admin/Seg_Data_Server
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

first commit

Browse Source
This commit is contained in:
admin
2026-05-20 15:05:35 +08:00
commit ac09b26253
2048 changed files with 189478 additions and 0 deletions
Download Patch File Download Diff File Expand all files Collapse all files

50
Seg_All_In_One_MMSeg/configs/pidnet/README.md Normal file
View File

@@ -0,0 +1,50 @@
# PIDNet
> [PIDNet: A Real-time Semantic Segmentation Network Inspired from PID Controller](https://arxiv.org/pdf/2206.02066.pdf)
## Introduction
<!-- [ALGORITHM] -->
<a href="https://github.com/XuJiacong/PIDNet">Official Repo</a>
<a href="https://github.com/open-mmlab/mmsegmentation/blob/main/mmseg/models/backbones/pidnet.py">Code Snippet</a>
## Abstract
<!-- [ABSTRACT] -->
Two-branch network architecture has shown its efficiency and effectiveness for real-time semantic segmentation tasks. However, direct fusion of low-level details and high-level semantics will lead to a phenomenon that the detailed features are easily overwhelmed by surrounding contextual information, namely overshoot in this paper, which limits the improvement of the accuracy of existed two-branch models. In this paper, we bridge a connection between Convolutional Neural Network (CNN) and Proportional-IntegralDerivative (PID) controller and reveal that the two-branch network is nothing but a Proportional-Integral (PI) controller, which inherently suffers from the similar overshoot issue. To alleviate this issue, we propose a novel threebranch network architecture: PIDNet, which possesses three branches to parse the detailed, context and boundary information (derivative of semantics), respectively, and employs boundary attention to guide the fusion of detailed and context branches in final stage. The family of PIDNets achieve the best trade-off between inference speed and accuracy and their test accuracy surpasses all the existed models with similar inference speed on Cityscapes, CamVid and COCO-Stuff datasets. Especially, PIDNet-S achieves 78.6% mIOU with inference speed of 93.2 FPS on Cityscapes test set and 80.1% mIOU with speed of 153.7 FPS on CamVid test set.
<!-- [IMAGE] -->
<div align=center>
<img src="https://raw.githubusercontent.com/XuJiacong/PIDNet/main/figs/pidnet.jpg" width="800"/>
</div>
## Results and models
### Cityscapes
| Method | Backbone | Crop Size | Lr schd | Mem (GB) | Inf time (fps) | Device | mIoU | mIoU(ms+flip) | config | download |
| ------ | -------- | --------- | ------- | -------- | -------------- | ------ | ----- | ------------- | -------------------------------------------------------------------------------------------------------------------------- | -------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
| PIDNet | PIDNet-S | 1024x1024 | 120000 | 3.38 | 80.82 | A100 | 78.74 | 80.87 | [config](https://github.com/open-mmlab/mmsegmentation/blob/main/configs/pidnet/pidnet-s_2xb6-120k_1024x1024-cityscapes.py) | [model](https://download.openmmlab.com/mmsegmentation/v0.5/pidnet/pidnet-s_2xb6-120k_1024x1024-cityscapes/pidnet-s_2xb6-120k_1024x1024-cityscapes_20230302_191700-bb8e3bcc.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/pidnet/pidnet-s_2xb6-120k_1024x1024-cityscapes/pidnet-s_2xb6-120k_1024x1024-cityscapes_20230302_191700.json) |
| PIDNet | PIDNet-M | 1024x1024 | 120000 | 5.14 | 71.98 | A100 | 80.22 | 82.05 | [config](https://github.com/open-mmlab/mmsegmentation/blob/main/configs/pidnet/pidnet-m_2xb6-120k_1024x1024-cityscapes.py) | [model](https://download.openmmlab.com/mmsegmentation/v0.5/pidnet/pidnet-m_2xb6-120k_1024x1024-cityscapes/pidnet-m_2xb6-120k_1024x1024-cityscapes_20230301_143452-f9bcdbf3.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/pidnet/pidnet-m_2xb6-120k_1024x1024-cityscapes/pidnet-m_2xb6-120k_1024x1024-cityscapes_20230301_143452.json) |
| PIDNet | PIDNet-L | 1024x1024 | 120000 | 5.83 | 60.06 | A100 | 80.89 | 82.37 | [config](https://github.com/open-mmlab/mmsegmentation/blob/main/configs/pidnet/pidnet-l_2xb6-120k_1024x1024-cityscapes.py) | [model](https://download.openmmlab.com/mmsegmentation/v0.5/pidnet/pidnet-l_2xb6-120k_1024x1024-cityscapes/pidnet-l_2xb6-120k_1024x1024-cityscapes_20230303_114514-0783ca6b.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/pidnet/pidnet-l_2xb6-120k_1024x1024-cityscapes/pidnet-l_2xb6-120k_1024x1024-cityscapes_20230303_114514.json) |
## Notes
The pretrained weights in config files are converted from [the official repo](https://github.com/XuJiacong/PIDNet#models).
## Citation
```bibtex
@misc{xu2022pidnet,
title={PIDNet: A Real-time Semantic Segmentation Network Inspired from PID Controller},
author={Jiacong Xu and Zixiang Xiong and Shankar P. Bhattacharyya},
year={2022},
eprint={2206.02066},
archivePrefix={arXiv},
primaryClass={cs.CV}
}
```

85
Seg_All_In_One_MMSeg/configs/pidnet/metafile.yaml Normal file
View File

@@ -0,0 +1,85 @@
Collections:
- Name: PIDNet
License: Apache License 2.0
Metadata:
Training Data:
- Cityscapes
Paper:
Title: 'PIDNet: A Real-time Semantic Segmentation Network Inspired from PID Controller'
URL: https://arxiv.org/pdf/2206.02066.pdf
README: configs/pidnet/README.md
Frameworks:
- PyTorch
Models:
- Name: pidnet-s_2xb6-120k_1024x1024-cityscapes
In Collection: PIDNet
Results:
Task: Semantic Segmentation
Dataset: Cityscapes
Metrics:
mIoU: 78.74
mIoU(ms+flip): 80.87
Config: configs/pidnet/pidnet-s_2xb6-120k_1024x1024-cityscapes.py
Metadata:
Training Data: Cityscapes
Batch Size: 12
Architecture:
- PIDNet-S
- PIDNet
Training Resources: 2x A100 GPUS
Memory (GB): 3.38
Weights: https://download.openmmlab.com/mmsegmentation/v0.5/pidnet/pidnet-s_2xb6-120k_1024x1024-cityscapes/pidnet-s_2xb6-120k_1024x1024-cityscapes_20230302_191700-bb8e3bcc.pth
Training log: https://download.openmmlab.com/mmsegmentation/v0.5/pidnet/pidnet-s_2xb6-120k_1024x1024-cityscapes/pidnet-s_2xb6-120k_1024x1024-cityscapes_20230302_191700.json
Paper:
Title: 'PIDNet: A Real-time Semantic Segmentation Network Inspired from PID Controller'
URL: https://arxiv.org/pdf/2206.02066.pdf
Code: https://github.com/open-mmlab/mmsegmentation/blob/main/mmseg/models/backbones/pidnet.py
Framework: PyTorch
- Name: pidnet-m_2xb6-120k_1024x1024-cityscapes
In Collection: PIDNet
Results:
Task: Semantic Segmentation
Dataset: Cityscapes
Metrics:
mIoU: 80.22
mIoU(ms+flip): 82.05
Config: configs/pidnet/pidnet-m_2xb6-120k_1024x1024-cityscapes.py
Metadata:
Training Data: Cityscapes
Batch Size: 12
Architecture:
- PIDNet-M
- PIDNet
Training Resources: 2x A100 GPUS
Memory (GB): 5.14
Weights: https://download.openmmlab.com/mmsegmentation/v0.5/pidnet/pidnet-m_2xb6-120k_1024x1024-cityscapes/pidnet-m_2xb6-120k_1024x1024-cityscapes_20230301_143452-f9bcdbf3.pth
Training log: https://download.openmmlab.com/mmsegmentation/v0.5/pidnet/pidnet-m_2xb6-120k_1024x1024-cityscapes/pidnet-m_2xb6-120k_1024x1024-cityscapes_20230301_143452.json
Paper:
Title: 'PIDNet: A Real-time Semantic Segmentation Network Inspired from PID Controller'
URL: https://arxiv.org/pdf/2206.02066.pdf
Code: https://github.com/open-mmlab/mmsegmentation/blob/main/mmseg/models/backbones/pidnet.py
Framework: PyTorch
- Name: pidnet-l_2xb6-120k_1024x1024-cityscapes
In Collection: PIDNet
Results:
Task: Semantic Segmentation
Dataset: Cityscapes
Metrics:
mIoU: 80.89
mIoU(ms+flip): 82.37
Config: configs/pidnet/pidnet-l_2xb6-120k_1024x1024-cityscapes.py
Metadata:
Training Data: Cityscapes
Batch Size: 12
Architecture:
- PIDNet-L
- PIDNet
Training Resources: 2x A100 GPUS
Memory (GB): 5.83
Weights: https://download.openmmlab.com/mmsegmentation/v0.5/pidnet/pidnet-l_2xb6-120k_1024x1024-cityscapes/pidnet-l_2xb6-120k_1024x1024-cityscapes_20230303_114514-0783ca6b.pth
Training log: https://download.openmmlab.com/mmsegmentation/v0.5/pidnet/pidnet-l_2xb6-120k_1024x1024-cityscapes/pidnet-l_2xb6-120k_1024x1024-cityscapes_20230303_114514.json
Paper:
Title: 'PIDNet: A Real-time Semantic Segmentation Network Inspired from PID Controller'
URL: https://arxiv.org/pdf/2206.02066.pdf
Code: https://github.com/open-mmlab/mmsegmentation/blob/main/mmseg/models/backbones/pidnet.py
Framework: PyTorch

