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

63
Seg_All_In_One_MMSeg/configs/fastfcn/README.md Normal file
View File

@@ -0,0 +1,63 @@
# FastFCN
> [FastFCN: Rethinking Dilated Convolution in the Backbone for Semantic Segmentation](https://arxiv.org/abs/1903.11816)
## Introduction
<!-- [ALGORITHM] -->
<a href="https://github.com/wuhuikai/FastFCN">Official Repo</a>
<a href="https://github.com/open-mmlab/mmsegmentation/blob/v0.18.0/mmseg/models/necks/jpu.py#L12">Code Snippet</a>
## Abstract
<!-- [ABSTRACT] -->
Modern approaches for semantic segmentation usually employ dilated convolutions in the backbone to extract high-resolution feature maps, which brings heavy computation complexity and memory footprint. To replace the time and memory consuming dilated convolutions, we propose a novel joint upsampling module named Joint Pyramid Upsampling (JPU) by formulating the task of extracting high-resolution feature maps into a joint upsampling problem. With the proposed JPU, our method reduces the computation complexity by more than three times without performance loss. Experiments show that JPU is superior to other upsampling modules, which can be plugged into many existing approaches to reduce computation complexity and improve performance. By replacing dilated convolutions with the proposed JPU module, our method achieves the state-of-the-art performance in Pascal Context dataset (mIoU of 53.13%) and ADE20K dataset (final score of 0.5584) while running 3 times faster.
<!-- [IMAGE] -->
<div align=center>
<img src="https://user-images.githubusercontent.com/24582831/142901374-6e0252ab-6e0f-4acd-86ad-1e9f49be3185.png" width="70%"/>
</div>
## Results and models
### Cityscapes
| Method | Backbone | Crop Size | Lr schd | Mem (GB) | Inf time (fps) | Device | mIoU | mIoU(ms+flip) | config | download |
| ------------------- | -------------- | --------- | ------: | -------- | -------------- | ------ | ----: | ------------- | ----------------------------------------------------------------------------------------------------------------------------------------- | ------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------ |
| FastFCN + DeepLabV3 | R-50-D32 | 512x1024 | 80000 | 5.67 | 2.64 | V100 | 79.12 | 80.58 | [config](https://github.com/open-mmlab/mmsegmentation/blob/main/configs/fastfcn/fastfcn_r50-d32_jpu_aspp_4xb2-80k_cityscapes-512x1024.py) | [model](https://download.openmmlab.com/mmsegmentation/v0.5/fastfcn/fastfcn_r50-d32_jpu_aspp_512x1024_80k_cityscapes/fastfcn_r50-d32_jpu_aspp_512x1024_80k_cityscapes_20210928_053722-5d1a2648.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/fastfcn/fastfcn_r50-d32_jpu_aspp_512x1024_80k_cityscapes/fastfcn_r50-d32_jpu_aspp_512x1024_80k_cityscapes_20210928_053722.log.json) |
| FastFCN + DeepLabV3 | R-50-D32 (4x4) | 512x1024 | 80000 | 9.79 | - | V100 | 79.52 | 80.91 | [config](https://github.com/open-mmlab/mmsegmentation/blob/main/configs/fastfcn/fastfcn_r50-d32_jpu_aspp_4xb2-80k_cityscapes-512x1024.py) | [model](https://download.openmmlab.com/mmsegmentation/v0.5/fastfcn/fastfcn_r50-d32_jpu_aspp_4x4_512x1024_80k_cityscapes/fastfcn_r50-d32_jpu_aspp_4x4_512x1024_80k_cityscapes_20210924_214357-72220849.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/fastfcn/fastfcn_r50-d32_jpu_aspp_4x4_512x1024_80k_cityscapes/fastfcn_r50-d32_jpu_aspp_4x4_512x1024_80k_cityscapes_20210924_214357.log.json) |
