NVIDIA/DeepLearningExamples Alternatives

choose when you want a maintained PyTorch library with hundreds of pretrained image backbones rather than standalone NVIDIA example scripts.

The largest collection of PyTorch image encoders / backbones. Including train, eval, inference, export scripts, and pretrained weights -- ResNet, ResNeXT, EfficientNet, NFNet, Vision Transformer (ViT), MobileNetV4, MobileNet-V3 & V2, RegNet, DPN, CSPNet, Swin Transformer, MaxViT, CoAtNet, ConvNeXt, and more

choose for a config-driven object-detection toolbox with many models; note it has not been updated in about 2 years.

OpenMMLab Detection Toolbox and Benchmark

choose when you specifically need an actively maintained face recognition/analysis toolkit instead of generic NVIDIA vision examples.

State-of-the-art 2D and 3D Face Analysis Project

choose for a comprehensive framework for speech/LLM/multimodal AI instead of standalone example scripts.

A scalable generative AI framework built for researchers and developers working on Large Language Models, Multimodal, and Speech AI (Automatic Speech Recognition and Text-to-Speech)

choose for SOTA audio/music generation models like MusicGen in a maintained library instead of NVIDIA speech synthesis examples.

Audiocraft is a library for audio processing and generation with deep learning. It features the state-of-the-art EnCodec audio compressor / tokenizer, along with MusicGen, a simple and controllable music generation LM with textual and melodic conditioning.

choose for a maintained audio/music/speech generation toolkit with reproducible research instead of seed's speech examples.

Amphion (/æmˈfaɪən/) is a toolkit for Audio, Music, and Speech Generation. Its purpose is to support reproducible research and help junior researchers and engineers get started in the field of audio, music, and speech generation research and development.

choose for a single ultra-lightweight mobile anchor-free detector, but it is narrower and unmaintained.

NanoDet-Plus⚡Super fast and lightweight anchor-free object detection model. 🔥Only 980 KB(int8) / 1.8MB (fp16) and run 97FPS on cellphone🔥

choose for a sandbox of cross-framework image classification models, but stale and narrower.

Sandbox for training deep learning networks

choose for Apple's CV training library if you want a different framework, but it is stale and narrower.

CVNets: A library for training computer vision networks

choose for a simple older detection framework as a baseline, but stale and narrower.

A Simple and Versatile Framework for Object Detection and Instance Recognition

choose if you target Jetson edge devices and need TensorRT inference examples rather than general-purpose training scripts.

Hello AI World guide to deploying deep-learning inference networks and deep vision primitives with TensorRT and NVIDIA Jetson.