PyTorch implementations of deep reinforcement learning algorithms and environments

基于pytorch实现的目标检测训练框架，各个部分模块化，方便修改模型。包含目标检测模型、训练、验证、测试、剪枝再训练、wandb可视化、onnx导出。

Code for "Adversarial Noise Layer: Regularize Neural Network By Adding Noise"

Best Practices, code samples, and documentation for Computer Vision.

deep learning for image processing including classification and object-detection etc.

The official repo for CVPR2023 highlight paper "Gradient Norm Aware Minimization Seeks First-Order Flatness and Improves Generalization".

WSAM

Tied-Augment: Controlling Representation Similarity Improves Data Augmentation

PyHessian is a Pytorch library for second-order based analysis and training of Neural Networks

paper "O2U-Net: A Simple Noisy Label Detection Approach for Deep Neural Networks" code

This is a pytorch repository of YOLOv4, attentive YOLOv4 and mobilenet YOLOv4 with PASCAL VOC and COCO

Trainable Weight Averaging for Fast Convergence and Better Generalization

Exploiting Explainable Metrics for Augmented SGD [CVPR2022]

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

SAM: Sharpness-Aware Minimization (PyTorch)

Official repo for PAC-Bayes Information Bottleneck.

TRADES (TRadeoff-inspired Adversarial DEfense via Surrogate-loss minimization)

Latex CV template built with Font Awesome.

Implementation of ASAM: Adaptive Sharpness-Aware Minimization for Scale-Invariant Learning of Deep Neural Networks, ICML 2021.

On the Loss Landscape of Adversarial Training: Identifying Challenges and How to Overcome Them [NeurIPS 2020]

Implementation of Vision Transformer, a simple way to achieve SOTA in vision classification with only a single transformer encoder, in Pytorch

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

Code for our paper "Regularizing Neural Networks via Adversarial Model Perturbation", CVPR2021