| FastFCN + PSPNet | R-50-D32 | 512x1024 | 80000 | 5.67 | 4.40 | V100 | 79.26 | 80.86 | [config](https://github.com/open-mmlab/mmsegmentation/blob/main/configs/fastfcn/fastfcn_r50-d32_jpu_psp_4xb2-80k_cityscapes-512x1024.py) | [model](https://download.openmmlab.com/mmsegmentation/v0.5/fastfcn/fastfcn_r50-d32_jpu_psp_512x1024_80k_cityscapes/fastfcn_r50-d32_jpu_psp_512x1024_80k_cityscapes_20210928_053722-57749bed.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/fastfcn/fastfcn_r50-d32_jpu_psp_512x1024_80k_cityscapes/fastfcn_r50-d32_jpu_psp_512x1024_80k_cityscapes_20210928_053722.log.json) |
| FastFCN + PSPNet | R-50-D32 (4x4) | 512x1024 | 80000 | 9.94 | - | V100 | 78.76 | 80.03 | [config](https://github.com/open-mmlab/mmsegmentation/blob/main/configs/fastfcn/fastfcn_r50-d32_jpu_psp_4xb2-80k_cityscapes-512x1024.py) | [model](https://download.openmmlab.com/mmsegmentation/v0.5/fastfcn/fastfcn_r50-d32_jpu_psp_4x4_512x1024_80k_cityscapes/fastfcn_r50-d32_jpu_psp_4x4_512x1024_80k_cityscapes_20210925_061841-77e87b0a.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/fastfcn/fastfcn_r50-d32_jpu_psp_4x4_512x1024_80k_cityscapes/fastfcn_r50-d32_jpu_psp_4x4_512x1024_80k_cityscapes_20210925_061841.log.json) |
| FastFCN + EncNet | R-50-D32 | 512x1024 | 80000 | 8.15 | 4.77 | V100 | 77.97 | 79.92 | [config](https://github.com/open-mmlab/mmsegmentation/blob/main/configs/fastfcn/fastfcn_r50-d32_jpu_enc_4xb2-80k_cityscapes-512x1024.py) | [model](https://download.openmmlab.com/mmsegmentation/v0.5/fastfcn/fastfcn_r50-d32_jpu_enc_512x1024_80k_cityscapes/fastfcn_r50-d32_jpu_enc_512x1024_80k_cityscapes_20210928_030036-78da5046.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/fastfcn/fastfcn_r50-d32_jpu_enc_512x1024_80k_cityscapes/fastfcn_r50-d32_jpu_enc_512x1024_80k_cityscapes_20210928_030036.log.json) |
| FastFCN + EncNet | R-50-D32 (4x4) | 512x1024 | 80000 | 15.45 | - | V100 | 78.6 | 80.25 | [config](https://github.com/open-mmlab/mmsegmentation/blob/main/configs/fastfcn/fastfcn_r50-d32_jpu_enc_4xb2-80k_cityscapes-512x1024.py) | [model](https://download.openmmlab.com/mmsegmentation/v0.5/fastfcn/fastfcn_r50-d32_jpu_enc_4x4_512x1024_80k_cityscapes/fastfcn_r50-d32_jpu_enc_4x4_512x1024_80k_cityscapes_20210926_093217-e1eb6dbb.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/fastfcn/fastfcn_r50-d32_jpu_enc_4x4_512x1024_80k_cityscapes/fastfcn_r50-d32_jpu_enc_4x4_512x1024_80k_cityscapes_20210926_093217.log.json) |
### ADE20K
| Method | Backbone | Crop Size | Lr schd | Mem (GB) | Inf time (fps) | Device | mIoU | mIoU(ms+flip) | config | download |
| ------------------- | -------- | --------- | ------: | -------- | -------------- | ------ | ----: | ------------- | ------------------------------------------------------------------------------------------------------------------------------------- | ---------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
| FastFCN + DeepLabV3 | R-50-D32 | 512x1024 | 80000 | 8.46 | 12.06 | V100 | 41.88 | 42.91 | [config](https://github.com/open-mmlab/mmsegmentation/blob/main/configs/fastfcn/fastfcn_r50-d32_jpu_aspp_4xb4-80k_ade20k-512x512.py) | [model](https://download.openmmlab.com/mmsegmentation/v0.5/fastfcn/fastfcn_r50-d32_jpu_aspp_512x512_80k_ade20k/fastfcn_r50-d32_jpu_aspp_512x512_80k_ade20k_20211013_190619-3aa40f2d.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/fastfcn/fastfcn_r50-d32_jpu_aspp_512x512_80k_ade20k/fastfcn_r50-d32_jpu_aspp_512x512_80k_ade20k_20211013_190619.log.json) |
