures.

naic_person_reid_dmt

NAIC 2020

naic_pytorch_2021

baseline

qlora

QLoRA: Efficient Finetuning of Quantized LLMs

segment-anything

The repository provides code for running inference with the SegmentAnything Model (SAM), links for downloading the trained model checkpoints, and example notebooks that show how to use the model.

stable-diffusion

A latent text-to-image diffusion model without safety check

taac2021-tagging-azx

腾讯广告推荐大赛赛道二第十名

tfpyth

Putting TensorFlow back in PyTorch, back in TensorFlow (differentiable TensorFlow PyTorch adapters).

u-net-with-multi-scale-skip-connections-and-asymmetric-convolution-blocks

uwmgi

code for UWMGI