Lite-HRNet: A Lightweight High-Resolution Network

Related tags

Deep Learning realtime segmentation semantic-segmentation cityscapes ade20k realtime-segmentation lite-hrnet mmsegmentation litehrnet
Overview

LiteHRNet Benchmark

🔥 🔥 Based on MMsegmentation 🔥 🔥

Cityscapes

FCN resize concat

config mIoU last mAcc last eval last mIoU best mAcc best eval best download
fcn-resize-concat_litehr18-with-head_512x1024_8x2_160k_cityscapes 71.81 80.6 10 71.81 80.6 10 log | 20210816_121228.log.json
fcn-resize-concat_litehr18-with-head_512x1024_8x2_320k_cityscapes 71.96 80.43 10 71.96 80.43 10 log | 20210816_121228.log.json
fcn-resize-concat_litehr18-with-head_512x1024_8x2_640k_cityscapes 69.29 78.91 8 69.29 78.91 8 log | 20210816_121228.log.json
fcn-resize-concat_litehr18-without-head_512x1024_8x2_160k_cityscapes 68.99 77.63 10 68.99 77.63 10 log | 20210816_121228.log.json
fcn-resize-concat_litehr18-without-head_512x1024_8x2_320k_cityscapes 70.42 78.72 10 70.42 78.72 10 log | 20210816_121228.log.json
fcn-resize-concat_litehr18-without-head_512x1024_8x2_640k_cityscapes 67.12 75.84 7 67.12 75.84 7 log | 20210816_121228.log.json
fcn-resize-concat_litehr30-with-head_512x1024_8x2_160k_cityscapes 73.81 82.42 10 73.81 82.42 10 log | 20210816_121228.log.json
fcn-resize-concat_litehr30-with-head_512x1024_8x2_320k_cityscapes 74.46 82.41 10 74.46 82.41 10 log | 20210816_121228.log.json
fcn-resize-concat_litehr30-with-head_512x1024_8x2_640k_cityscapes 69.15 79.65 6 69.15 79.65 6 log | 20210816_121228.log.json
fcn-resize-concat_litehr30-without-head_512x1024_8x2_160k_cityscapes 72.11 80.72 10 72.11 80.72 10 log | 20210816_121228.log.json
fcn-resize-concat_litehr30-without-head_512x1024_8x2_320k_cityscapes 72.12 80.15 10 72.12 80.15 10 log | 20210816_121228.log.json
fcn-resize-concat_litehr30-without-head_512x1024_8x2_640k_cityscapes 67.31 77.76 5 67.31 77.76 5 log | 20210816_121228.log.json

FCN

config mIoU last mAcc last eval last mIoU best mAcc best eval best download
fcn_litehr18-with-head_512x1024_8x2_160k_cityscapes 71.49 79.95 10 71.49 79.95 10 log | 20210816_121228.log.json
fcn_litehr18-with-head_512x1024_8x2_320k_cityscapes 73.03 81.35 10 73.03 81.35 10 log | 20210816_121228.log.json
fcn_litehr18-with-head_512x1024_8x2_640k_cityscapes 68.06 76.67 8 68.26 77.17 7 log | 20210816_121228.log.json
fcn_litehr18-without-head_512x1024_8x2_160k_cityscapes 69.43 78.15 10 69.43 78.15 10 log | 20210816_121228.log.json
fcn_litehr18-without-head_512x1024_8x2_320k_cityscapes 70.61 78.87 10 70.61 78.87 10 log | 20210816_121228.log.json
fcn_litehr18-without-head_512x1024_8x2_640k_cityscapes 63.83 73.11 4 63.83 73.11 4 log | 20210816_121228.log.json
fcn_litehr30-with-head_512x1024_8x2_160k_cityscapes 72.65 81.36 10 72.65 81.36 10 log | 20210816_121228.log.json
fcn_litehr30-with-head_512x1024_8x2_320k_cityscapes 74.98 83.22 10 74.98 83.22 10 log | 20210816_121228.log.json
fcn_litehr30-with-head_512x1024_8x2_640k_cityscapes 69.11 78.88 6 69.11 78.88 6 log | 20210816_121228.log.json
fcn_litehr30-without-head_512x1024_8x2_160k_cityscapes 72.78 81.37 10 72.78 81.37 10 log | 20210816_121228.log.json
fcn_litehr30-without-head_512x1024_8x2_320k_cityscapes 72.37 80.29 10 72.37 80.29 10 log | 20210816_121228.log.json
fcn_litehr30-without-head_512x1024_8x2_640k_cityscapes 63.53 74.6 4 65.91 75.91 3 log | 20210816_121228.log.json