162
Seg_All_In_One_MMSeg/configs/pidnet/my_pidnet_large_g1-300e_val1_check10_publicdataset_autolaparo-512x512.py Normal file
View File

@@ -0,0 +1,162 @@
_base_ = [
'../_base_/models/pidnet.py',
'../_base_/datasets/publicdataset_autolaparo.py',
'../_base_/default_runtime.py',
'../_base_/schedules/schedule_300e_val1_check10.py',
]
norm_cfg = dict(
type='BN',
)
crop_size = (512, 512)
data_preprocessor = dict(
size=(512, 512),
mean=[
123.62464353460942,
85.34836259209033,
82.31539425671558,
],
std=[
47.172211618459315,
47.08256715323592,
48.135121265163605,
],
bgr_to_rgb=False,
)
train_pipeline = [
dict(
type='LoadImageFromFile',
),
dict(
type='LoadAnnotations',
),
dict(
type='RandomResize',
scale=(1920, 1080),
ratio_range=(0.5, 2.0),
),
dict(
type='RandomCrop',
crop_size=(256, 256),
cat_max_ratio=0.75,
),
dict(
type='RandomFlip',
prob=0.5,
),
dict(
type='PhotoMetricDistortion',
),
dict(
type='GenerateEdge',
edge_width=4,
),
dict(
type='PackSegInputs',
),
]
train_dataloader = dict(
dataset=dict(
pipeline=[
dict(
type='LoadImageFromFile',
),
dict(
type='LoadAnnotations',
),
dict(
type='RandomResize',
scale=(1920, 1080),
ratio_range=(0.5, 2.0),
),
dict(
type='RandomCrop',
crop_size=(256, 256),
cat_max_ratio=0.75,
),
dict(
type='RandomFlip',
prob=0.5,
),
dict(
type='PhotoMetricDistortion',
),
dict(
type='GenerateEdge',
edge_width=4,
),
dict(
type='PackSegInputs',
),
],
),
)
model = dict(
data_preprocessor=dict(
size=(512, 512),
mean=[
123.62464353460942,
85.34836259209033,
82.31539425671558,
],
std=[
47.172211618459315,
47.08256715323592,
48.135121265163605,
],
bgr_to_rgb=False,
),
backbone=dict(
channels=64,
ppm_channels=112,
num_stem_blocks=3,
num_branch_blocks=4,
init_cfg=dict(
type='Pretrained',
checkpoint='./My_Local_Model/open_mmlab/pidnet-l.pth',
),
),
decode_head=dict(
num_classes=10,
in_channels=256,
channels=256,
),
)
optim_wrapper = dict(
type='OptimWrapper',
_delete_=True,
optimizer=dict(
type='AdamW',
lr=0.0001,
weight_decay=0.0005,
),
clip_grad=dict(
max_norm=1,
norm_type=2,
),
)
param_scheduler = [
dict(
type='LinearLR',
start_factor=1e-06,
by_epoch=True,
begin=0,
end=10,
),
dict(
type='PolyLR',
power=0.9,
begin=10,
end=300,
eta_min=1e-05,
by_epoch=True,
),
]

162
Seg_All_In_One_MMSeg/configs/pidnet/my_pidnet_large_g1-300e_val1_check10_publicdataset_cholecseg8k-512x512.py Normal file
View File

@@ -0,0 +1,162 @@
_base_ = [
'../_base_/models/pidnet.py',
'../_base_/datasets/publicdataset_cholecseg8k.py',
'../_base_/default_runtime.py',
'../_base_/schedules/schedule_300e_val1_check10.py',
]
norm_cfg = dict(
type='BN',
)
crop_size = (512, 512)
data_preprocessor = dict(
size=(512, 512),
mean=[
85.65740418979115,
53.99282220050495,
46.074045888534535,
],
std=[
72.24589167201978,
56.76979155397199,
49.056637115061775,
],
bgr_to_rgb=False,
)
train_pipeline = [
dict(
type='LoadImageFromFile',
),
dict(
type='LoadAnnotations',
),
dict(
type='RandomResize',
scale=(1920, 1080),
ratio_range=(0.5, 2.0),
),
dict(
type='RandomCrop',
crop_size=(256, 256),
cat_max_ratio=0.75,
),
dict(
type='RandomFlip',
prob=0.5,
),
dict(
type='PhotoMetricDistortion',
),
dict(
type='GenerateEdge',
edge_width=4,
),
dict(
type='PackSegInputs',
),
]
train_dataloader = dict(
dataset=dict(
pipeline=[
dict(
type='LoadImageFromFile',
),
dict(
type='LoadAnnotations',
),
dict(
type='RandomResize',
scale=(1920, 1080),
ratio_range=(0.5, 2.0),
),
dict(
type='RandomCrop',
crop_size=(256, 256),
cat_max_ratio=0.75,
),
dict(
type='RandomFlip',
prob=0.5,
),
dict(
type='PhotoMetricDistortion',
),
dict(
type='GenerateEdge',
edge_width=4,
),
dict(
type='PackSegInputs',
),
],
),
)
model = dict(
data_preprocessor=dict(
size=(512, 512),
mean=[
85.65740418979115,
53.99282220050495,
46.074045888534535,
],
std=[
72.24589167201978,
56.76979155397199,
49.056637115061775,
],
bgr_to_rgb=False,
),
backbone=dict(
channels=64,
ppm_channels=112,
num_stem_blocks=3,
num_branch_blocks=4,
init_cfg=dict(
type='Pretrained',
checkpoint='./My_Local_Model/open_mmlab/pidnet-l.pth',
),
),
decode_head=dict(
num_classes=13,
in_channels=256,
channels=256,
),
)
optim_wrapper = dict(
type='OptimWrapper',
_delete_=True,
optimizer=dict(
type='AdamW',
lr=0.0001,
weight_decay=0.0005,
),
clip_grad=dict(
max_norm=1,
norm_type=2,
),
)
param_scheduler = [
dict(
type='LinearLR',
start_factor=1e-06,
by_epoch=True,
begin=0,
end=10,
),
dict(
type='PolyLR',
power=0.9,
begin=10,
end=300,
eta_min=1e-05,
by_epoch=True,
),
]

