Machine Learning · GitHub

APDTFlow is a modern and extensible forecasting framework for time series data that leverages advanced techniques including neural ordinary differential equations (Neural ODEs), transformer-based components, and probabilistic modeling. Its modular design allows researchers and practitioners to experiment with multiple forecasting models and easily

[CVPR 2020] CenterMask : Real-time Anchor-Free Instance Segmentation

• First anchor-free one-stage instance segmentation. To the best of our knowledge, CenterMask is the first instance segmentation on top of anchor-free object detection (15/11/2019).
• Toward Real-Time: CenterMask-Lite. This works provide not only large-scale CenterMask but also lightweight CenterMask-Lite that can run at real-time speed (> 30 fps).

A reimplementation of Stable Diffusion 3.5 in pure PyTorch

An application tool of edge-connect, which can do anime inpainting and drawing. 动漫人物图片自动修复，去马赛克，填补，去瑕疵

[CVPR 2022] Thin-Plate Spline Motion Model for Image Animation.

验证码识别

[T-PAMI] A curated list of self-supervised multimodal learning resources.

The convertor/conversion of deep learning models for different deep learning frameworks/softwares.

One-click training of your own GPT. Training a GPT has never been easier for beginners. / 一键预训练+SFT一个属于自己的LLM，0基础训练GPT原来可以这么简单？

• 🔤 Flexible Tokenization — Character-level or custom tokenizers (Qwen, etc.)
• 🚄 Efficient Training — Multi-process acceleration & distributed training

Fast, modular reference implementation and easy training of Semantic Segmentation algorithms in PyTorch.

• Modular Design: easily construct customized semantic segmentation models by combining different components.
• Distributed Training: >60% faster than the multi-thread parallel method(nn.DataParallel), we use the multi-processing parallel method.

Keras implementation of a CNN network for age and gender estimation