Skip to content

Latest commit

 

History

History
54 lines (41 loc) · 2.91 KB

README.md

File metadata and controls

54 lines (41 loc) · 2.91 KB

LightNet++

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].

Dependencies

Datasets for Autonomous Driving

Results

Results on Cityscapes (Pixel-level/Semantic Segmentation)

Model mIoU (S.S* Mixed Precision)
MobileNetV2Plus X1.0 71.5314 (WIP)
ShuffleNetV2Plus X1.0 69.0885-72.5255 (WIP)
  • S.S.: Single Scale (1024x2048)

Feature Visualization