Stars
appbuilder-sdk, 千帆AppBuilder-SDK帮助开发者灵活、快速的搭建AI原生应用
Making large AI models cheaper, faster and more accessible
The Torch-MLIR project aims to provide first class support from the PyTorch ecosystem to the MLIR ecosystem.
Play with MLIR right in your browser
🤖 PaddleViT: State-of-the-art Visual Transformer and MLP Models for PaddlePaddle 2.0+
Open deep learning compiler stack for cpu, gpu and specialized accelerators
飞桨大模型开发套件,提供大语言模型、跨模态大模型、生物计算大模型等领域的全流程开发工具链。
PyTorch implementation of adversarial attacks [torchattacks]
A Python toolbox to create adversarial examples that fool neural networks in PyTorch, TensorFlow, and JAX
A PyTorch Library for Meta-learning Research
The Open Source Framework for Machine Vision
Code relative to "Reliable evaluation of adversarial robustness with an ensemble of diverse parameter-free attacks"
pytorch structural similarity (SSIM) loss
Automatic architecture search and hyperparameter optimization for PyTorch
Implementation of Vision Transformer, a simple way to achieve SOTA in vision classification with only a single transformer encoder, in Pytorch
This is an official implementation for "Swin Transformer: Hierarchical Vision Transformer using Shifted Windows".
InterpretDL: Interpretation of Deep Learning Models,基于『飞桨』的模型可解释性算法库。
OpenMMLab Text Detection, Recognition and Understanding Toolbox
Unified Multilingual Robustness Evaluation Toolkit for Natural Language Processing
TextAttack 🐙 is a Python framework for adversarial attacks, data augmentation, and model training in NLP https://textattack.readthedocs.io/en/master/
Public release of code for Robust Physical-World Attacks on Deep Learning Visual Classification (Eykholt et al., CVPR 2018)
SimCLRv2 - Big Self-Supervised Models are Strong Semi-Supervised Learners