HarDNeXt: Official HarDNeXt repository

Last update: May 26, 2022

Related tags

Deep Learning HarDNeXt

Overview

HarDNeXt-Pytorch

HarDNeXt: A Stage Receptive Field and Connectivity Aware Convolution Neural Network

HarDNeXt-MSEG for Medical Image Segmentation in 0.913 mDice / 127 FPS, 0.910 mDice / 150 FPS on Kvasir-SEG dataset

Image Classification (ImgaeNet 2012)

Medical Image Segmentation (Kvasir-SEG)

Performance on ImageNet2012 Validation Set

Model Name	MAC(B)	FPS (2080 Ti)(FP32)	EPI	Top-1 Acc (FP32)
ResNet-34	3.67	347	0.435	73.3
DenseNet-121	2.88	97	1.08	74.65
HarDNet-39	2.12	245	0.487	74.4
HarDNeXt-28	2.07	359	0.354	74.09
HarDNeXt-32	2.11	324	0.397	74.5
HarDNeXt-39	2.84	299	0.466	75.36

Model Name	MAC(B)	FPS (2080 Ti)(FP32)	EPI	Top-1 Acc (FP32)
ResNet-50	4.12	257	0.643	76.15
DenseNet-169	3.42	71	1.571	76
HarDNet-68	4.26	149	0.836	76.5
HarDNeXt-50	3.51	215	0.619	76.32

Model Name	MAC(B)	FPS (2080 Ti)(FP32)	EPI	Top-1 Acc (FP32)
ResNet-101	7.84	141	1.207	77.3
DenseNet-201	4.37	58	1.92	77.2
ResNeXt-50	4.27	166	0.92	77.62
HarDNeXt-56	6.32	182	0.89	77.3

Training

python ./src/main.py --model_name hardnext --arch 39 /imagenet/data/path

Evaluation

python ./src/main.py --model_name hardnext --arch 39  --evaluation --resume /pretrained weight/data/path

HarDNeXt: Official HarDNeXt repository

Related tags

Overview

HarDNeXt-Pytorch

HarDNeXt: A Stage Receptive Field and Connectivity Aware Convolution Neural Network

HarDNeXt-MSEG for Medical Image Segmentation in 0.913 mDice / 127 FPS, 0.910 mDice / 150 FPS on Kvasir-SEG dataset

Image Classification (ImgaeNet 2012)

Medical Image Segmentation (Kvasir-SEG)

Performance on ImageNet2012 Validation Set

Training

Evaluation

Owner

Realtime_Multi-Person_Pose_Estimation

An atmospheric growth and evolution model based on the EVo degassing model and FastChem 2.0

Dilated Convolution with Learnable Spacings PyTorch

Semi-Supervised Learning, Object Detection, ICCV2021

Office source code of paper UniFuse: Unidirectional Fusion for 360$^\circ$ Panorama Depth Estimation

Official code repository for the publication "Latent Equilibrium: A unified learning theory for arbitrarily fast computation with arbitrarily slow neurons"

Collection of machine learning related notebooks to share.

Code for the paper "Graph Attention Tracking". (CVPR2021)

Zsseg.baseline - Zero-Shot Semantic Segmentation

PyTorch implementation of the paper Dynamic Token Normalization Improves Vision Transfromers.

Tensorflow-Project-Template - A best practice for tensorflow project template architecture.

This is a Pytorch implementation of the paper: Self-Supervised Graph Transformer on Large-Scale Molecular Data.

Pytorch Implementation of Zero-Shot Image-to-Text Generation for Visual-Semantic Arithmetic

Speedy Implementation of Instance-based Learning (IBL) agents in Python

Repository for self-supervised landmark discovery

[ICCV'2021] "SSH: A Self-Supervised Framework for Image Harmonization", Yifan Jiang, He Zhang, Jianming Zhang, Yilin Wang, Zhe Lin, Kalyan Sunkavalli, Simon Chen, Sohrab Amirghodsi, Sarah Kong, Zhangyang Wang

CL-Gym: Full-Featured PyTorch Library for Continual Learning

A Python module for parallel optimization of expensive black-box functions

Few-shot NLP benchmark for unified, rigorous eval

code for paper "Not All Unlabeled Data are Equal: Learning to Weight Data in Semi-supervised Learning" by Zhongzheng Ren, Raymond A. Yeh, Alexander G. Schwing.

HarDNeXt: Official HarDNeXt repository

Related tags

Overview

HarDNeXt-Pytorch

HarDNeXt: A Stage Receptive Field and Connectivity Aware Convolution Neural Network

HarDNeXt-MSEG for Medical Image Segmentation in 0.913 mDice / 127 FPS, 0.910 mDice / 150 FPS on Kvasir-SEG dataset

Image Classification (ImgaeNet 2012)

Medical Image Segmentation (Kvasir-SEG)

Performance on ImageNet2012 Validation Set

Training

Evaluation

Owner

Realtime_Multi-Person_Pose_Estimation

An atmospheric growth and evolution model based on the EVo degassing model and FastChem 2.0

Dilated Convolution with Learnable Spacings PyTorch

Semi-Supervised Learning, Object Detection, ICCV2021

Office source code of paper UniFuse: Unidirectional Fusion for 360$^\circ$ Panorama Depth Estimation

Official code repository for the publication "Latent Equilibrium: A unified learning theory for arbitrarily fast computation with arbitrarily slow neurons"

Collection of machine learning related notebooks to share.

Code for the paper "Graph Attention Tracking". (CVPR2021)

Zsseg.baseline - Zero-Shot Semantic Segmentation

PyTorch implementation of the paper Dynamic Token Normalization Improves Vision Transfromers.

Tensorflow-Project-Template - A best practice for tensorflow project template architecture.

This is a Pytorch implementation of the paper: Self-Supervised Graph Transformer on Large-Scale Molecular Data.

Pytorch Implementation of Zero-Shot Image-to-Text Generation for Visual-Semantic Arithmetic

Speedy Implementation of Instance-based Learning (IBL) agents in Python

Repository for self-supervised landmark discovery

[ICCV'2021] "SSH: A Self-Supervised Framework for Image Harmonization", Yifan Jiang, He Zhang, Jianming Zhang, Yilin Wang, Zhe Lin, Kalyan Sunkavalli, Simon Chen, Sohrab Amirghodsi, Sarah Kong, Zhangyang Wang

CL-Gym: Full-Featured PyTorch Library for Continual Learning

A Python module for parallel optimization of expensive black-box functions

Few-shot NLP benchmark for unified, rigorous eval

code for paper "Not All Unlabeled Data are Equal: Learning to Weight Data in Semi-supervised Learning" by Zhongzheng Ren*, Raymond A. Yeh*, Alexander G. Schwing.

code for paper "Not All Unlabeled Data are Equal: Learning to Weight Data in Semi-supervised Learning" by Zhongzheng Ren, Raymond A. Yeh, Alexander G. Schwing.