| FastFCN + DeepLabV3 | R-50-D32 | 512x1024 | 160000 | - | - | V100 | 43.58 | 44.92 | [config](https://github.com/open-mmlab/mmsegmentation/blob/main/configs/fastfcn/fastfcn_r50-d32_jpu_aspp_4xb4-160k_ade20k-512x512.py) | [model](https://download.openmmlab.com/mmsegmentation/v0.5/fastfcn/fastfcn_r50-d32_jpu_aspp_512x512_160k_ade20k/fastfcn_r50-d32_jpu_aspp_512x512_160k_ade20k_20211008_152246-27036aee.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/fastfcn/fastfcn_r50-d32_jpu_aspp_512x512_160k_ade20k/fastfcn_r50-d32_jpu_aspp_512x512_160k_ade20k_20211008_152246.log.json) |
| FastFCN + PSPNet | R-50-D32 | 512x1024 | 80000 | 8.02 | 19.21 | V100 | 41.40 | 42.12 | [config](https://github.com/open-mmlab/mmsegmentation/blob/main/configs/fastfcn/fastfcn_r50-d32_jpu_psp_4xb4-80k_ade20k-512x512.py) | [model](https://download.openmmlab.com/mmsegmentation/v0.5/fastfcn/fastfcn_r50-d32_jpu_psp_512x512_80k_ade20k/fastfcn_r50-d32_jpu_psp_512x512_80k_ade20k_20210930_225137-993d07c8.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/fastfcn/fastfcn_r50-d32_jpu_psp_512x512_80k_ade20k/fastfcn_r50-d32_jpu_psp_512x512_80k_ade20k_20210930_225137.log.json) |
| FastFCN + PSPNet | R-50-D32 | 512x1024 | 160000 | - | - | V100 | 42.63 | 43.71 | [config](https://github.com/open-mmlab/mmsegmentation/blob/main/configs/fastfcn/fastfcn_r50-d32_jpu_psp_4xb4-160k_ade20k-512x512.py) | [model](https://download.openmmlab.com/mmsegmentation/v0.5/fastfcn/fastfcn_r50-d32_jpu_psp_512x512_160k_ade20k/fastfcn_r50-d32_jpu_psp_512x512_160k_ade20k_20211008_105455-e8f5a2fd.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/fastfcn/fastfcn_r50-d32_jpu_psp_512x512_160k_ade20k/fastfcn_r50-d32_jpu_psp_512x512_160k_ade20k_20211008_105455.log.json) |
| FastFCN + EncNet | R-50-D32 | 512x1024 | 80000 | 9.67 | 17.23 | V100 | 40.88 | 42.36 | [config](https://github.com/open-mmlab/mmsegmentation/blob/main/configs/fastfcn/fastfcn_r50-d32_jpu_enc_4xb4-80k_ade20k-512x512.py) | [model](https://download.openmmlab.com/mmsegmentation/v0.5/fastfcn/fastfcn_r50-d32_jpu_enc_512x512_80k_ade20k/fastfcn_r50-d32_jpu_enc_512x512_80k_ade20k_20210930_225214-65aef6dd.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/fastfcn/fastfcn_r50-d32_jpu_enc_512x512_80k_ade20k/fastfcn_r50-d32_jpu_enc_512x512_80k_ade20k_20210930_225214.log.json) |
| FastFCN + EncNet | R-50-D32 | 512x1024 | 160000 | - | - | V100 | 42.50 | 44.21 | [config](https://github.com/open-mmlab/mmsegmentation/blob/main/configs/fastfcn/fastfcn_r50-d32_jpu_enc_4xb4-160k_ade20k-512x512.py) | [model](https://download.openmmlab.com/mmsegmentation/v0.5/fastfcn/fastfcn_r50-d32_jpu_enc_512x512_160k_ade20k/fastfcn_r50-d32_jpu_enc_512x512_160k_ade20k_20211008_105456-d875ce3c.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/fastfcn/fastfcn_r50-d32_jpu_enc_512x512_160k_ade20k/fastfcn_r50-d32_jpu_enc_512x512_160k_ade20k_20211008_105456.log.json) |
Note:
- `4x4` means 4 GPUs with 4 samples per GPU in training, default setting is 4 GPUs with 2 samples per GPU in training.
- Results of [DeepLabV3 (mIoU: 79.32)](https://github.com/open-mmlab/mmsegmentation/blob/main/configs/deeplabv3), [PSPNet (mIoU: 78.55)](https://github.com/open-mmlab/mmsegmentation/blob/main/configs/pspnet) and [ENCNet (mIoU: 77.94)](https://github.com/open-mmlab/mmsegmentation/blob/main/configs/encnet) can be found in each original repository.
## Citation
```bibtex
@article{wu2019fastfcn,
title={Fastfcn: Rethinking dilated convolution in the backbone for semantic segmentation},
author={Wu, Huikai and Zhang, Junge and Huang, Kaiqi and Liang, Kongming and Yu, Yizhou},
journal={arXiv preprint arXiv:1903.11816},
year={2019}
}
```

