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

A clear, concise, simple yet powerful and efficient API for deep learning.

Infrastructures™ for Machine Learning Training/Inference in Production.

A lightweight deep learning library

One-Stop System for Machine Learning.

Deep Learning Library. For education. Based on pure Numpy. Support CNN, RNN, LSTM, GRU etc.

A deep learning framework created from scratch with Python and NumPy

benchmark for embededded-ai deep learning inference engines, such as NCNN / TNN / MNN / TensorFlow Lite etc.

[Experimental] Graph and Tensor Abstraction for Deep Learning all in Common Lisp

[MICCAI'24] Official implementation of "BGF-YOLO: Enhanced YOLOv8 with Multiscale Attentional Feature Fusion for Brain Tumor Detection".

[IMAVIS] Official implementation of "ASF-YOLO: A Novel YOLO Model with Attentional Scale Sequence Fusion for Cell Instance Segmentation".

以jax为后端的类似keras的框架

[CVPR 2024] CFAT: Unleashing Triangular Windows for Image Super-resolution

NumPy-based Dynamic Deep Learning Framework

Explore the latest AI Agent Toolkit!

Deep Learning framework in C++/CUDA that supports symbolic/automatic differentiation, dynamic computation graphs, tensor/matrix operations accelerated by GPU and implementations of various state-of-the-art graph neural networks and other Machine Learning models including Covariant Compositional Networks For Learning Graphs [Risi et al]

🌳 An educational modern C++ deep learning framework supporting CUDA

Flow-based data pre-processing for deep learning

Imperative deep learning framework with customized GPU and CPU backend

Facial Expression Recognition (FER) for Mental Health Detection applies AI models like Swin Transformer, CNN, and ViT for detecting emotions linked to anxiety, depression, PTSD, and OCD. It focuses on AI for mental health, emotion detection using OpenCV Python, and real-time applications in healthcare and HR systems.