谢昕辰 dd47cef801
[Feature] Support PIDNet (#2609)
## 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
2023-03-15 14:55:30 +08:00

22 lines
909 B
Python

# Copyright (c) OpenMMLab. All rights reserved.
from .basic_block import BasicBlock, Bottleneck
from .embed import PatchEmbed
from .encoding import Encoding
from .inverted_residual import InvertedResidual, InvertedResidualV3
from .make_divisible import make_divisible
from .ppm import DAPPM, PAPPM
from .res_layer import ResLayer
from .se_layer import SELayer
from .self_attention_block import SelfAttentionBlock
from .shape_convert import (nchw2nlc2nchw, nchw_to_nlc, nlc2nchw2nlc,
nlc_to_nchw)
from .up_conv_block import UpConvBlock
from .wrappers import Upsample, resize
__all__ = [
'ResLayer', 'SelfAttentionBlock', 'make_divisible', 'InvertedResidual',
'UpConvBlock', 'InvertedResidualV3', 'SELayer', 'PatchEmbed',
'nchw_to_nlc', 'nlc_to_nchw', 'nchw2nlc2nchw', 'nlc2nchw2nlc', 'Encoding',
'Upsample', 'resize', 'DAPPM', 'PAPPM', 'BasicBlock', 'Bottleneck'
]