## Motivation Support SOTA real-time semantic segmentation method in [Paper with code](https://paperswithcode.com/task/real-time-semantic-segmentation) Paper: https://arxiv.org/pdf/2206.02066.pdf Official repo: https://github.com/XuJiacong/PIDNet ## Current results **Cityscapes** |Model|Ref mIoU|mIoU (ours)| |---|---|---| |PIDNet-S|78.8|78.74| |PIDNet-M|79.9|80.22| |PIDNet-L|80.9|80.89| ## TODO - [x] Support inference with official weights - [x] Support training on Cityscapes - [x] Update docstring - [x] Add unit test |
||
---|---|---|
.. | ||
__init__.py | ||
basic_block.py | ||
embed.py | ||
encoding.py | ||
inverted_residual.py | ||
make_divisible.py | ||
ppm.py | ||
res_layer.py | ||
se_layer.py | ||
self_attention_block.py | ||
shape_convert.py | ||
up_conv_block.py | ||
wrappers.py |