162
Seg_All_In_One_MMSeg/configs/pidnet/my_pidnet_large_g1-300e_val1_check10_publicdataset_dresden-512x512.py Normal file
View File

@@ -0,0 +1,162 @@
_base_ = [
'../_base_/models/pidnet.py',
'../_base_/datasets/publicdataset_dresden.py',
'../_base_/default_runtime.py',
'../_base_/schedules/schedule_300e_val1_check10.py',
]
norm_cfg = dict(
type='BN',
)
crop_size = (512, 512)
data_preprocessor = dict(
size=(512, 512),
mean=[
103.172638338208,
61.44762740851152,
51.407770213021976,
],
std=[
75.77031253622098,
54.63616729031377,
49.45572239497569,
],
bgr_to_rgb=False,
)
train_pipeline = [
dict(
type='LoadImageFromFile',
),
dict(
type='LoadAnnotations',
),
dict(
type='RandomResize',
scale=(512, 512),
ratio_range=(0.5, 2.0),
),
dict(
type='RandomCrop',
crop_size=(256, 256),
cat_max_ratio=0.75,
),
dict(
type='RandomFlip',
prob=0.5,
),
dict(
type='PhotoMetricDistortion',
),
dict(
type='GenerateEdge',
edge_width=4,
),
dict(
type='PackSegInputs',
),
]
train_dataloader = dict(
dataset=dict(
pipeline=[
dict(
type='LoadImageFromFile',
),
dict(
type='LoadAnnotations',
),
dict(
type='RandomResize',
scale=(512, 512),
ratio_range=(0.5, 2.0),
),
dict(
type='RandomCrop',
crop_size=(256, 256),
cat_max_ratio=0.75,
),
dict(
type='RandomFlip',
prob=0.5,
),
dict(
type='PhotoMetricDistortion',
),
dict(
type='GenerateEdge',
edge_width=4,
),
dict(
type='PackSegInputs',
),
],
),
)
model = dict(
data_preprocessor=dict(
size=(512, 512),
mean=[
103.172638338208,
61.44762740851152,
51.407770213021976,
],
std=[
75.77031253622098,
54.63616729031377,
49.45572239497569,
],
bgr_to_rgb=False,
),
backbone=dict(
channels=64,
ppm_channels=112,
num_stem_blocks=3,
num_branch_blocks=4,
init_cfg=dict(
type='Pretrained',
checkpoint='./My_Local_Model/open_mmlab/pidnet-l.pth',
),
),
decode_head=dict(
num_classes=11,
in_channels=256,
channels=256,
),
)
optim_wrapper = dict(
type='OptimWrapper',
_delete_=True,
optimizer=dict(
type='AdamW',
lr=0.0001,
weight_decay=0.0005,
),
clip_grad=dict(
max_norm=1,
norm_type=2,
),
)
param_scheduler = [
dict(
type='LinearLR',
start_factor=1e-06,
by_epoch=True,
begin=0,
end=10,
),
dict(
type='PolyLR',
power=0.9,
begin=10,
end=300,
eta_min=1e-05,
by_epoch=True,
),
]

162
Seg_All_In_One_MMSeg/configs/pidnet/my_pidnet_large_g1-300e_val1_check10_publicdataset_endovis_2017-512x512.py Normal file
View File

@@ -0,0 +1,162 @@
_base_ = [
'../_base_/models/pidnet.py',
'../_base_/datasets/publicdataset_endovis_2017.py',
'../_base_/default_runtime.py',
'../_base_/schedules/schedule_300e_val1_check10.py',
]
norm_cfg = dict(
type='BN',
)
crop_size = (512, 512)
data_preprocessor = dict(
size=(512, 512),
mean=[
122.21429912990676,
77.0821859677977,
87.03836664626716,
],
std=[
50.53335800365262,
42.895340354037465,
47.739426483390446,
],
bgr_to_rgb=False,
)
train_pipeline = [
dict(
type='LoadImageFromFile',
),
dict(
type='LoadAnnotations',
),
dict(
type='RandomResize',
scale=(512, 512),
ratio_range=(0.5, 2.0),
),
dict(
type='RandomCrop',
crop_size=(256, 256),
cat_max_ratio=0.75,
),
dict(
type='RandomFlip',
prob=0.5,
),
dict(
type='PhotoMetricDistortion',
),
dict(
type='GenerateEdge',
edge_width=4,
),
dict(
type='PackSegInputs',
),
]
train_dataloader = dict(
dataset=dict(
pipeline=[
dict(
type='LoadImageFromFile',
),
dict(
type='LoadAnnotations',
),
dict(
type='RandomResize',
scale=(512, 512),
ratio_range=(0.5, 2.0),
),
dict(
type='RandomCrop',
crop_size=(256, 256),
cat_max_ratio=0.75,
),
dict(
type='RandomFlip',
prob=0.5,
),
dict(
type='PhotoMetricDistortion',
),
dict(
type='GenerateEdge',
edge_width=4,
),
dict(
type='PackSegInputs',
),
],
),
)
model = dict(
data_preprocessor=dict(
size=(512, 512),
mean=[
122.21429912990676,
77.0821859677977,
87.03836664626716,
],
std=[
50.53335800365262,
42.895340354037465,
47.739426483390446,
],
bgr_to_rgb=False,
),
backbone=dict(
channels=64,
ppm_channels=112,
num_stem_blocks=3,
num_branch_blocks=4,
init_cfg=dict(
type='Pretrained',
checkpoint='./My_Local_Model/open_mmlab/pidnet-l.pth',
),
),
decode_head=dict(
num_classes=8,
in_channels=256,
channels=256,
),
)
optim_wrapper = dict(
type='OptimWrapper',
_delete_=True,
optimizer=dict(
type='AdamW',
lr=0.0001,
weight_decay=0.0005,
),
clip_grad=dict(
max_norm=1,
norm_type=2,
),
)
param_scheduler = [
dict(
type='LinearLR',
start_factor=1e-06,
by_epoch=True,
begin=0,
end=10,
),
dict(
type='PolyLR',
power=0.9,
begin=10,
end=300,
eta_min=1e-05,
by_epoch=True,
),
]

162
Seg_All_In_One_MMSeg/configs/pidnet/my_pidnet_large_g1-300e_val1_check10_publicdataset_endovis_2018-512x512.py Normal file
View File