20
Seg_All_In_One_MMSeg/configs/fastfcn/fastfcn_r50-d32_jpu_aspp_4xb2-80k_cityscapes-512x1024.py Normal file
View File

@@ -0,0 +1,20 @@
# model settings
_base_ = './fastfcn_r50-d32_jpu_psp_4xb2-80k_cityscapes-512x1024.py'
norm_cfg = dict(type='SyncBN', requires_grad=True)
model = dict(
decode_head=dict(
_delete_=True,
type='ASPPHead',
in_channels=2048,
in_index=2,
channels=512,
dilations=(1, 12, 24, 36),
dropout_ratio=0.1,
num_classes=19,
norm_cfg=norm_cfg,
align_corners=False,
loss_decode=dict(
type='CrossEntropyLoss', use_sigmoid=False, loss_weight=1.0)),
# model training and testing settings
train_cfg=dict(),
test_cfg=dict(mode='whole'))

20
Seg_All_In_One_MMSeg/configs/fastfcn/fastfcn_r50-d32_jpu_aspp_4xb4-160k_ade20k-512x512.py Normal file
View File

@@ -0,0 +1,20 @@
# model settings
_base_ = './fastfcn_r50-d32_jpu_psp_4xb4-160k_ade20k-512x512.py'
norm_cfg = dict(type='SyncBN', requires_grad=True)
model = dict(
decode_head=dict(
_delete_=True,
type='ASPPHead',
in_channels=2048,
in_index=2,
channels=512,
dilations=(1, 12, 24, 36),
dropout_ratio=0.1,
num_classes=150,
norm_cfg=norm_cfg,
align_corners=False,
loss_decode=dict(
type='CrossEntropyLoss', use_sigmoid=False, loss_weight=1.0)),
# model training and testing settings
train_cfg=dict(),
test_cfg=dict(mode='whole'))

20
Seg_All_In_One_MMSeg/configs/fastfcn/fastfcn_r50-d32_jpu_aspp_4xb4-80k_ade20k-512x512.py Normal file
View File

@@ -0,0 +1,20 @@
# model settings
_base_ = './fastfcn_r50-d32_jpu_psp_4xb4-80k_ade20k-512x512.py'
norm_cfg = dict(type='SyncBN', requires_grad=True)
model = dict(
decode_head=dict(
_delete_=True,
type='ASPPHead',
in_channels=2048,
in_index=2,
channels=512,
dilations=(1, 12, 24, 36),
dropout_ratio=0.1,
num_classes=150,
norm_cfg=norm_cfg,
align_corners=False,
loss_decode=dict(
type='CrossEntropyLoss', use_sigmoid=False, loss_weight=1.0)),
# model training and testing settings
train_cfg=dict(),
test_cfg=dict(mode='whole'))

5
Seg_All_In_One_MMSeg/configs/fastfcn/fastfcn_r50-d32_jpu_aspp_4xb4-80k_cityscapes-512x1024.py Normal file
View File

@@ -0,0 +1,5 @@
# model settings
_base_ = './fastfcn_r50-d32_jpu_aspp_4xb2-80k_cityscapes-512x1024.py'
train_dataloader = dict(batch_size=4, num_workers=4)
val_dataloader = dict(batch_size=1, num_workers=4)
test_dataloader = val_dataloader

24
Seg_All_In_One_MMSeg/configs/fastfcn/fastfcn_r50-d32_jpu_enc_4xb2-80k_cityscapes-512x1024.py Normal file
View File

@@ -0,0 +1,24 @@
# model settings
_base_ = './fastfcn_r50-d32_jpu_psp_4xb2-80k_cityscapes-512x1024.py'
norm_cfg = dict(type='SyncBN', requires_grad=True)
model = dict(
decode_head=dict(
_delete_=True,
type='EncHead',
in_channels=[512, 1024, 2048],
in_index=(0, 1, 2),
channels=512,
num_codes=32,
use_se_loss=True,
add_lateral=False,
dropout_ratio=0.1,
num_classes=19,
norm_cfg=norm_cfg,
align_corners=False,
loss_decode=dict(
type='CrossEntropyLoss', use_sigmoid=False, loss_weight=1.0),
loss_se_decode=dict(
type='CrossEntropyLoss', use_sigmoid=True, loss_weight=0.2)),
# model training and testing settings
train_cfg=dict(),
test_cfg=dict(mode='whole'))

24
Seg_All_In_One_MMSeg/configs/fastfcn/fastfcn_r50-d32_jpu_enc_4xb4-160k_ade20k-512x512.py Normal file
View File

@@ -0,0 +1,24 @@
# model settings
_base_ = './fastfcn_r50-d32_jpu_psp_4xb4-160k_ade20k-512x512.py'
norm_cfg = dict(type='SyncBN', requires_grad=True)
model = dict(
decode_head=dict(
_delete_=True,
type='EncHead',
in_channels=[512, 1024, 2048],
in_index=(0, 1, 2),
channels=512,
num_codes=32,
use_se_loss=True,
add_lateral=False,
dropout_ratio=0.1,
num_classes=150,
norm_cfg=norm_cfg,
align_corners=False,
loss_decode=dict(
type='CrossEntropyLoss', use_sigmoid=False, loss_weight=1.0),
loss_se_decode=dict(
type='CrossEntropyLoss', use_sigmoid=True, loss_weight=0.2)),
# model training and testing settings
train_cfg=dict(),
test_cfg=dict(mode='whole'))