ADE20k

FCN resize concat

config mIoU last mAcc last eval last mIoU best mAcc best eval best download
fcn-resize-concat_litehr18-with-head_512x512_160k_ade20k 16.15 22.12 2 16.15 22.12 2 log | 20210816_121228.log.json
fcn-resize-concat_litehr18-with-head_512x512_160k_ade20k 24.2 31.67 10 24.2 31.67 10 log | 20210816_121228.log.json
fcn-resize-concat_litehr18-with-head_512x512_160k_ade20k 26.17 34.86 10 26.17 34.86 10 log | 20210816_121228.log.json
fcn-resize-concat_litehr18-without-head_512x512_160k_ade20k 16.89 22.96 2 16.89 22.96 2 log | 20210816_121228.log.json
fcn-resize-concat_litehr18-without-head_512x512_160k_ade20k 24.71 32.46 10 24.71 32.46 10 log | 20210816_121228.log.json
fcn-resize-concat_litehr30-with-head_512x512_160k_ade20k 16.77 22.89 2 16.77 22.89 2 log | 20210816_121228.log.json
fcn-resize-concat_litehr30-with-head_512x512_160k_ade20k 26.81 34.96 10 26.81 34.96 10 log | 20210816_121228.log.json
fcn-resize-concat_litehr30-without-head_512x512_160k_ade20k 16.37 22.7 2 16.37 22.7 2 log | 20210816_121228.log.json
fcn-resize-concat_litehr30-without-head_512x512_160k_ade20k 24.38 32.52 10 24.38 32.52 10 log | 20210816_121228.log.json

FCN

config mIoU last mAcc last eval last mIoU best mAcc best eval best download
fcn_litehr18-with-head_512x512_160k_ade20k 0 0 0 0 0 0 log | 20210816_121228.log.json
fcn_litehr18-with-head_512x512_160k_ade20k 23.82 31.51 10 23.82 31.51 10 log | 20210816_121228.log.json
fcn_litehr18-with-head_512x512_160k_ade20k 24.14 31.81 10 24.14 31.81 10 log | 20210816_121228.log.json
fcn_litehr18-without-head_512x512_160k_ade20k 12.23 17.0 2 12.23 17.0 2 log | 20210816_121228.log.json
fcn_litehr18-without-head_512x512_160k_ade20k 20.82 27.58 10 20.82 27.58 10 log | 20210816_121228.log.json
fcn_litehr18-without-head_512x512_160k_ade20k 21.98 29.06 10 21.98 29.06 10 log | 20210816_121228.log.json
fcn_litehr30-with-head_512x512_160k_ade20k 14.11 19.06 3 14.11 19.06 3 log | 20210816_121228.log.json
fcn_litehr30-with-head_512x512_160k_ade20k 24.06 31.78 10 24.06 31.78 10 log | 20210816_121228.log.json
fcn_litehr30-without-head_512x512_160k_ade20k 14.37 19.21 3 14.37 19.21 3 log | 20210816_121228.log.json
fcn_litehr30-without-head_512x512_160k_ade20k 25.22 32.67 10 25.22 32.67 10 log | 20210816_121228.log.json
You might also like...
Python scripts to detect faces in Python with the BlazeFace Tensorflow Lite models
Python scripts to detect faces in Python with the BlazeFace Tensorflow Lite models

Python scripts to detect faces using Python with the BlazeFace Tensorflow Lite models. Tested on Windows 10, Tensorflow 2.4.0 (Python 3.8).

