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].
More about USM(Unsharp Mask)-Operator Block see Repo: SharpPeleeNet
- Python3.6
- PyTorch(1.0.1+)
- inplace_abn
- apex: Tools for easy mixed precision and distributed training in Pytorch
- tensorboard
- tensorboardX
- tqdm
| 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) |
- S.S.: Single Scale (1024x2048)