24
Seg_All_In_One_MMSeg/configs/fastfcn/fastfcn_r50-d32_jpu_enc_4xb4-80k_ade20k-512x512.py Normal file
View File

@@ -0,0 +1,24 @@
# model settings
_base_ = './fastfcn_r50-d32_jpu_psp_4xb4-80k_ade20k-512x512.py'
norm_cfg = dict(type='SyncBN', requires_grad=True)
model = dict(
decode_head=dict(
_delete_=True,
type='EncHead',
in_channels=[512, 1024, 2048],
in_index=(0, 1, 2),
channels=512,
num_codes=32,
use_se_loss=True,
add_lateral=False,
dropout_ratio=0.1,
num_classes=150,
norm_cfg=norm_cfg,
align_corners=False,
loss_decode=dict(
type='CrossEntropyLoss', use_sigmoid=False, loss_weight=1.0),
loss_se_decode=dict(
type='CrossEntropyLoss', use_sigmoid=True, loss_weight=0.2)),
# model training and testing settings
train_cfg=dict(),
test_cfg=dict(mode='whole'))

5
Seg_All_In_One_MMSeg/configs/fastfcn/fastfcn_r50-d32_jpu_enc_4xb4-80k_cityscapes-512x1024.py Normal file
View File

@@ -0,0 +1,5 @@
# model settings
_base_ = './fastfcn_r50-d32_jpu_enc_4xb2-80k_cityscapes-512x1024.py'
train_dataloader = dict(batch_size=4, num_workers=4)
val_dataloader = dict(batch_size=1, num_workers=4)
test_dataloader = val_dataloader

8
Seg_All_In_One_MMSeg/configs/fastfcn/fastfcn_r50-d32_jpu_psp_4xb2-80k_cityscapes-512x1024.py Normal file
View File

@@ -0,0 +1,8 @@
_base_ = [
'../_base_/models/fastfcn_r50-d32_jpu_psp.py',
'../_base_/datasets/cityscapes.py', '../_base_/default_runtime.py',
'../_base_/schedules/schedule_80k.py'
]
crop_size = (512, 1024)
data_preprocessor = dict(size=crop_size)
model = dict(data_preprocessor=data_preprocessor)

11
Seg_All_In_One_MMSeg/configs/fastfcn/fastfcn_r50-d32_jpu_psp_4xb4-160k_ade20k-512x512.py Normal file
View File

@@ -0,0 +1,11 @@
_base_ = [
'../_base_/models/fastfcn_r50-d32_jpu_psp.py',
'../_base_/datasets/ade20k.py', '../_base_/default_runtime.py',
'../_base_/schedules/schedule_160k.py'
]
crop_size = (512, 512)
data_preprocessor = dict(size=crop_size)
model = dict(
data_preprocessor=data_preprocessor,
decode_head=dict(num_classes=150),
auxiliary_head=dict(num_classes=150))

11
Seg_All_In_One_MMSeg/configs/fastfcn/fastfcn_r50-d32_jpu_psp_4xb4-80k_ade20k-512x512.py Normal file
View File

@@ -0,0 +1,11 @@
_base_ = [
'../_base_/models/fastfcn_r50-d32_jpu_psp.py',
'../_base_/datasets/ade20k.py', '../_base_/default_runtime.py',
'../_base_/schedules/schedule_80k.py'
]
crop_size = (512, 512)
data_preprocessor = dict(size=crop_size)
model = dict(
data_preprocessor=data_preprocessor,
decode_head=dict(num_classes=150),
auxiliary_head=dict(num_classes=150))

11
Seg_All_In_One_MMSeg/configs/fastfcn/fastfcn_r50-d32_jpu_psp_4xb4-80k_cityscapes-512x1024.py Normal file
View File

@@ -0,0 +1,11 @@
_base_ = [
'../_base_/models/fastfcn_r50-d32_jpu_psp.py',
'../_base_/datasets/cityscapes.py', '../_base_/default_runtime.py',
'../_base_/schedules/schedule_80k.py'
]
crop_size = (512, 1024)
data_preprocessor = dict(size=crop_size)
model = dict(data_preprocessor=data_preprocessor)
train_dataloader = dict(batch_size=4, num_workers=4)
val_dataloader = dict(batch_size=1, num_workers=4)
test_dataloader = val_dataloader