@@ -0,0 +1,162 @@
_base_ = [
'../_base_/models/pidnet.py',
'../_base_/datasets/publicdataset_endovis_2018.py',
'../_base_/default_runtime.py',
'../_base_/schedules/schedule_300e_val1_check10.py',
]
norm_cfg = dict(
type='BN',
)
crop_size = (512, 512)
data_preprocessor = dict(
size=(512, 512),
mean=[
122.21429912990676,
77.0821859677977,
87.03836664626716,
],
std=[
50.53335800365262,
42.895340354037465,
47.739426483390446,
],
bgr_to_rgb=False,
)
train_pipeline = [
dict(
type='LoadImageFromFile',
),
dict(
type='LoadAnnotations',
),
dict(
type='RandomResize',
scale=(512, 512),
ratio_range=(0.5, 2.0),
),
dict(
type='RandomCrop',
crop_size=(256, 256),
cat_max_ratio=0.75,
),
dict(
type='RandomFlip',
prob=0.5,
),
dict(
type='PhotoMetricDistortion',
),
dict(
type='GenerateEdge',
edge_width=4,
),
dict(
type='PackSegInputs',
),
]
train_dataloader = dict(
dataset=dict(
pipeline=[
dict(
type='LoadImageFromFile',
),
dict(
type='LoadAnnotations',
),
dict(
type='RandomResize',
scale=(512, 512),
ratio_range=(0.5, 2.0),
),
dict(
type='RandomCrop',
crop_size=(256, 256),
cat_max_ratio=0.75,
),
dict(
type='RandomFlip',
prob=0.5,
),
dict(
type='PhotoMetricDistortion',
),
dict(
type='GenerateEdge',
edge_width=4,
),
dict(
type='PackSegInputs',
),
],
),
)
model = dict(
data_preprocessor=dict(
size=(512, 512),
mean=[
122.21429912990676,
77.0821859677977,
87.03836664626716,
],
std=[
50.53335800365262,
42.895340354037465,
47.739426483390446,
],
bgr_to_rgb=False,
),
backbone=dict(
channels=64,
ppm_channels=112,
num_stem_blocks=3,
num_branch_blocks=4,
init_cfg=dict(
type='Pretrained',
checkpoint='./My_Local_Model/open_mmlab/pidnet-l.pth',
),
),
decode_head=dict(
num_classes=8,
in_channels=256,
channels=256,
),
)
optim_wrapper = dict(
type='OptimWrapper',
_delete_=True,
optimizer=dict(
type='AdamW',
lr=0.0001,
weight_decay=0.0005,
),
clip_grad=dict(
max_norm=1,
norm_type=2,
),
)
param_scheduler = [
dict(
type='LinearLR',
start_factor=1e-06,
by_epoch=True,
begin=0,
end=10,
),
dict(
type='PolyLR',
power=0.9,
begin=10,
end=300,
eta_min=1e-05,
by_epoch=True,
),
]

162
Seg_All_In_One_MMSeg/configs/pidnet/my_pidnet_middle_g1-300e_val1_check10_publicdataset_autolaparo-512x512.py Normal file
View File

@@ -0,0 +1,162 @@
_base_ = [
'../_base_/models/pidnet.py',
'../_base_/datasets/publicdataset_autolaparo.py',
'../_base_/default_runtime.py',
'../_base_/schedules/schedule_300e_val1_check10.py',
]
norm_cfg = dict(
type='BN',
)
crop_size = (512, 512)
data_preprocessor = dict(
size=(512, 512),
mean=[
123.62464353460942,
85.34836259209033,
82.31539425671558,
],
std=[
47.172211618459315,
47.08256715323592,
48.135121265163605,
],
bgr_to_rgb=False,
)
train_pipeline = [
dict(
type='LoadImageFromFile',
),
dict(
type='LoadAnnotations',
),
dict(
type='RandomResize',
scale=(1920, 1080),
ratio_range=(0.5, 2.0),
),
dict(
type='RandomCrop',
crop_size=(256, 256),
cat_max_ratio=0.75,
),
dict(
type='RandomFlip',
prob=0.5,
),
dict(
type='PhotoMetricDistortion',
),
dict(
type='GenerateEdge',
edge_width=4,
),
dict(
type='PackSegInputs',
),
]
train_dataloader = dict(
dataset=dict(
pipeline=[
dict(
type='LoadImageFromFile',
),
dict(
type='LoadAnnotations',
),
dict(
type='RandomResize',
scale=(1920, 1080),
ratio_range=(0.5, 2.0),
),
dict(
type='RandomCrop',
crop_size=(256, 256),
cat_max_ratio=0.75,
),
dict(
type='RandomFlip',
prob=0.5,
),
dict(
type='PhotoMetricDistortion',
),
dict(
type='GenerateEdge',
edge_width=4,
),
dict(
type='PackSegInputs',
),
],
),
)
model = dict(
data_preprocessor=dict(
size=(512, 512),
mean=[
123.62464353460942,
85.34836259209033,
82.31539425671558,
],
std=[
47.172211618459315,
47.08256715323592,
48.135121265163605,
],
bgr_to_rgb=False,
),
backbone=dict(
channels=64,
ppm_channels=96,
num_stem_blocks=2,
num_branch_blocks=3,
init_cfg=dict(
type='Pretrained',
checkpoint='./My_Local_Model/open_mmlab/pidnet-m.pth',
),
),
decode_head=dict(
num_classes=10,
in_channels=256,
channels=128,
),
)
optim_wrapper = dict(
type='OptimWrapper',
_delete_=True,
optimizer=dict(
type='AdamW',
lr=0.0001,
weight_decay=0.0005,
),
clip_grad=dict(
max_norm=1,
norm_type=2,
),
)
param_scheduler = [
dict(
type='LinearLR',
start_factor=1e-06,
by_epoch=True,
begin=0,
end=10,
),
dict(
type='PolyLR',
power=0.9,
begin=10,
end=300,
eta_min=1e-05,
by_epoch=True,
),
]

162
Seg_All_In_One_MMSeg/configs/pidnet/my_pidnet_middle_g1-300e_val1_check10_publicdataset_cholecseg8k-512x512.py Normal file
View File

@@ -0,0 +1,162 @@
_base_ = [
'../_base_/models/pidnet.py',
'../_base_/datasets/publicdataset_cholecseg8k.py',
'../_base_/default_runtime.py',
'../_base_/schedules/schedule_300e_val1_check10.py',
]
norm_cfg = dict(
type='BN',
)
crop_size = (512, 512)
data_preprocessor = dict(
size=(512, 512),
mean=[
85.65740418979115,
53.99282220050495,
46.074045888534535,
],
std=[
72.24589167201978,
56.76979155397199,
49.056637115061775,
],
bgr_to_rgb=False,
)
train_pipeline = [
dict(
type='LoadImageFromFile',
),
dict(
type='LoadAnnotations',
),
dict(
type='RandomResize',
scale=(1920, 1080),
ratio_range=(0.5, 2.0),
),
dict(
type='RandomCrop',
crop_size=(256, 256),
cat_max_ratio=0.75,
),
dict(
type='RandomFlip',
prob=0.5,
),
dict(
type='PhotoMetricDistortion',
),
dict(
type='GenerateEdge',
edge_width=4,
),
dict(
type='PackSegInputs',
),
]
train_dataloader = dict(
dataset=dict(
pipeline=[
dict(
type='LoadImageFromFile',
),
dict(
type='LoadAnnotations',
),
dict(
type='RandomResize',
scale=(1920, 1080),
ratio_range=(0.5, 2.0),
),
dict(
type='RandomCrop',
crop_size=(256, 256),
cat_max_ratio=0.75,
),
dict(
type='RandomFlip',
prob=0.5,
),
dict(
type='PhotoMetricDistortion',
),
dict(
type='GenerateEdge',
edge_width=4,
),
dict(
type='PackSegInputs',
),
],
),
)
model = dict(
data_preprocessor=dict(
size=(512, 512),
mean=[
85.65740418979115,
53.99282220050495,
46.074045888534535,
],
std=[
72.24589167201978,
56.76979155397199,
49.056637115061775,
],
bgr_to_rgb=False,
),
backbone=dict(
channels=64,
ppm_channels=96,
num_stem_blocks=2,
num_branch_blocks=3,
init_cfg=dict(
type='Pretrained',
checkpoint='./My_Local_Model/open_mmlab/pidnet-m.pth',
),
),
decode_head=dict(
num_classes=13,
in_channels=256,
channels=128,
),
)
optim_wrapper = dict(
type='OptimWrapper',
_delete_=True,
optimizer=dict(
type='AdamW',
lr=0.0001,
weight_decay=0.0005,
),
clip_grad=dict(
max_norm=1,
norm_type=2,
),
)
param_scheduler = [
dict(
type='LinearLR',
start_factor=1e-06,
by_epoch=True,
begin=0,
end=10,
),
dict(
type='PolyLR',
power=0.9,
begin=10,
end=300,
eta_min=1e-05,
by_epoch=True,
),
]

