freedomlyle
Follow
Stars
The most powerful and modular diffusion model GUI, api and backend with a graph/nodes interface.
YOLOv5 🚀 in PyTorch > ONNX > CoreML > TFLite
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…
The largest collection of PyTorch image encoders / backbones. Including train, eval, inference, export scripts, and pretrained weights -- ResNet, ResNeXT, EfficientNet, NFNet, Vision Transformer (V…
Data Apps & Dashboards for Python. No JavaScript Required.
Fast and flexible image augmentation library. Paper about the library: https://www.mdpi.com/2078-2489/11/2/125
A flexible tool for creating, organizing, and sharing visualizations of live, rich data. Supports Torch and Numpy.
A PyTorch implementation of EfficientNet
A PyTorch Library for Accelerating 3D Deep Learning Research
The official PyTorch implementation of Towards Fast, Accurate and Stable 3D Dense Face Alignment, ECCV 2020.
💻深度学习实战：手写数字识别、Discuz验证码识别、垃圾分类、语义分割
A collection of state-of-the-art video or single-image super-resolution architectures, reimplemented in tensorflow.
Ranger - a synergistic optimizer using RAdam (Rectified Adam), Gradient Centralization and LookAhead in one codebase
Open source deep learning based unsupervised image retrieval toolbox built on PyTorch🔥
Fast and Accurate One-Stage Space-Time Video Super-Resolution (accepted in CVPR 2020)
基于PaddlePaddle实现的语音识别，中文语音识别。项目完善，识别效果好。支持Windows，Linux下训练和预测，支持Nvidia Jetson开发板预测。
[ECCV2020] A super-resolution dataset of paired LR-HR scene text images
Pytorch implementation of Structure-Preserving Super Resolution with Gradient Guidance (CVPR 2020 & TPAMI 2021)
A simple and complete implementation of super-resolution paper.
《Python数据分析与挖掘实战》随书源码与数据
人工智障本地图片检索工具 | An EfficientNet based image retrieval tool
🔥 🔥 🔥Train Your Own DataSet for YOLACT and YOLACT++ Instance Segmentation Model!!!
Meta-SR: A Magnification-Arbitrary Network for Super-Resolution (CVPR2019)