311
Seg_All_In_One_MMSeg/configs/fastfcn/metafile.yaml Normal file
View File

@@ -0,0 +1,311 @@
Collections:
- Name: FastFCN
License: Apache License 2.0
Metadata:
Training Data:
- Cityscapes
- ADE20K
Paper:
Title: 'FastFCN: Rethinking Dilated Convolution in the Backbone for Semantic Segmentation'
URL: https://arxiv.org/abs/1903.11816
README: configs/fastfcn/README.md
Frameworks:
- PyTorch
Models:
- Name: fastfcn_r50-d32_jpu_aspp_4xb2-80k_cityscapes-512x1024
In Collection: FastFCN
Results:
Task: Semantic Segmentation
Dataset: Cityscapes
Metrics:
mIoU: 79.12
mIoU(ms+flip): 80.58
Config: configs/fastfcn/fastfcn_r50-d32_jpu_aspp_4xb2-80k_cityscapes-512x1024.py
Metadata:
Training Data: Cityscapes
Batch Size: 8
Architecture:
- R-50-D32
- FastFCN
- DeepLabV3
Training Resources: 4x V100 GPUS
Memory (GB): 5.67
Weights: https://download.openmmlab.com/mmsegmentation/v0.5/fastfcn/fastfcn_r50-d32_jpu_aspp_512x1024_80k_cityscapes/fastfcn_r50-d32_jpu_aspp_512x1024_80k_cityscapes_20210928_053722-5d1a2648.pth
Training log: https://download.openmmlab.com/mmsegmentation/v0.5/fastfcn/fastfcn_r50-d32_jpu_aspp_512x1024_80k_cityscapes/fastfcn_r50-d32_jpu_aspp_512x1024_80k_cityscapes_20210928_053722.log.json
Paper:
Title: 'FastFCN: Rethinking Dilated Convolution in the Backbone for Semantic Segmentation'
URL: https://arxiv.org/abs/1903.11816
Code: https://github.com/open-mmlab/mmsegmentation/blob/v0.18.0/mmseg/models/necks/jpu.py#L12
Framework: PyTorch
- Name: fastfcn_r50-d32_jpu_aspp_4xb2-80k_cityscapes-512x1024
In Collection: FastFCN
Results:
Task: Semantic Segmentation
Dataset: Cityscapes
Metrics:
mIoU: 79.52
mIoU(ms+flip): 80.91
Config: configs/fastfcn/fastfcn_r50-d32_jpu_aspp_4xb2-80k_cityscapes-512x1024.py
Metadata:
Training Data: Cityscapes
Batch Size: 8
Architecture:
- R-50-D32
- FastFCN
- DeepLabV3
Training Resources: 4x V100 GPUS
Memory (GB): 9.79
Weights: https://download.openmmlab.com/mmsegmentation/v0.5/fastfcn/fastfcn_r50-d32_jpu_aspp_4x4_512x1024_80k_cityscapes/fastfcn_r50-d32_jpu_aspp_4x4_512x1024_80k_cityscapes_20210924_214357-72220849.pth
Training log: https://download.openmmlab.com/mmsegmentation/v0.5/fastfcn/fastfcn_r50-d32_jpu_aspp_4x4_512x1024_80k_cityscapes/fastfcn_r50-d32_jpu_aspp_4x4_512x1024_80k_cityscapes_20210924_214357.log.json
Paper:
Title: 'FastFCN: Rethinking Dilated Convolution in the Backbone for Semantic Segmentation'
URL: https://arxiv.org/abs/1903.11816
Code: https://github.com/open-mmlab/mmsegmentation/blob/v0.18.0/mmseg/models/necks/jpu.py#L12
Framework: PyTorch
- Name: fastfcn_r50-d32_jpu_psp_4xb2-80k_cityscapes-512x1024
In Collection: FastFCN
Results:
Task: Semantic Segmentation
Dataset: Cityscapes
Metrics:
mIoU: 79.26
mIoU(ms+flip): 80.86
Config: configs/fastfcn/fastfcn_r50-d32_jpu_psp_4xb2-80k_cityscapes-512x1024.py
Metadata:
Training Data: Cityscapes
Batch Size: 8
Architecture:
- R-50-D32
- FastFCN
- PSPNet
Training Resources: 4x V100 GPUS
Memory (GB): 5.67
Weights: https://download.openmmlab.com/mmsegmentation/v0.5/fastfcn/fastfcn_r50-d32_jpu_psp_512x1024_80k_cityscapes/fastfcn_r50-d32_jpu_psp_512x1024_80k_cityscapes_20210928_053722-57749bed.pth