162
Seg_All_In_One_MMSeg/configs/pidnet/my_pidnet_middle_g1-300e_val1_check10_publicdataset_dresden-512x512.py Normal file
View File

@@ -0,0 +1,162 @@
_base_ = [
'../_base_/models/pidnet.py',
'../_base_/datasets/publicdataset_dresden.py',
'../_base_/default_runtime.py',
'../_base_/schedules/schedule_300e_val1_check10.py',
]
norm_cfg = dict(
type='BN',
)
crop_size = (512, 512)
data_preprocessor = dict(
size=(512, 512),
mean=[
103.172638338208,
61.44762740851152,
51.407770213021976,
],
std=[
75.77031253622098,
54.63616729031377,
49.45572239497569,
],
bgr_to_rgb=False,
)
train_pipeline = [
dict(
type='LoadImageFromFile',
),
dict(
type='LoadAnnotations',
),
dict(
type='RandomResize',
scale=(512, 512),
ratio_range=(0.5, 2.0),
),
dict(
type='RandomCrop',
crop_size=(256, 256),
cat_max_ratio=0.75,
),
dict(
type='RandomFlip',
prob=0.5,
),
dict(
type='PhotoMetricDistortion',
),
dict(
type='GenerateEdge',
edge_width=4,
),
dict(
type='PackSegInputs',
),
]
train_dataloader = dict(
dataset=dict(
pipeline=[
dict(
type='LoadImageFromFile',
),
dict(
type='LoadAnnotations',
),
dict(
type='RandomResize',
scale=(512, 512),
ratio_range=(0.5, 2.0),
),
dict(
type='RandomCrop',
crop_size=(256, 256),
cat_max_ratio=0.75,
),
dict(
type='RandomFlip',
prob=0.5,
),
dict(
type='PhotoMetricDistortion',
),
dict(
type='GenerateEdge',
edge_width=4,
),
dict(
type='PackSegInputs',
),
],
),
)
model = dict(
data_preprocessor=dict(
size=(512, 512),
mean=[
103.172638338208,
61.44762740851152,
51.407770213021976,
],
std=[
75.77031253622098,
54.63616729031377,
49.45572239497569,
],
bgr_to_rgb=False,
),
backbone=dict(
channels=64,
ppm_channels=96,
num_stem_blocks=2,
num_branch_blocks=3,
init_cfg=dict(
type='Pretrained',
checkpoint='./My_Local_Model/open_mmlab/pidnet-m.pth',
),
),
decode_head=dict(
num_classes=11,
in_channels=256,
channels=128,
),
)
optim_wrapper = dict(
type='OptimWrapper',
_delete_=True,
optimizer=dict(
type='AdamW',
lr=0.0001,
weight_decay=0.0005,
),
clip_grad=dict(
max_norm=1,
norm_type=2,
),
)
param_scheduler = [
dict(
type='LinearLR',
start_factor=1e-06,
by_epoch=True,
begin=0,
end=10,
),
dict(
type='PolyLR',
power=0.9,
begin=10,
end=300,
eta_min=1e-05,
by_epoch=True,
),
]

162
Seg_All_In_One_MMSeg/configs/pidnet/my_pidnet_middle_g1-300e_val1_check10_publicdataset_endovis_2017-512x512.py Normal file
View File

@@ -0,0 +1,162 @@
_base_ = [
'../_base_/models/pidnet.py',
'../_base_/datasets/publicdataset_endovis_2017.py',
'../_base_/default_runtime.py',
'../_base_/schedules/schedule_300e_val1_check10.py',
]
norm_cfg = dict(
type='BN',
)
crop_size = (512, 512)
data_preprocessor = dict(
size=(512, 512),
mean=[
122.21429912990676,
77.0821859677977,
87.03836664626716,
],
std=[
50.53335800365262,
42.895340354037465,
47.739426483390446,
],
bgr_to_rgb=False,
)
train_pipeline = [
dict(
type='LoadImageFromFile',
),
dict(
type='LoadAnnotations',
),
dict(
type='RandomResize',
scale=(512, 512),
ratio_range=(0.5, 2.0),
),
dict(
type='RandomCrop',
crop_size=(256, 256),
cat_max_ratio=0.75,
),
dict(
type='RandomFlip',
prob=0.5,
),
dict(
type='PhotoMetricDistortion',
),
dict(
type='GenerateEdge',
edge_width=4,
),
dict(
type='PackSegInputs',
),
]
train_dataloader = dict(
dataset=dict(
pipeline=[
dict(
type='LoadImageFromFile',
),
dict(
type='LoadAnnotations',
),
dict(
type='RandomResize',
scale=(512, 512),
ratio_range=(0.5, 2.0),
),
dict(
type='RandomCrop',
crop_size=(256, 256),
cat_max_ratio=0.75,
),
dict(
type='RandomFlip',
prob=0.5,
),
dict(
type='PhotoMetricDistortion',
),
dict(
type='GenerateEdge',
edge_width=4,
),
dict(
type='PackSegInputs',
),
],
),
)
model = dict(
data_preprocessor=dict(
size=(512, 512),
mean=[
122.21429912990676,
77.0821859677977,
87.03836664626716,
],
std=[
50.53335800365262,
42.895340354037465,
47.739426483390446,
],
bgr_to_rgb=False,
),
backbone=dict(
channels=64,
ppm_channels=96,
num_stem_blocks=2,
num_branch_blocks=3,
init_cfg=dict(
type='Pretrained',
checkpoint='./My_Local_Model/open_mmlab/pidnet-m.pth',
),
),
decode_head=dict(
num_classes=8,
in_channels=256,
channels=128,
),
)
optim_wrapper = dict(
type='OptimWrapper',
_delete_=True,
optimizer=dict(
type='AdamW',
lr=0.0001,
weight_decay=0.0005,
),
clip_grad=dict(
max_norm=1,
norm_type=2,
),
)
param_scheduler = [
dict(
type='LinearLR',
start_factor=1e-06,
by_epoch=True,
begin=0,
end=10,
),
dict(
type='PolyLR',
power=0.9,
begin=10,
end=300,
eta_min=1e-05,
by_epoch=True,
),
]

162
Seg_All_In_One_MMSeg/configs/pidnet/my_pidnet_middle_g1-300e_val1_check10_publicdataset_endovis_2018-512x512.py Normal file
View File

