mirror of
https://github.com/open-mmlab/mmsegmentation.git
synced 2025-06-03 22:03:48 +08:00
608e319eb6
## Motivation Support SAN for Open-Vocabulary Semantic Segmentation Paper: [Side Adapter Network for Open-Vocabulary Semantic Segmentation](https://arxiv.org/abs/2302.12242) official Code: [SAN](https://github.com/MendelXu/SAN) ## Modification - Added the parameters of backbone vit for implementing the image encoder of CLIP. - Added text encoder code. - Added segmentor multimodel encoder-decoder code for open-vocabulary semantic segmentation. - Added SideAdapterNetwork decode head code. - Added config files for train and inference. - Added tools for converting pretrained models. - Added loss implementation for mask classification model, such as SAN, Maskformer and remove dependency on mmdetection. - Added test units for text encoder, multimodel encoder-decoder, san decode head and hungarian_assigner. ## Use cases ### Convert Models **pretrained SAN model** The official pretrained model can be downloaded from [san_clip_vit_b_16.pth](https://huggingface.co/Mendel192/san/blob/main/san_vit_b_16.pth) and [san_clip_vit_large_14.pth](https://huggingface.co/Mendel192/san/blob/main/san_vit_large_14.pth). Use tools/model_converters/san2mmseg.py to convert offcial model into mmseg style. `python tools/model_converters/san2mmseg.py <MODEL_PATH> <OUTPUT_PATH>` **pretrained CLIP model** Use the CLIP model provided by openai to train SAN. The CLIP model can be download from [ViT-B-16.pt](https://openaipublic.azureedge.net/clip/models/5806e77cd80f8b59890b7e101eabd078d9fb84e6937f9e85e4ecb61988df416f/ViT-B-16.pt) and [ViT-L-14-336px.pt](https://openaipublic.azureedge.net/clip/models/3035c92b350959924f9f00213499208652fc7ea050643e8b385c2dac08641f02/ViT-L-14-336px.pt). Use tools/model_converters/clip2mmseg.py to convert model into mmseg style. `python tools/model_converters/clip2mmseg.py <MODEL_PATH> <OUTPUT_PATH>` ### Inference test san_vit-base-16 model on coco-stuff164k dataset `python tools/test.py ./configs/san/san-vit-b16_coco-stuff164k-640x640.py <TRAINED_MODEL_PATH>` ### Train test san_vit-base-16 model on coco-stuff164k dataset `python tools/train.py ./configs/san/san-vit-b16_coco-stuff164k-640x640.py --cfg-options model.pretrained=<PRETRAINED_MODEL_PATH>` ## Comparision Results ### Train on COCO-Stuff164k | | | mIoU | mAcc | pAcc | | --------------- | ----- | ----- | ----- | ----- | | san-vit-base16 | official | 41.93 | 56.73 | 67.69 | | | mmseg | 41.93 | 56.84 | 67.84 | | san-vit-large14 | official | 45.57 | 59.52 | 69.76 | | | mmseg | 45.78 | 59.61 | 69.21 | ### Evaluate on Pascal Context | | | mIoU | mAcc | pAcc | | --------------- | ----- | ----- | ----- | ----- | | san-vit-base16 | official | 54.05 | 72.96 | 77.77 | | | mmseg | 54.04 | 73.74 | 77.71 | | san-vit-large14 | official | 57.53 | 77.56 | 78.89 | | | mmseg | 56.89 | 76.96 | 78.74 | ### Evaluate on Voc12Aug | | | mIoU | mAcc | pAcc | | --------------- | ----- | ----- | ----- | ----- | | san-vit-base16 | official | 93.86 | 96.61 | 97.11 | | | mmseg | 94.58 | 97.01 | 97.38 | | san-vit-large14 | official | 95.17 | 97.61 | 97.63 | | | mmseg | 95.58 | 97.75 | 97.79 | --------- Co-authored-by: CastleDream <35064479+CastleDream@users.noreply.github.com> Co-authored-by: yeedrag <46050186+yeedrag@users.noreply.github.com> Co-authored-by: Yang-ChangHui <71805205+Yang-Changhui@users.noreply.github.com> Co-authored-by: Xu CAO <49406546+SheffieldCao@users.noreply.github.com> Co-authored-by: xiexinch <xiexinch@outlook.com> Co-authored-by: 小飞猪 <106524776+ooooo-create@users.noreply.github.com>
71 lines
2.1 KiB
Python
71 lines
2.1 KiB
Python
# Copyright (c) OpenMMLab. All rights reserved.
|
|
# yapf: disable
|
|
from .class_names import (ade_classes, ade_palette, bdd100k_classes,
|
|
bdd100k_palette, cityscapes_classes,
|
|
cityscapes_palette, cocostuff_classes,
|
|
cocostuff_palette, dataset_aliases, get_classes,
|
|
get_palette, isaid_classes, isaid_palette,
|
|
loveda_classes, loveda_palette, potsdam_classes,
|
|
potsdam_palette, stare_classes, stare_palette,
|
|
synapse_classes, synapse_palette, vaihingen_classes,
|
|
vaihingen_palette, voc_classes, voc_palette)
|
|
# yapf: enable
|
|
from .collect_env import collect_env
|
|
from .get_templates import get_predefined_templates
|
|
from .io import datafrombytes
|
|
from .misc import add_prefix, stack_batch
|
|
from .set_env import register_all_modules
|
|
from .tokenizer import tokenize
|
|
from .typing_utils import (ConfigType, ForwardResults, MultiConfig,
|
|
OptConfigType, OptMultiConfig, OptSampleList,
|
|
SampleList, TensorDict, TensorList)
|
|
|
|
# isort: off
|
|
from .mask_classification import MatchMasks, seg_data_to_instance_data
|
|
|
|
__all__ = [
|
|
'collect_env',
|
|
'register_all_modules',
|
|
'stack_batch',
|
|
'add_prefix',
|
|
'ConfigType',
|
|
'OptConfigType',
|
|
'MultiConfig',
|
|
'OptMultiConfig',
|
|
'SampleList',
|
|
'OptSampleList',
|
|
'TensorDict',
|
|
'TensorList',
|
|
'ForwardResults',
|
|
'cityscapes_classes',
|
|
'ade_classes',
|
|
'voc_classes',
|
|
'cocostuff_classes',
|
|
'loveda_classes',
|
|
'potsdam_classes',
|
|
'vaihingen_classes',
|
|
'isaid_classes',
|
|
'stare_classes',
|
|
'cityscapes_palette',
|
|
'ade_palette',
|
|
'voc_palette',
|
|
'cocostuff_palette',
|
|
'loveda_palette',
|
|
'potsdam_palette',
|
|
'vaihingen_palette',
|
|
'isaid_palette',
|
|
'stare_palette',
|
|
'dataset_aliases',
|
|
'get_classes',
|
|
'get_palette',
|
|
'datafrombytes',
|
|
'synapse_palette',
|
|
'synapse_classes',
|
|
'get_predefined_templates',
|
|
'tokenize',
|
|
'seg_data_to_instance_data',
|
|
'MatchMasks',
|
|
'bdd100k_classes',
|
|
'bdd100k_palette',
|
|
]
|