deep learning for image processing (classification/detection) tutorials
A Chinese educational tutorial with videos, slides, and code that walks through implementing classic image classification (and some detection) network architectures in PyTorch and TensorFlow.
Same problem, same approach. Swapping one for another is a config change, not a rewrite.
Choose for a broader, actively maintained Chinese hands-on tutorial with 100 examples covering classification, detection, and NLP.
深度学习100例、深度学习DL、图片分类、目标识别、目标检测、自然语言处理nlp、文本分类、TensorFlow、PyTorch
Solves the same problem with a different architecture or at a different layer. Expect to rewrite the integration.
Use when you want a full-featured CV training library with many models instead of a tutorial-backed code walkthrough.
CVNets: A library for training computer vision networks
Use if you need a broader pre-built model zoo covering classification, segmentation, and detection without video explanations.
Sandbox for training deep learning networks
Use for production object detection with a large set of ready-made detector architectures.
OpenMMLab Detection Toolbox and Benchmark
Use when you need production-ready pretrained image encoders and training scripts instead of hand-written tutorial code.
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
Use for optimized official training scripts if you are on NVIDIA hardware and want reproducible performance.
State-of-the-Art Deep Learning scripts organized by models - easy to train and deploy with reproducible accuracy and performance on enterprise-grade infrastructure.
Use when you need a super-lightweight anchor-free detector for on-device deployment instead of learning from a tutorial.
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 well-commented single-file implementations of many papers, including classification and detection, if you don't need a guided course.
A resource for learning about Machine learning & Deep Learning
An earlier or more limited way to do the job. Still the right call when you need something small, proven, or CPU-only.
Same backbone-code collection but unmaintained for 1.6 years, so use only as a code reference.
Integrate deep learning models for image classification | Backbone learning/comparison/magic modification project
Older TF2 example snippets; use if you want a different set of examples and don't need updates.
🙄 Difficult algorithm, Simple code.
A 3.5-year-old TensorFlow port of Dive into Deep Learning; use as a systematic book rather than an image-specific course.
本项目将《动手学深度学习》(Dive into Deep Learning)原书中的MXNet实现改为TensorFlow 2.0实现，项目已得到李沐老师的认可
Use only if you specifically want BiT transfer-learning checkpoints; otherwise too narrow compared to the seed.
Official repository for the "Big Transfer (BiT): General Visual Representation Learning" paper.
Older, simple object detection framework; use if you need its legacy codebase.
A Simple and Versatile Framework for Object Detection and Instance Recognition
An older English video-course companion; use if you prefer a structured English course, but it is not updated recently.
All course materials for the Zero to Mastery Deep Learning with TensorFlow course.
These projects were analysed and named deep-learning-for-image-processing among their alternatives. The relationship is not symmetric — how deep-learning-for-image-processing rates them is a separate judgement, made when deep-learning-for-image-processing is analysed in its own right.
calls deep-learning-for-image-processing “Narrow, code-focused tutorials on image classification and detection; choose if your focus is computer vision.”
深度学习入门开源书，基于TensorFlow 2.0案例实战。Open source Deep Learning book, based on TensorFlow 2.0 framework.