@@ -0,0 +1,162 @@
_base_ = [
'../_base_/models/pidnet.py',
'../_base_/datasets/publicdataset_endovis_2018.py',
'../_base_/default_runtime.py',
'../_base_/schedules/schedule_300e_val1_check10.py',
]
norm_cfg = dict(
type='BN',
)
crop_size = (512, 512)
data_preprocessor = dict(
size=(512, 512),
mean=[
122.21429912990676,
77.0821859677977,
87.03836664626716,
],
std=[
50.53335800365262,
42.895340354037465,
47.739426483390446,
],
bgr_to_rgb=False,
)
train_pipeline = [
dict(
type='LoadImageFromFile',
),
dict(
type='LoadAnnotations',
),
dict(
type='RandomResize',
scale=(512, 512),
ratio_range=(0.5, 2.0),
),
dict(
type='RandomCrop',
crop_size=(256, 256),
cat_max_ratio=0.75,
),
dict(
type='RandomFlip',
prob=0.5,
),
dict(
type='PhotoMetricDistortion',
),
dict(
type='GenerateEdge',
edge_width=4,
),
dict(
type='PackSegInputs',
),
]
train_dataloader = dict(
dataset=dict(
pipeline=[
dict(
type='LoadImageFromFile',
),
dict(
type='LoadAnnotations',
),
dict(
type='RandomResize',
scale=(512, 512),
ratio_range=(0.5, 2.0),
),
dict(
type='RandomCrop',
crop_size=(256, 256),
cat_max_ratio=0.75,
),
dict(
type='RandomFlip',
prob=0.5,
),
dict(
type='PhotoMetricDistortion',
),
dict(
type='GenerateEdge',
edge_width=4,
),
dict(
type='PackSegInputs',
),
],
),
)
model = dict(
data_preprocessor=dict(
size=(512, 512),
mean=[
122.21429912990676,
77.0821859677977,
87.03836664626716,
],
std=[
50.53335800365262,
42.895340354037465,
47.739426483390446,
],
bgr_to_rgb=False,
),
backbone=dict(
channels=64,
ppm_channels=96,
num_stem_blocks=2,
num_branch_blocks=3,
init_cfg=dict(
type='Pretrained',
checkpoint='./My_Local_Model/open_mmlab/pidnet-m.pth',
),
),
decode_head=dict(
num_classes=8,
in_channels=256,
channels=128,
),
)
optim_wrapper = dict(
type='OptimWrapper',
_delete_=True,
optimizer=dict(
type='AdamW',
lr=0.0001,
weight_decay=0.0005,
),
clip_grad=dict(
max_norm=1,
norm_type=2,
),
)
param_scheduler = [
dict(
type='LinearLR',
start_factor=1e-06,
by_epoch=True,
begin=0,
end=10,
),
dict(
type='PolyLR',
power=0.9,
begin=10,
end=300,
eta_min=1e-05,
by_epoch=True,
),
]

162
Seg_All_In_One_MMSeg/configs/pidnet/my_pidnet_small_g1-300e_val1_check10_publicdataset_autolaparo-512x512.py Normal file
View File

@@ -0,0 +1,162 @@
_base_ = [
'../_base_/models/pidnet.py',
'../_base_/datasets/publicdataset_autolaparo.py',
'../_base_/default_runtime.py',
'../_base_/schedules/schedule_300e_val1_check10.py',
]
norm_cfg = dict(
type='BN',
)
crop_size = (512, 512)
data_preprocessor = dict(
size=(512, 512),
mean=[
123.62464353460942,
85.34836259209033,
82.31539425671558,
],
std=[
47.172211618459315,
47.08256715323592,
48.135121265163605,
],
bgr_to_rgb=False,
)
train_pipeline = [
dict(
type='LoadImageFromFile',
),
dict(
type='LoadAnnotations',
),
dict(
type='RandomResize',
scale=(1920, 1080),
ratio_range=(0.5, 2.0),
),
dict(
type='RandomCrop',
crop_size=(256, 256),
cat_max_ratio=0.75,
),
dict(
type='RandomFlip',
prob=0.5,
),
dict(
type='PhotoMetricDistortion',
),
dict(
type='GenerateEdge',
edge_width=4,
),
dict(
type='PackSegInputs',
),
]
train_dataloader = dict(
dataset=dict(
pipeline=[
dict(
type='LoadImageFromFile',
),
dict(
type='LoadAnnotations',
),
dict(
type='RandomResize',
scale=(1920, 1080),
ratio_range=(0.5, 2.0),
),
dict(
type='RandomCrop',
crop_size=(256, 256),
cat_max_ratio=0.75,
),
dict(
type='RandomFlip',
prob=0.5,
),
dict(
type='PhotoMetricDistortion',
),
dict(
type='GenerateEdge',
edge_width=4,
),
dict(
type='PackSegInputs',
),
],
),
)
model = dict(
data_preprocessor=dict(
size=(512, 512),
mean=[
123.62464353460942,
85.34836259209033,
82.31539425671558,
],
std=[
47.172211618459315,
47.08256715323592,
48.135121265163605,
],
bgr_to_rgb=False,
),
backbone=dict(
channels=32,
ppm_channels=96,
num_stem_blocks=2,
num_branch_blocks=3,
init_cfg=dict(
type='Pretrained',
checkpoint='./My_Local_Model/open_mmlab/pidnet-s.pth',
),
),
decode_head=dict(
num_classes=10,
in_channels=128,
channels=128,
),
)
optim_wrapper = dict(
type='OptimWrapper',
_delete_=True,
optimizer=dict(
type='AdamW',
lr=0.0001,
weight_decay=0.0005,
),
clip_grad=dict(
max_norm=1,
norm_type=2,
),
)
param_scheduler = [
dict(
type='LinearLR',
start_factor=1e-06,
by_epoch=True,
begin=0,
end=10,
),
dict(
type='PolyLR',
power=0.9,
begin=10,
end=300,
eta_min=1e-05,
by_epoch=True,
),
]

162
Seg_All_In_One_MMSeg/configs/pidnet/my_pidnet_small_g1-300e_val1_check10_publicdataset_cholecseg8k-512x512.py Normal file
View File

@@ -0,0 +1,162 @@
_base_ = [
'../_base_/models/pidnet.py',
'../_base_/datasets/publicdataset_cholecseg8k.py',
'../_base_/default_runtime.py',
'../_base_/schedules/schedule_300e_val1_check10.py',
]
norm_cfg = dict(
type='BN',
)
crop_size = (512, 512)
data_preprocessor = dict(
size=(512, 512),
mean=[
85.65740418979115,
53.99282220050495,
46.074045888534535,
],
std=[
72.24589167201978,
56.76979155397199,
49.056637115061775,
],
bgr_to_rgb=False,
)
train_pipeline = [
dict(
type='LoadImageFromFile',
),
dict(
type='LoadAnnotations',
),
dict(
type='RandomResize',
scale=(1920, 1080),
ratio_range=(0.5, 2.0),
),
dict(
type='RandomCrop',
crop_size=(256, 256),
cat_max_ratio=0.75,
),
dict(
type='RandomFlip',
prob=0.5,
),
dict(
type='PhotoMetricDistortion',
),
dict(
type='GenerateEdge',
edge_width=4,
),
dict(
type='PackSegInputs',
),
]
train_dataloader = dict(
dataset=dict(
pipeline=[
dict(
type='LoadImageFromFile',
),
dict(
type='LoadAnnotations',
),
dict(
type='RandomResize',
scale=(1920, 1080),
ratio_range=(0.5, 2.0),
),
dict(
type='RandomCrop',
crop_size=(256, 256),
cat_max_ratio=0.75,
),
dict(
type='RandomFlip',
prob=0.5,
),
dict(
type='PhotoMetricDistortion',
),
dict(
type='GenerateEdge',
edge_width=4,
),
dict(
type='PackSegInputs',
),
],
),
)
model = dict(
data_preprocessor=dict(
size=(512, 512),
mean=[
85.65740418979115,
53.99282220050495,
46.074045888534535,
],
std=[
72.24589167201978,
56.76979155397199,
49.056637115061775,
],
bgr_to_rgb=False,
),
backbone=dict(
channels=32,
ppm_channels=96,
num_stem_blocks=2,
num_branch_blocks=3,
init_cfg=dict(
type='Pretrained',
checkpoint='./My_Local_Model/open_mmlab/pidnet-s.pth',
),
),
decode_head=dict(
num_classes=13,
in_channels=128,
channels=128,
),
)
optim_wrapper = dict(
type='OptimWrapper',
_delete_=True,
optimizer=dict(
type='AdamW',
lr=0.0001,
weight_decay=0.0005,
),
clip_grad=dict(
max_norm=1,
norm_type=2,
),
)
param_scheduler = [
dict(
type='LinearLR',
start_factor=1e-06,
by_epoch=True,
begin=0,
end=10,
),
dict(
type='PolyLR',
power=0.9,
begin=10,
end=300,
eta_min=1e-05,
by_epoch=True,
),
]