Ibai Gorordo 46 Nov 17, 2022
Python codes for Lite Audio-Visual Speech Enhancement.

Lite Audio-Visual Speech Enhancement (Interspeech 2020) Introduction This is the PyTorch implementation of Lite Audio-Visual Speech Enhancement (LAVSE

Shang-Yi Chuang 85 Dec 1, 2022
A tutorial showing how to train, convert, and run TensorFlow Lite object detection models on Android devices, the Raspberry Pi, and more!
A tutorial showing how to train, convert, and run TensorFlow Lite object detection models on Android devices, the Raspberry Pi, and more!

A tutorial showing how to train, convert, and run TensorFlow Lite object detection models on Android devices, the Raspberry Pi, and more!

Evan 1.3k Jan 2, 2023
🍅🍅🍅YOLOv5-Lite: lighter, faster and easier to deploy. Evolved from yolov5 and the size of model is only 1.7M (int8) and 3.3M (fp16). It can reach 10+ FPS on the Raspberry Pi 4B when the input size is 320×320~
🍅🍅🍅YOLOv5-Lite: lighter, faster and easier to deploy. Evolved from yolov5 and the size of model is only 1.7M (int8) and 3.3M (fp16). It can reach 10+ FPS on the Raspberry Pi 4B when the input size is 320×320~

YOLOv5-Lite：lighter, faster and easier to deploy Perform a series of ablation experiments on yolov5 to make it lighter (smaller Flops, lower memory, a

pogg 1.5k Jan 5, 2023
Example scripts for the detection of lanes using the ultra fast lane detection model in Tensorflow Lite.
Example scripts for the detection of lanes using the ultra fast lane detection model in Tensorflow Lite.

TFlite Ultra Fast Lane Detection Inference Example scripts for the detection of lanes using the ultra fast lane detection model in Tensorflow Lite. So

Ibai Gorordo 12 Aug 27, 2022
Python scripts form performing stereo depth estimation using the HITNET model in Tensorflow Lite.
Python scripts form performing stereo depth estimation using the HITNET model in Tensorflow Lite.

TFLite-HITNET-Stereo-depth-estimation Python scripts form performing stereo depth estimation using the HITNET model in Tensorflow Lite. Stereo depth e

Ibai Gorordo 22 Oct 20, 2022
Swapping face using Face Mesh with TensorFlow Lite
Swapping face using Face Mesh with TensorFlow Lite

Swapping face using Face Mesh with TensorFlow Lite

iwatake 17 Apr 26, 2022
A repository that shares tuning results of trained models generated by TensorFlow / Keras. Post-training quantization (Weight Quantization, Integer Quantization, Full Integer Quantization, Float16 Quantization), Quantization-aware training. TensorFlow Lite. OpenVINO. CoreML. TensorFlow.js. TF-TRT. MediaPipe. ONNX. [.tflite,.h5,.pb,saved_model,tfjs,tftrt,mlmodel,.xml/.bin, .onnx]
A repository that shares tuning results of trained models generated by TensorFlow / Keras. Post-training quantization (Weight Quantization, Integer Quantization, Full Integer Quantization, Float16 Quantization), Quantization-aware training. TensorFlow Lite. OpenVINO. CoreML. TensorFlow.js. TF-TRT. MediaPipe. ONNX. [.tflite,.h5,.pb,saved_model,tfjs,tftrt,mlmodel,.xml/.bin, .onnx]

PINTO_model_zoo Please read the contents of the LICENSE file located directly under each folder before using the model. My model conversion scripts ar

Katsuya Hyodo 2.4k Jan 5, 2023
this is a lite easy to use virtual keyboard project for anyone to use
this is a lite easy to use virtual keyboard project for anyone to use

virtual_Keyboard this is a lite easy to use virtual keyboard project for anyone to use motivation I made this for this year's recruitment for RobEn AA