Training log: https://download.openmmlab.com/mmsegmentation/v0.5/fastfcn/fastfcn_r50-d32_jpu_psp_512x1024_80k_cityscapes/fastfcn_r50-d32_jpu_psp_512x1024_80k_cityscapes_20210928_053722.log.json
Paper:
Title: 'FastFCN: Rethinking Dilated Convolution in the Backbone for Semantic Segmentation'
URL: https://arxiv.org/abs/1903.11816
Code: https://github.com/open-mmlab/mmsegmentation/blob/v0.18.0/mmseg/models/necks/jpu.py#L12
Framework: PyTorch
- Name: fastfcn_r50-d32_jpu_psp_4xb2-80k_cityscapes-512x1024
In Collection: FastFCN
Results:
Task: Semantic Segmentation
Dataset: Cityscapes
Metrics:
mIoU: 78.76
mIoU(ms+flip): 80.03
Config: configs/fastfcn/fastfcn_r50-d32_jpu_psp_4xb2-80k_cityscapes-512x1024.py
Metadata:
Training Data: Cityscapes
Batch Size: 8
Architecture:
- R-50-D32
- FastFCN
- PSPNet
Training Resources: 4x V100 GPUS
Memory (GB): 9.94
Weights: https://download.openmmlab.com/mmsegmentation/v0.5/fastfcn/fastfcn_r50-d32_jpu_psp_4x4_512x1024_80k_cityscapes/fastfcn_r50-d32_jpu_psp_4x4_512x1024_80k_cityscapes_20210925_061841-77e87b0a.pth
Training log: https://download.openmmlab.com/mmsegmentation/v0.5/fastfcn/fastfcn_r50-d32_jpu_psp_4x4_512x1024_80k_cityscapes/fastfcn_r50-d32_jpu_psp_4x4_512x1024_80k_cityscapes_20210925_061841.log.json
Paper:
Title: 'FastFCN: Rethinking Dilated Convolution in the Backbone for Semantic Segmentation'
URL: https://arxiv.org/abs/1903.11816
Code: https://github.com/open-mmlab/mmsegmentation/blob/v0.18.0/mmseg/models/necks/jpu.py#L12
Framework: PyTorch
- Name: fastfcn_r50-d32_jpu_enc_4xb2-80k_cityscapes-512x1024
In Collection: FastFCN
Results:
Task: Semantic Segmentation
Dataset: Cityscapes
Metrics:
mIoU: 77.97
mIoU(ms+flip): 79.92
Config: configs/fastfcn/fastfcn_r50-d32_jpu_enc_4xb2-80k_cityscapes-512x1024.py
Metadata:
Training Data: Cityscapes
Batch Size: 8
Architecture:
- R-50-D32
- FastFCN
- EncNet
Training Resources: 4x V100 GPUS
Memory (GB): 8.15
Weights: https://download.openmmlab.com/mmsegmentation/v0.5/fastfcn/fastfcn_r50-d32_jpu_enc_512x1024_80k_cityscapes/fastfcn_r50-d32_jpu_enc_512x1024_80k_cityscapes_20210928_030036-78da5046.pth
Training log: https://download.openmmlab.com/mmsegmentation/v0.5/fastfcn/fastfcn_r50-d32_jpu_enc_512x1024_80k_cityscapes/fastfcn_r50-d32_jpu_enc_512x1024_80k_cityscapes_20210928_030036.log.json
Paper:
Title: 'FastFCN: Rethinking Dilated Convolution in the Backbone for Semantic Segmentation'
URL: https://arxiv.org/abs/1903.11816
Code: https://github.com/open-mmlab/mmsegmentation/blob/v0.18.0/mmseg/models/necks/jpu.py#L12
Framework: PyTorch
- Name: fastfcn_r50-d32_jpu_enc_4xb2-80k_cityscapes-512x1024
In Collection: FastFCN
Results:
Task: Semantic Segmentation
Dataset: Cityscapes
Metrics:
mIoU: 78.6
mIoU(ms+flip): 80.25
Config: configs/fastfcn/fastfcn_r50-d32_jpu_enc_4xb2-80k_cityscapes-512x1024.py
Metadata:
Training Data: Cityscapes
Batch Size: 8
Architecture:
- R-50-D32
- FastFCN
- EncNet
Training Resources: 4x V100 GPUS
Memory (GB): 15.45
Weights: https://download.openmmlab.com/mmsegmentation/v0.5/fastfcn/fastfcn_r50-d32_jpu_enc_4x4_512x1024_80k_cityscapes/fastfcn_r50-d32_jpu_enc_4x4_512x1024_80k_cityscapes_20210926_093217-e1eb6dbb.pth