162
Seg_All_In_One_MMSeg/configs/pidnet/my_pidnet_small_g1-300e_val1_check10_publicdataset_dresden-512x512.py Normal file
View File

@@ -0,0 +1,162 @@
_base_ = [
'../_base_/models/pidnet.py',
'../_base_/datasets/publicdataset_dresden.py',
'../_base_/default_runtime.py',
'../_base_/schedules/schedule_300e_val1_check10.py',
]
norm_cfg = dict(
type='BN',
)
crop_size = (512, 512)
data_preprocessor = dict(
size=(512, 512),
mean=[
103.172638338208,
61.44762740851152,
51.407770213021976,
],
std=[
75.77031253622098,
54.63616729031377,
49.45572239497569,
],
bgr_to_rgb=False,
)
train_pipeline = [
dict(
type='LoadImageFromFile',
),
dict(
type='LoadAnnotations',
),
dict(
type='RandomResize',
scale=(512, 512),
ratio_range=(0.5, 2.0),
),
dict(
type='RandomCrop',
crop_size=(256, 256),
cat_max_ratio=0.75,
),
dict(
type='RandomFlip',
prob=0.5,
),
dict(
type='PhotoMetricDistortion',
),
dict(
type='GenerateEdge',
edge_width=4,
),
dict(
type='PackSegInputs',
),
]
train_dataloader = dict(
dataset=dict(
pipeline=[
dict(
type='LoadImageFromFile',
),
dict(
type='LoadAnnotations',
),
dict(
type='RandomResize',
scale=(512, 512),
ratio_range=(0.5, 2.0),
),
dict(
type='RandomCrop',
crop_size=(256, 256),
cat_max_ratio=0.75,
),
dict(
type='RandomFlip',
prob=0.5,
),
dict(
type='PhotoMetricDistortion',
),
dict(
type='GenerateEdge',
edge_width=4,
),
dict(
type='PackSegInputs',
),
],
),
)
model = dict(
data_preprocessor=dict(
size=(512, 512),
mean=[
103.172638338208,
61.44762740851152,
51.407770213021976,
],
std=[
75.77031253622098,
54.63616729031377,
49.45572239497569,
],
bgr_to_rgb=False,
),
backbone=dict(
channels=32,
ppm_channels=96,
num_stem_blocks=2,
num_branch_blocks=3,
init_cfg=dict(
type='Pretrained',
checkpoint='./My_Local_Model/open_mmlab/pidnet-s.pth',
),
),
decode_head=dict(
num_classes=11,
in_channels=128,
channels=128,
),
)
optim_wrapper = dict(
type='OptimWrapper',
_delete_=True,
optimizer=dict(
type='AdamW',
lr=0.0001,
weight_decay=0.0005,
),
clip_grad=dict(
max_norm=1,
norm_type=2,
),
)
param_scheduler = [
dict(
type='LinearLR',
start_factor=1e-06,
by_epoch=True,
begin=0,
end=10,
),
dict(
type='PolyLR',
power=0.9,
begin=10,
end=300,
eta_min=1e-05,
by_epoch=True,
),
]

162
Seg_All_In_One_MMSeg/configs/pidnet/my_pidnet_small_g1-300e_val1_check10_publicdataset_endovis_2017-512x512.py Normal file
View File

@@ -0,0 +1,162 @@
_base_ = [
'../_base_/models/pidnet.py',
'../_base_/datasets/publicdataset_endovis_2017.py',
'../_base_/default_runtime.py',
'../_base_/schedules/schedule_300e_val1_check10.py',
]
norm_cfg = dict(
type='BN',
)
crop_size = (512, 512)
data_preprocessor = dict(
size=(512, 512),
mean=[
122.21429912990676,
77.0821859677977,
87.03836664626716,
],
std=[
50.53335800365262,
42.895340354037465,
47.739426483390446,
],
bgr_to_rgb=False,
)
train_pipeline = [
dict(
type='LoadImageFromFile',
),
dict(
type='LoadAnnotations',
),
dict(
type='RandomResize',
scale=(512, 512),
ratio_range=(0.5, 2.0),
),
dict(
type='RandomCrop',
crop_size=(256, 256),
cat_max_ratio=0.75,
),
dict(
type='RandomFlip',
prob=0.5,
),
dict(
type='PhotoMetricDistortion',
),
dict(
type='GenerateEdge',
edge_width=4,
),
dict(
type='PackSegInputs',
),
]
train_dataloader = dict(
dataset=dict(
pipeline=[
dict(
type='LoadImageFromFile',
),
dict(
type='LoadAnnotations',
),
dict(
type='RandomResize',
scale=(512, 512),
ratio_range=(0.5, 2.0),
),
dict(
type='RandomCrop',
crop_size=(256, 256),
cat_max_ratio=0.75,
),
dict(
type='RandomFlip',
prob=0.5,
),
dict(
type='PhotoMetricDistortion',
),
dict(
type='GenerateEdge',
edge_width=4,
),
dict(
type='PackSegInputs',
),
],
),
)
model = dict(
data_preprocessor=dict(
size=(512, 512),
mean=[
122.21429912990676,
77.0821859677977,
87.03836664626716,
],
std=[
50.53335800365262,
42.895340354037465,
47.739426483390446,
],
bgr_to_rgb=False,
),
backbone=dict(
channels=32,
ppm_channels=96,
num_stem_blocks=2,
num_branch_blocks=3,
init_cfg=dict(
type='Pretrained',
checkpoint='./My_Local_Model/open_mmlab/pidnet-s.pth',
),
),
decode_head=dict(
num_classes=8,
in_channels=128,
channels=128,
),
)
optim_wrapper = dict(
type='OptimWrapper',
_delete_=True,
optimizer=dict(
type='AdamW',
lr=0.0001,
weight_decay=0.0005,
),
clip_grad=dict(
max_norm=1,
norm_type=2,
),
)
param_scheduler = [
dict(
type='LinearLR',
start_factor=1e-06,
by_epoch=True,
begin=0,
end=10,
),
dict(
type='PolyLR',
power=0.9,
begin=10,
end=300,
eta_min=1e-05,
by_epoch=True,
),
]

162
Seg_All_In_One_MMSeg/configs/pidnet/my_pidnet_small_g1-300e_val1_check10_publicdataset_endovis_2018-512x512.py Normal file
View File

