jinxiqinghuan's repositories
jinxiqinghuan.github.io
My blog project.
micronet
micronet, a model compression and deploy lib. compression: 1、quantization: quantization-aware-training(QAT), High-Bit(>2b)(DoReFa/Quantization and Training of Neural Networks for Efficient Integer-Arithmetic-Only Inference)、Low-Bit(≤2b)/Ternary and Binary(TWN/BNN/XNOR-Net); post-training-quantization(PTQ), 8-bit(tensorrt); 2、 pruning: normal、regular and group convolutional channel pruning; 3、 group convolution structure; 4、batch-normalization fuse for quantization. deploy: tensorrt, fp32/fp16/int8(ptq-calibration)、op-adapt(upsample)、dynamic_shape
Pytorch-Transformers
The implement of Transformers with Pytorch.
Real_ESRGAN_Paddle
The implement of Real_ESRGAN use Paddle.
StyleCLIP_Paddle
The implement of StyleCLIP use Paddle.
Swin-Transformer
This is an official implementation for "Swin Transformer: Hierarchical Vision Transformer using Shifted Windows".
TextGenerator
OCR dataset Text-Detection dataset Font-Classification dataset generator
2021_algorithm_intern_information
CV 算法工程师技术栈笔记，包含深度学习基础、计算机视觉知识笔记、算法岗面试题答案和 CV 岗面经，以及校招可投递公司信息表。
Brain-Tumor-Detection
Brain Tumor Detection Using Convolutional Neural Networks.
DocDiff
DocDiff: Document Enhancement via Residual Diffusion Models. The first diffusion-based models designed for diverse document enhancement tasks. This model is lightweight, efficient, flexible and can also be used for img2img tasks in natural scenes.
dp_models
Implement some famous models by Pytorch
MedImage_Format_Convert
A simple python program for medical image format convert.
Org_Registation_GUI
数字图像处理作业，基于orb特征检测算法的时间轴配准
PaddleOCR
Awesome multilingual OCR toolkits based on PaddlePaddle (practical ultra lightweight OCR system, support 80+ languages recognition, provide data annotation and synthesis tools, support training and deployment among server, mobile, embedded and IoT devices)
patchify.py
A library that helps you split image into small, overlappable patches, and merge patches into original image.
pycorrector
pycorrector is a toolkit for text error correction. 文本纠错，实现了Kenlm，T5，MacBERT，ChatGLM3，LLaMA等模型应用在纠错场景，开箱即用。
pytorch
Tensors and Dynamic neural networks in Python with strong GPU acceleration
pytorch-doc-zh
Pytorch 中文文档
PyTorch-GAN
PyTorch implementations of Generative Adversarial Networks.
text_renderer
Generate text images for training deep learning ocr model
wechat-chatgpt
Use ChatGPT On Wechat via wechaty