Juntang Zhuang

Adabelief-Optimizer. Repository for NeurIPS 2020 Spotlight "AdaBelief Optimizer: Adapting stepsizes by the belief in observed gradients"

ShelfNet. implementation for paper "ShelfNet for fast semantic segmentation"

GSAM. PyTorch repository for ICLR 2022 paper (GSAM) which improves generalization (e.g. +3.8% top-1 accuracy on ImageNet with ViT-B/32)

LadderNet. Python

torch_ACA. repo for paper: Adaptive Checkpoint Adjoint (ACA) method for gradient estimation in neural ODE

TorchDiffEqPack. Python

ShelfNet-lw-cityscapes. ShelfNet-lightweight for paper [ShelfNet for fast semantic segmentation]

ACProp-Optimizer. Implementation for ACProp ( Momentum centering and asynchronous update for adaptive gradient methdos, NeurIPS 2021)

explain_invertible. repo for "Decision explanation and feature importance for invertible networks"

SNGAN-AdaBelief. Train SN-GAN with AdaBelief

fairseq-adabelief. Python

SAC-Adabelief. Python

machine-learning-notes. My continuously updated Machine Learning, Probabilistic Models and Deep Learning notes and demos (2000+ slides) 我不间断更新的机器学习，概率模型和深度学习的讲义(2000+页)和视频链接

transformer-adabelief. Python

rainbow-adabelief. HTML

EAdam-optimizer. Some improvements on Adam

mit-deep-learning-book-pdf. MIT Deep Learning Book in PDF format (complete and parts) by Ian Goodfellow, Yoshua Bengio and Aaron Courville

datasets. 🤗 The largest hub of ready-to-use datasets for ML models with fast, easy-to-use and efficient data manipulation tools

keras. Deep Learning for humans

Awesome-LLM-Strawberry. A collection of LLM papers, blogs, and projects, with a focus on OpenAI o1 and reasoning techniques.

fairseq. Facebook AI Research Sequence-to-Sequence Toolkit written in Python.

symplectic-adjoint-method. Code for "Symplectic Adjoint Method for Exact Gradient of Neural ODE with Minimal Memory," NeurIPS, 2021.

PyTorch-Wavelet-Toolbox. Differentiable fast wavelet transforms in PyTorch with GPU support.

machine_learning_refined. Notes, examples, and Python demos for the textbook "Machine Learning Refined" (published by Cambridge University Press).

pytorch-image-models. PyTorch image models, scripts, pretrained weights -- ResNet, ResNeXT, EfficientNet, EfficientNetV2, NFNet, Vision Transformer, MixNet, MobileNet-V3/V2, RegNet, DPN, CSPNet, and more

addons. Useful extra functionality for TensorFlow 2.x maintained by SIG-addons

CS-Notes. :books: 技术面试必备基础知识、Leetcode、计算机操作系统、计算机网络、系统设计

federated. A collection of Google research projects related to Federated Learning and Federated Analytics.

audio. Data manipulation and transformation for audio signal processing, powered by PyTorch

system-design-primer. Learn how to design large-scale systems. Prep for the system design interview. Includes Anki flashcards.

Uni-Fold. Python

juntang-zhuang.github.io. HTML

flax. Flax is a neural network library for JAX that is designed for flexibility.

pytorch. Tensors and Dynamic neural networks in Python with strong GPU acceleration

adabelief-toy-examples-pytorch. numerical experiments in https://arxiv.org/pdf/2010.07468.pdf

alphafold2. To eventually become an unofficial Pytorch implementation / replication of Alphafold2, as details of the architecture get released