freedomlyle
Follow
Stars
The most powerful and modular diffusion model GUI, api and backend with a graph/nodes interface.
Data Apps & Dashboards for Python. No JavaScript Required.
Animate Anyone: Consistent and Controllable Image-to-Video Synthesis for Character Animation
The official PyTorch implementation of Towards Fast, Accurate and Stable 3D Dense Face Alignment, ECCV 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。
提供对YOLOv3及Tiny的多种剪枝版本，以适应不同的需求。
《Python数据分析与挖掘实战》随书源码与数据
Ranger - a synergistic optimizer using RAdam (Rectified Adam), Gradient Centralization and LookAhead in one codebase
A flexible tool for creating, organizing, and sharing visualizations of live, rich data. Supports Torch and Numpy.
The largest collection of PyTorch image encoders / backbones. Including train, eval, inference, export scripts, and pretrained weights -- ResNet, ResNeXT, EfficientNet, NFNet, Vision Transformer (V…
🔥 🔥 🔥Train Your Own DataSet for YOLACT and YOLACT++ Instance Segmentation Model!!!
A PyTorch Library for Accelerating 3D Deep Learning Research
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…
针对三维模型检索，并采用卷积神经网络，提出两个算法：1.采用体素化深层特征进行训练。2. 采用虚拟摄像机抓取多角度视图特征进行训练。
A PyTorch implementation of EfficientNet
💻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
YOLOv5 🚀 in PyTorch > ONNX > CoreML > TFLite
A cloud-native vector database, storage for next generation AI applications
人工智障本地图片检索工具 | An EfficientNet based image retrieval tool
Open source deep learning based unsupervised image retrieval toolbox built on PyTorch🔥
Fast and flexible image augmentation library. Paper about the library: https://www.mdpi.com/2078-2489/11/2/125
Pytorch implementation of Structure-Preserving Super Resolution with Gradient Guidance (CVPR 2020 & TPAMI 2021)
Rethinking Data Augmentation for Image Super-resolution (CVPR 2020)
Fast and Accurate One-Stage Space-Time Video Super-Resolution (accepted in CVPR 2020)