Awesome
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)<sup>[1,8]</sup> + DSASPPInPlaceABNBlock<sup>[2,3]</sup> + Parallel Bottleneck Channel-Spatial Attention Block (PBCSABlock)<sup>[6]</sup> + UnSharp Masking (USM) + Encoder-Decoder Arch.<sup>[3]</sup> + InplaceABN<sup>[4]</sup>.
-
ShuffleNetV2Plus: Modified ShuffleNetV2 (backbone)<sup>[1,8]</sup> + DSASPPInPlaceABNBlock<sup>[2,3]</sup> + Parallel Bottleneck Channel-Spatial Attention Block (PBCSABlock)<sup>[6]</sup>+ UnSharp Masking (USM) + Encoder-Decoder Arch.<sup>[3]</sup> + InplaceABN<sup>[4]</sup>.
-
MixSeg-MixBiFPN: Modified MixNet (backbone)<sup>[1,8]</sup> + MixBiFPNBlock<sup>[2,3]</sup> + Encoder-Decoder Arch.<sup>[3]</sup>
More about USM(Unsharp Mask)-Operator Block see Repo: SharpPeleeNet
Dependencies
- Python3.6
- PyTorch(1.0.1+)
- inplace_abn
- apex: Tools for easy mixed precision and distributed training in Pytorch
- tensorboard
- tensorboardX
- tqdm
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)