linksense/LightNetPlusPlus linksense/LightNetPlusPlus

  • Stars
    star
    236
  • Rank 170,480 (Top 4 %)
  • Language
    Python
  • License
    MIT License
  • Created over 5 years ago
  • Updated over 4 years ago
Twitter logo Share LinkedIn logo Share Facebook logo Share
linksense/LightNetPlusPlus
github

linksense

Reviews

There are no reviews yet. Be the first to send feedback to the community and the maintainers!

Repository Details

LightNet++: Boosted Light-weighted Networks for Real-time Semantic Segmentation

LightNet++

!!!New Repo.!!! ⇒ EfficientNet.PyTorch: Concise, Modular, Human-friendly PyTorch implementation of EfficientNet with Pre-trained Weights

!!!New Repo.!!! ⇒ MixNet-Pytorch: Concise, Modular, Human-friendly PyTorch implementation of MixNet with Pre-trained Weights

This repository contains the code (PyTorch-1.0+, W.I.P.) for: "LightNet++: Boosted Light-weighted Networks for Real-time Semantic Segmentation" by Huijun Liu.
LightNet++ is an advanced version of LightNet, which purpose to get more concise model design, smaller models, and better performance.

  • MobileNetV2Plus: Modified MobileNetV2 (backbone)[1,8] + DSASPPInPlaceABNBlock[2,3] + Parallel Bottleneck Channel-Spatial Attention Block (PBCSABlock)[6] + UnSharp Masking (USM) + Encoder-Decoder Arch.[3] + InplaceABN[4].

  • ShuffleNetV2Plus: Modified ShuffleNetV2 (backbone)[1,8] + DSASPPInPlaceABNBlock[2,3] + Parallel Bottleneck Channel-Spatial Attention Block (PBCSABlock)[6]+ UnSharp Masking (USM) + Encoder-Decoder Arch.[3] + InplaceABN[4].

  • MixSeg-MixBiFPN: Modified MixNet (backbone)[1,8] + MixBiFPNBlock[2,3] + Encoder-Decoder Arch.[3]

More about USM(Unsharp Mask)-Operator Block see Repo: SharpPeleeNet

Dependencies

Datasets for Autonomous Driving

Results

Results on Cityscapes (Pixel-level/Semantic Segmentation)

Model mIoU (S.S* Mixed Precision) Model Weight
MobileNetV2Plus X1.0 71.5314 (WIP) cityscapes_mobilenetv2plus_x1.0.pkl (14.3 MB)
ShuffleNetV2Plus X1.0 69.0885-72.5255 (WIP) cityscapes_shufflenetv2plus_x1.0.pkl (8.59 MB)
MixSeg+MixBiFPN ArchS 72.2321 (WIP) cityscapes_mixseg_archs_mixbifpn.pkl (16.4 MB)
  • S.S.: Single Scale (1024x2048)

Feature Visualization

More Repositories

1

LightNet

LightNet: Light-weight Networks for Semantic Image Segmentation (Cityscapes and Mapillary Vistas Dataset)
Python
716
star
2

NNAEC-NeuralNetworkbasedAcousticEchoCancellation

NNAEC-Neural Network based Acoustic Echo Cancellation
MATLAB
41
star
3

EfficientNet.PyTorch

Concise, Modular, Human-friendly PyTorch implementation of EfficientNet with Pre-trained Weights.
Python
30
star
4

ConvolutionaNeuralNetworksToEnhanceCodedSpeech

In this work we propose two postprocessing approaches applying convolutional neural networks (CNNs) either in the time domain or the cepstral domain to enhance the coded speech without any modification of the codecs. The time domain approach follows an end-to-end fashion, while the cepstral domain approach uses analysis-synthesis with cepstral domain features. The proposed postprocessors in both domains are evaluated for various narrowband and wideband speech codecs in a wide range of conditions. The proposed postprocessor improves speech quality (PESQ) by up to 0.25 MOS-LQO points for G.711, 0.30 points for G.726, 0.82 points for G.722, and 0.26 points for adaptive multirate wideband codec (AMR-WB). In a subjective CCR listening test, the proposed postprocessor on G.711-coded speech exceeds the speech quality of an ITU-T-standardized postfilter by 0.36 CMOS points, and obtains a clear preference of 1.77 CMOS points compared to G.711, even en par with uncoded speech.
Python
27
star
5

MixNet-PyTorch

Concise, Modular, Human-friendly PyTorch implementation of MixNet with Pre-trained Weights.
Python
16
star
6

SharpPeleeNet

ImageNet pre-trained SharpPeleeNet can be used in real-time Semantic Segmentation/Objects Detection
Python
12
star
7

SocialCarsLeftTurnProhibition

Final code of the "Lane-based Signal Optimization with Left Turn Prohibition in Urban Road Networks"
Java
1
star