Basic unsupervised implementation of Layer-wise Relevance Propagation (Bach et al.,Montavon et al.) in PyTorch for VGG networks from PyTorch’s Model Zoo.This tutorial served as a starting point.In this implementation, I tried to make sure that the code is easy to understand and easy to extend to othernetwork architectures. I also added a novel relevance propagation filter to this implementation resulting in much crisper heatmaps(see my blog for more information).If you want to use it, please don’t forget to cite this […]

Official Pytorch Implementation for Deep Contextual Video Compression, NeurIPS 2021 Python 3.8 and conda, get Conda CUDA 11.0 Environment conda create -n $YOUR_PY38_ENV_NAME python=3.8 conda activate $YOUR_PY38_ENV_NAME pip install torch==1.7.1+cu110 torchvision==0.8.2+cu110 torchaudio==0.7.2 -f https://download.pytorch.org/whl/torch_stable.html python -m pip install -r requirements.txt Currenlty the spatial resolution of video needs to be cropped into the integral times of 64. The dataset format can be seen in dataset_config_example.json. For example, one video of HEVC Class B can be prepared as: Crop the original YUV […]

Code for reproducing the experiments in the paper: Jayoung Kim*, Jinsung Jeon*, Jaehoon Lee, Jihyeon Hyeong, Noseong Park. “FFJORD: Free-form Continuous Dynamics for Scalable Reversible Generative Models.” International World Wide Web Conference (2021).[arxiv] GitHub View Github    

Rethinking of Pedestrian Attribute Recognition: A Reliable Evaluation under Zero-Shot Pedestrian Identity Setting (official Pytorch implementation) This paper submitted to TIP is the extension of the previous Arxiv paper. This project aims to provide a strong baseline for Pedestrian Attribute Recognition and Multi-Label Classification. provide two new datasets RAPzs and PETAzs following zero-shot pedestrian identity setting. provide a general training pipeline for pedestrian attribute recognition and multi-label classification task. This project provide DDP training, which is mainly used for multi-label […]

Unofficial implementation of the Pix2Seq paper Different from the paper image input size 1280 bin size 1280 LambdaLR scheduler used instead of LinearLR resnet50 instead of resnet50d or resnet101 etc. Download first the coco2017 dataset and put it under the dataset folder. – dataset – annotations – instances_train2017.json – instances_val2017.json – train2017 – 000000000000.jpg – … – val2017 python train.py –config configs/pix2seq.yaml GitHub View Github    

This is the official repository for our paper: Sharpness-aware Quantization for Deep Neural Networks by Jing Liu, Jianfei Cai, and Bohan Zhuang. Recent Update 2021.11.24: We release the source code of SAQ. Setup the environments Clone the repository locally: git clone https://github.com/zhuang-group/SAQ Install pytorch 1.8+, tensorboard and prettytable conda install pytorch torchvision torchaudio cudatoolkit=11.3 -c pytorch pip install tensorboard pip install prettytable Data preparation

This is a deep learning library that makes face recognition efficient, and effective, which can train tens of millionsidentity on a single server. Requirements How to Training To train a model, run train.py with the path to the configs: 1. Single node, 8 GPUs: python -m torch.distributed.launch –nproc_per_node=8 –nnodes=1 –node_rank=0 –master_addr=”127.0.0.1″ –master_port=1234 train.py configs/ms1mv3_r50 2. Multiple nodes, each node 8 GPUs: Node 0: python -m torch.distributed.launch –nproc_per_node=8 –nnodes=2 –node_rank=0 –master_addr=

서강대학교 현대모비스 SW 프로그램에서 진행한 인공지능 프로젝트입니다. Jetson nano를 이용해 pre-trained network를 fine tuning시켜 차량 및 신호등 인식을 구현하였습니다. https://www.youtube.com/watch?v=jYsIBuAgdao This repo implements SSD (Single Shot MultiBox Detector) in PyTorch for object detection, using MobileNet backbones. It also has out-of-box support for retraining on Google Open Images dataset. For documentation, please refer to Object Detection portion of the Hello AI World tutorial:Re-training SSD-Mobilenet Thanks to @qfgaohao for the upstream implementation from: https://github.com/qfgaohao/pytorch-ssd GitHub View Github    

PyTorch-LIT is the Lite Inference Toolkit (LIT) for PyTorch which focuses on easy and fast inference of large models on end-devices. With the rapid growth of deep learning research, models are becoming increasingly complex in terms of parameters and complexity, making it difficult to run the models on currently available end devices. For example, GPT-J with 6B parameters only needs 24 GB of RAM in full-precision mode to be ready for execution, which may be impossible in most systems; even […]

This is an implementation of the following paper: Yue Zhao, Meng Li, Liangzhen Lai, Naveen Suda, Damon Civin, Vikas Chandra. Federated Learning with Non-IID DataarXiv:1806.00582. Paper TL;DR: Previous federated optization algorithms (such as FedAvg and FedProx) converge to stationary points of a mismatched objective function due to heterogeneity in data distribution. In this paper, the authors propose a data-sharing strategy to improve training on non-IID data by creating a small subset of data which is globally shared between all the […]