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>
78 lines
3.1 KiB
Python
78 lines
3.1 KiB
Python
# Copyright (c) OpenMMLab. All rights reserved.
|
|
from unittest import TestCase
|
|
|
|
import torch
|
|
from mmengine.structures import InstanceData
|
|
|
|
from mmseg.models.assigners import HungarianAssigner
|
|
|
|
|
|
class TestHungarianAssigner(TestCase):
|
|
|
|
def test_init(self):
|
|
with self.assertRaises(AssertionError):
|
|
HungarianAssigner([])
|
|
|
|
def test_hungarian_match_assigner(self):
|
|
assigner = HungarianAssigner([
|
|
dict(type='ClassificationCost', weight=2.0),
|
|
dict(type='CrossEntropyLossCost', weight=5.0, use_sigmoid=True),
|
|
dict(type='DiceCost', weight=5.0, pred_act=True, eps=1.0)
|
|
])
|
|
num_classes = 3
|
|
num_masks = 10
|
|
num_points = 20
|
|
gt_instances = InstanceData()
|
|
gt_instances.labels = torch.randint(0, num_classes, (num_classes, ))
|
|
gt_instances.masks = torch.randint(0, 2, (num_classes, num_points))
|
|
pred_instances = InstanceData()
|
|
pred_instances.scores = torch.rand((num_masks, num_classes))
|
|
pred_instances.masks = torch.rand((num_masks, num_points))
|
|
|
|
matched_quiery_inds, matched_label_inds = \
|
|
assigner.assign(pred_instances, gt_instances)
|
|
unique_quiery_inds = torch.unique(matched_quiery_inds)
|
|
unique_label_inds = torch.unique(matched_label_inds)
|
|
self.assertTrue(len(unique_quiery_inds) == len(matched_quiery_inds))
|
|
self.assertTrue(
|
|
torch.equal(unique_label_inds, torch.arange(0, num_classes)))
|
|
|
|
def test_cls_match_cost(self):
|
|
num_classes = 3
|
|
num_masks = 10
|
|
gt_instances = InstanceData()
|
|
gt_instances.labels = torch.randint(0, num_classes, (num_classes, ))
|
|
pred_instances = InstanceData()
|
|
pred_instances.scores = torch.rand((num_masks, num_classes))
|
|
|
|
# test ClassificationCost
|
|
assigner = HungarianAssigner(dict(type='ClassificationCost'))
|
|
matched_quiery_inds, matched_label_inds = \
|
|
assigner.assign(pred_instances, gt_instances)
|
|
unique_quiery_inds = torch.unique(matched_quiery_inds)
|
|
unique_label_inds = torch.unique(matched_label_inds)
|
|
self.assertTrue(len(unique_quiery_inds) == len(matched_quiery_inds))
|
|
self.assertTrue(
|
|
torch.equal(unique_label_inds, torch.arange(0, num_classes)))
|
|
|
|
def test_mask_match_cost(self):
|
|
num_classes = 3
|
|
num_masks = 10
|
|
num_points = 20
|
|
gt_instances = InstanceData()
|
|
gt_instances.masks = torch.randint(0, 2, (num_classes, num_points))
|
|
pred_instances = InstanceData()
|
|
pred_instances.masks = torch.rand((num_masks, num_points))
|
|
|
|
# test DiceCost
|
|
assigner = HungarianAssigner(
|
|
dict(type='DiceCost', pred_act=True, eps=1.0))
|
|
assign_result = assigner.assign(pred_instances, gt_instances)
|
|
self.assertTrue(len(assign_result[0]) == len(assign_result[1]))
|
|
|
|
# test CrossEntropyLossCost
|
|
assigner = HungarianAssigner(
|
|
dict(type='CrossEntropyLossCost', use_sigmoid=True))
|
|
assign_result = assigner.assign(pred_instances, gt_instances)
|
|
self.assertTrue(len(assign_result[0]) == len(assign_result[1]))
|