Stars
YOLOv12: Attention-Centric Real-Time Object Detectors
The original implementation of the experiments in the paper of AdaShift (See https://arxiv.org/abs/1810.00143)
When it comes to optimizers, it's always better to be safe than sorry
The AdEMAMix Optimizer: Better, Faster, Older.
[CVPR 2025] Attention Distillation: A Unified Approach to Visual Characteristics Transfer
🧑🏫 60+ Implementations/tutorials of deep learning papers with side-by-side notes 📝; including transformers (original, xl, switch, feedback, vit, ...), optimizers (adam, adabelief, sophia, ...), ga…
A library for scientific machine learning and physics-informed learning
Muon optimizer: +>30% sample efficiency with <3% wallclock overhead
Implementation of Denoising Diffusion Probabilistic Model in Pytorch
Pytorch implementation of Diffusion Models (https://arxiv.org/pdf/2006.11239.pdf)
Schedule-Free Optimization in PyTorch
Ranger - a synergistic optimizer using RAdam (Rectified Adam), Gradient Centralization and LookAhead in one codebase
Code for Adam-mini: Use Fewer Learning Rates To Gain More https://arxiv.org/abs/2406.16793
Integrate the DeepSeek API into popular softwares
This repo includes ChatGPT prompt curation to use ChatGPT and other LLM tools better.
NoisyNN: Exploring the impact of information entropy change in learning systems
Neural Network optimizers implemented from scratch in numpy (Adam, Adadelta, RMSProp, SGD, etc.)
PINNs-Torch, Physics-informed Neural Networks (PINNs) implemented in PyTorch.
YOLOv5 🚀 in PyTorch > ONNX > CoreML > TFLite
This may be the simplest implement of DDPM. You can directly run Main.py to train the UNet on CIFAR-10 dataset and see the amazing process of denoising.
mobilenetv3 with pytorch，provide pre-train model
A PyTorch implementation of EfficientNet
Code for visualizing the loss landscape of neural nets