@@ -0,0 +1,162 @@
_base_ = [
'../_base_/models/pidnet.py',
'../_base_/datasets/publicdataset_endovis_2018.py',
'../_base_/default_runtime.py',
'../_base_/schedules/schedule_300e_val1_check10.py',
]
norm_cfg = dict(
type='BN',
)
crop_size = (512, 512)
data_preprocessor = dict(
size=(512, 512),
mean=[
122.21429912990676,
77.0821859677977,
87.03836664626716,
],
std=[
50.53335800365262,
42.895340354037465,
47.739426483390446,
],
bgr_to_rgb=False,
)
train_pipeline = [
dict(
type='LoadImageFromFile',
),
dict(
type='LoadAnnotations',
),
dict(
type='RandomResize',
scale=(512, 512),
ratio_range=(0.5, 2.0),
),
dict(
type='RandomCrop',
crop_size=(256, 256),
cat_max_ratio=0.75,
),
dict(
type='RandomFlip',
prob=0.5,
),
dict(
type='PhotoMetricDistortion',
),
dict(
type='GenerateEdge',
edge_width=4,
),
dict(
type='PackSegInputs',
),
]
train_dataloader = dict(
dataset=dict(
pipeline=[
dict(
type='LoadImageFromFile',
),
dict(
type='LoadAnnotations',
),
dict(
type='RandomResize',
scale=(512, 512),
ratio_range=(0.5, 2.0),
),
dict(
type='RandomCrop',
crop_size=(256, 256),
cat_max_ratio=0.75,
),
dict(
type='RandomFlip',
prob=0.5,
),
dict(
type='PhotoMetricDistortion',
),
dict(
type='GenerateEdge',
edge_width=4,
),
dict(
type='PackSegInputs',
),
],
),
)
model = dict(
data_preprocessor=dict(
size=(512, 512),
mean=[
122.21429912990676,
77.0821859677977,
87.03836664626716,
],
std=[
50.53335800365262,
42.895340354037465,
47.739426483390446,
],
bgr_to_rgb=False,
),
backbone=dict(
channels=32,
ppm_channels=96,
num_stem_blocks=2,
num_branch_blocks=3,
init_cfg=dict(
type='Pretrained',
checkpoint='./My_Local_Model/open_mmlab/pidnet-s.pth',
),
),
decode_head=dict(
num_classes=8,
in_channels=128,
channels=128,
),
)
optim_wrapper = dict(
type='OptimWrapper',
_delete_=True,
optimizer=dict(
type='AdamW',
lr=0.0001,
weight_decay=0.0005,
),
clip_grad=dict(
max_norm=1,
norm_type=2,
),
)
param_scheduler = [
dict(
type='LinearLR',
start_factor=1e-06,
by_epoch=True,
begin=0,
end=10,
),
dict(
type='PolyLR',
power=0.9,
begin=10,
end=300,
eta_min=1e-05,
by_epoch=True,
),
]

10
Seg_All_In_One_MMSeg/configs/pidnet/pidnet-l_2xb6-120k_1024x1024-cityscapes.py Normal file
View File

@@ -0,0 +1,10 @@
_base_ = './pidnet-s_2xb6-120k_1024x1024-cityscapes.py'
checkpoint_file = 'https://download.openmmlab.com/mmsegmentation/v0.5/pretrain/pidnet/pidnet-l_imagenet1k_20230306-67889109.pth' # noqa
model = dict(
backbone=dict(
channels=64,
ppm_channels=112,
num_stem_blocks=3,
num_branch_blocks=4,
init_cfg=dict(checkpoint=checkpoint_file)),
decode_head=dict(in_channels=256, channels=256))

5
Seg_All_In_One_MMSeg/configs/pidnet/pidnet-m_2xb6-120k_1024x1024-cityscapes.py Normal file
View File

@@ -0,0 +1,5 @@
_base_ = './pidnet-s_2xb6-120k_1024x1024-cityscapes.py'
checkpoint_file = 'https://download.openmmlab.com/mmsegmentation/v0.5/pretrain/pidnet/pidnet-m_imagenet1k_20230306-39893c52.pth' # noqa
model = dict(
backbone=dict(channels=64, init_cfg=dict(checkpoint=checkpoint_file)),
decode_head=dict(in_channels=256))

113
Seg_All_In_One_MMSeg/configs/pidnet/pidnet-s_2xb6-120k_1024x1024-cityscapes.py Normal file
View File

@@ -0,0 +1,113 @@
_base_ = [
'../_base_/datasets/cityscapes_1024x1024.py',
'../_base_/default_runtime.py'
]
# The class_weight is borrowed from https://github.com/openseg-group/OCNet.pytorch/issues/14 # noqa
# Licensed under the MIT License
class_weight = [
0.8373, 0.918, 0.866, 1.0345, 1.0166, 0.9969, 0.9754, 1.0489, 0.8786,
1.0023, 0.9539, 0.9843, 1.1116, 0.9037, 1.0865, 1.0955, 1.0865, 1.1529,
1.0507
]
checkpoint_file = 'https://download.openmmlab.com/mmsegmentation/v0.5/pretrain/pidnet/pidnet-s_imagenet1k_20230306-715e6273.pth' # noqa
crop_size = (1024, 1024)
data_preprocessor = dict(
type='SegDataPreProcessor',
mean=[123.675, 116.28, 103.53],
std=[58.395, 57.12, 57.375],
bgr_to_rgb=True,
pad_val=0,
seg_pad_val=255,
size=crop_size)
norm_cfg = dict(type='SyncBN', requires_grad=True)
model = dict(
type='EncoderDecoder',
data_preprocessor=data_preprocessor,
backbone=dict(
type='PIDNet',
in_channels=3,
channels=32,
ppm_channels=96,
num_stem_blocks=2,
num_branch_blocks=3,
align_corners=False,
norm_cfg=norm_cfg,
act_cfg=dict(type='ReLU', inplace=True),
init_cfg=dict(type='Pretrained', checkpoint=checkpoint_file)),
decode_head=dict(
type='PIDHead',
in_channels=128,
channels=128,
num_classes=19,
norm_cfg=norm_cfg,
act_cfg=dict(type='ReLU', inplace=True),
align_corners=True,
loss_decode=[
dict(
type='CrossEntropyLoss',
use_sigmoid=False,
class_weight=class_weight,
loss_weight=0.4),
dict(
type='OhemCrossEntropy',
thres=0.9,
min_kept=131072,
class_weight=class_weight,
loss_weight=1.0),
dict(type='BoundaryLoss', loss_weight=20.0),
dict(
type='OhemCrossEntropy',
thres=0.9,
min_kept=131072,
class_weight=class_weight,
loss_weight=1.0)
]),
train_cfg=dict(),
test_cfg=dict(mode='whole'))
train_pipeline = [
dict(type='LoadImageFromFile'),
dict(type='LoadAnnotations'),
dict(
type='RandomResize',
scale=(2048, 1024),
ratio_range=(0.5, 2.0),
keep_ratio=True),
dict(type='RandomCrop', crop_size=crop_size, cat_max_ratio=0.75),
dict(type='RandomFlip', prob=0.5),
dict(type='PhotoMetricDistortion'),
dict(type='GenerateEdge', edge_width=4),
dict(type='PackSegInputs')
]
train_dataloader = dict(batch_size=6, dataset=dict(pipeline=train_pipeline))
iters = 120000
# optimizer
optimizer = dict(type='SGD', lr=0.01, momentum=0.9, weight_decay=0.0005)
optim_wrapper = dict(type='OptimWrapper', optimizer=optimizer, clip_grad=None)
# learning policy
param_scheduler = [
dict(
type='PolyLR',
eta_min=0,
power=0.9,
begin=0,
end=iters,
by_epoch=False)
]
# training schedule for 120k
train_cfg = dict(
type='IterBasedTrainLoop', max_iters=iters, val_interval=iters // 10)
val_cfg = dict(type='ValLoop')
test_cfg = dict(type='TestLoop')
default_hooks = dict(
timer=dict(type='IterTimerHook'),
logger=dict(type='LoggerHook', interval=50, log_metric_by_epoch=False),
param_scheduler=dict(type='ParamSchedulerHook'),
checkpoint=dict(
type='CheckpointHook', by_epoch=False, interval=iters // 10),
sampler_seed=dict(type='DistSamplerSeedHook'),
visualization=dict(type='SegVisualizationHook'))
randomness = dict(seed=304)