CTPN + DenseNet + CTC based end-to-end Chinese OCR implemented using tensorflow and keras

复现大模型相关算法及一些学习记录

Code for BLT research paper

Physical Symbolic Optimization

This is an official implementation for "Swin Transformer: Hierarchical Vision Transformer using Shifted Windows" on Object Detection and Instance Segmentation.

基于Frida的脱壳工具

Reproduce MTCNN using Tensorflow

Generate text images for training deep learning ocr model

PyTorch implementation of Multi-Label Image Recognition with Graph Convolutional Networks, CVPR 2019.

Research Framework for easy and efficient training of GANs based on Pytorch

🛠️ 哔哩哔哩（B站）辅助工具箱，支持Cookie/Token/Password融合持久化登录与多用户操作

Deep Image Matting

Scaling Up Your Kernels to 31x31: Revisiting Large Kernel Design in CNNs (CVPR 2022)

⚡ Based on Yolo's low-power, ultra-lightweight universal target detection algorithm, the parameter is only 250k, and the speed of the smart phone mobile terminal can reach ~300fps+

The implementation of various lightweight networks by using PyTorch. such as：MobileNetV2，MobileNeXt，GhostNet，ParNet，MobileViT、AdderNet，ShuffleNetV1-V2，LCNet，ConvNeXt，etc. ⭐⭐⭐⭐⭐

⚡ A newly designed ultra lightweight anchor free target detection algorithm， weight only 250K parameters， reduces the time consumption by 10% compared with yolo-fastest, and the post-processing is …

[验证码识别-部署] This project is based on CNN+BLSTM+CTC to realize verificationtion. This projeccode identificat is only for deployment models.

All-in-one Toolbox for Computer Vision Research.

A Diagnostic Dataset for Compositional Language and Elementary Visual Reasoning

Code for the paper "DewarpNet: Single-Image Document Unwarping With Stacked 3D and 2D Regression Networks" (ICCV '19)

Code release for Best-of-N Jailbreaking

Official implementation of paper "Query2Label: A Simple Transformer Way to Multi-Label Classification".

StyleShot: A SnapShot on Any Style. 一款可以迁移任意风格到任意内容的模型，无需针对图片微调，即能生成高质量的个性风格化图片!

Ensembling Off-the-shelf Models for GAN Training (CVPR 2022 Oral)

Official TensorFlow code for the paper "Efficient-CapsNet: Capsule Network with Self-Attention Routing".

基于MobileNetV2/EfficientNet-b0/... + LSTM + CTC的不定长图像识别训练pytorch框架

PyTorch code for "EleGANt: Exquisite and Locally Editable GAN for Makeup Transfer" (ECCV 2022)

Code and data for paper: https://arxiv.org/abs/1802.07101

pdd (拼多多) 爬虫 js 解密 anti_content 参数解密及全站抓取代码思路实现

Youtu-Embedding is an industry-leading, general-purpose text representation model developed by Tencent Youtu Lab.