Mohamed Emad 3 Oct 23, 2021
Comments
  • CVE-2007-4559 Patch

    CVE-2007-4559 Patch

    Patching CVE-2007-4559

    Hi, we are security researchers from the Advanced Research Center at Trellix. We have began a campaign to patch a widespread bug named CVE-2007-4559. CVE-2007-4559 is a 15 year old bug in the Python tarfile package. By using extract() or extractall() on a tarfile object without sanitizing input, a maliciously crafted .tar file could perform a directory path traversal attack. We found at least one unsantized extractall() in your codebase and are providing a patch for you via pull request. The patch essentially checks to see if all tarfile members will be extracted safely and throws an exception otherwise. We encourage you to use this patch or your own solution to secure against CVE-2007-4559. Further technical information about the vulnerability can be found in this blog.

    If you have further questions you may contact us through this projects lead researcher Kasimir Schulz.

    opened by TrellixVulnTeam 0
Owner
null
GitHub https://arxiv.org/pdf/2104.06403.pdf
KSAI Lite is a deep learning inference framework of kingsoft, based on tensorflow lite

KSAI Lite is a deep learning inference framework of kingsoft, based on tensorflow lite

null 80 Dec 27, 2022
Fashion Landmark Estimation with HRNet

HRNet for Fashion Landmark Estimation (Modified from deep-high-resolution-net.pytorch) Introduction This code applies the HRNet (Deep High-Resolution

SVIP Lab 91 Dec 26, 2022
Train the HRNet model on ImageNet

High-resolution networks (HRNets) for Image classification News [2021/01/20] Add some stronger ImageNet pretrained models, e.g., the HRNet_W48_C_ssld_

HRNet 866 Jan 4, 2023
A lightweight face-recognition toolbox and pipeline based on tensorflow-lite

FaceIDLight ?? Description A lightweight face-recognition toolbox and pipeline based on tensorflow-lite with MTCNN-Face-Detection and ArcFace-Face-Rec

Martin Knoche 16 Dec 7, 2022
Implementation of 'lightweight' GAN, proposed in ICLR 2021, in Pytorch. High resolution image generations that can be trained within a day or two

512x512 flowers after 12 hours of training, 1 gpu 256x256 flowers after 12 hours of training, 1 gpu Pizza 'Lightweight' GAN Implementation of 'lightwe

Phil Wang 1.5k Jan 2, 2023
Boosting Monocular Depth Estimation Models to High-Resolution via Content-Adaptive Multi-Resolution Merging

Boosting Monocular Depth Estimation Models to High-Resolution via Content-Adaptive Multi-Resolution Merging This repository contains an implementation

Computational Photography Lab @ SFU 1.1k Jan 2, 2023
Official implement of Paper：A deeply supervised image fusion network for change detection in high resolution bi-temporal remote sening images

A deeply supervised image fusion network for change detection in high resolution bi-temporal remote sensing images 深度监督影像融合网络DSIFN用于高分辨率双时相遥感影像变化检测 Of

Chenxiao Zhang 135 Dec 19, 2022
Pyramid Grafting Network for One-Stage High Resolution Saliency Detection. CVPR 2022

PGNet Pyramid Grafting Network for One-Stage High Resolution Saliency Detection. CVPR 2022, CVPR 2022 (arXiv 2204.05041) Abstract Recent salient objec

CVTEAM 109 Dec 5, 2022
A lightweight Python-based 3D network multi-agent simulator. Uses a cell-based congestion model. Calculates risk, loudness and battery capacities of the agents. Suitable for 3D network optimization tasks.

AMAZ3DSim AMAZ3DSim is a lightweight python-based 3D network multi-agent simulator. It uses a cell-based congestion model. It calculates risk, battery

Daniel Hirsch 13 Nov 4, 2022
Lightweight mmm - Lightweight (Bayesian) Media Mix Model

Lightweight (Bayesian) Media Mix Model This is not an official Google product. L

Google 342 Jan 3, 2023