Training log: https://download.openmmlab.com/mmsegmentation/v0.5/fastfcn/fastfcn_r50-d32_jpu_enc_4x4_512x1024_80k_cityscapes/fastfcn_r50-d32_jpu_enc_4x4_512x1024_80k_cityscapes_20210926_093217.log.json
Paper:
Title: 'FastFCN: Rethinking Dilated Convolution in the Backbone for Semantic Segmentation'
URL: https://arxiv.org/abs/1903.11816
Code: https://github.com/open-mmlab/mmsegmentation/blob/v0.18.0/mmseg/models/necks/jpu.py#L12
Framework: PyTorch
- Name: fastfcn_r50-d32_jpu_aspp_4xb4-80k_ade20k-512x512
In Collection: FastFCN
Results:
Task: Semantic Segmentation
Dataset: ADE20K
Metrics:
mIoU: 41.88
mIoU(ms+flip): 42.91
Config: configs/fastfcn/fastfcn_r50-d32_jpu_aspp_4xb4-80k_ade20k-512x512.py
Metadata:
Training Data: ADE20K
Batch Size: 16
Architecture:
- R-50-D32
- FastFCN
- DeepLabV3
Training Resources: 4x V100 GPUS
Memory (GB): 8.46
Weights: https://download.openmmlab.com/mmsegmentation/v0.5/fastfcn/fastfcn_r50-d32_jpu_aspp_512x512_80k_ade20k/fastfcn_r50-d32_jpu_aspp_512x512_80k_ade20k_20211013_190619-3aa40f2d.pth
Training log: https://download.openmmlab.com/mmsegmentation/v0.5/fastfcn/fastfcn_r50-d32_jpu_aspp_512x512_80k_ade20k/fastfcn_r50-d32_jpu_aspp_512x512_80k_ade20k_20211013_190619.log.json
Paper:
Title: 'FastFCN: Rethinking Dilated Convolution in the Backbone for Semantic Segmentation'
URL: https://arxiv.org/abs/1903.11816
Code: https://github.com/open-mmlab/mmsegmentation/blob/v0.18.0/mmseg/models/necks/jpu.py#L12
Framework: PyTorch
- Name: fastfcn_r50-d32_jpu_aspp_4xb4-160k_ade20k-512x512
In Collection: FastFCN
Results:
Task: Semantic Segmentation
Dataset: ADE20K
Metrics:
mIoU: 43.58
mIoU(ms+flip): 44.92
Config: configs/fastfcn/fastfcn_r50-d32_jpu_aspp_4xb4-160k_ade20k-512x512.py
Metadata:
Training Data: ADE20K
Batch Size: 16
Architecture:
- R-50-D32
- FastFCN
- DeepLabV3
Training Resources: 4x V100 GPUS
Weights: https://download.openmmlab.com/mmsegmentation/v0.5/fastfcn/fastfcn_r50-d32_jpu_aspp_512x512_160k_ade20k/fastfcn_r50-d32_jpu_aspp_512x512_160k_ade20k_20211008_152246-27036aee.pth
Training log: https://download.openmmlab.com/mmsegmentation/v0.5/fastfcn/fastfcn_r50-d32_jpu_aspp_512x512_160k_ade20k/fastfcn_r50-d32_jpu_aspp_512x512_160k_ade20k_20211008_152246.log.json
Paper:
Title: 'FastFCN: Rethinking Dilated Convolution in the Backbone for Semantic Segmentation'
URL: https://arxiv.org/abs/1903.11816
Code: https://github.com/open-mmlab/mmsegmentation/blob/v0.18.0/mmseg/models/necks/jpu.py#L12
Framework: PyTorch
- Name: fastfcn_r50-d32_jpu_psp_4xb4-80k_ade20k-512x512
In Collection: FastFCN
Results:
Task: Semantic Segmentation
Dataset: ADE20K
Metrics:
mIoU: 41.4
mIoU(ms+flip): 42.12
Config: configs/fastfcn/fastfcn_r50-d32_jpu_psp_4xb4-80k_ade20k-512x512.py
Metadata:
Training Data: ADE20K
Batch Size: 16
Architecture:
- R-50-D32
- FastFCN
- PSPNet
Training Resources: 4x V100 GPUS
Memory (GB): 8.02
Weights: https://download.openmmlab.com/mmsegmentation/v0.5/fastfcn/fastfcn_r50-d32_jpu_psp_512x512_80k_ade20k/fastfcn_r50-d32_jpu_psp_512x512_80k_ade20k_20210930_225137-993d07c8.pth
Training log: https://download.openmmlab.com/mmsegmentation/v0.5/fastfcn/fastfcn_r50-d32_jpu_psp_512x512_80k_ade20k/fastfcn_r50-d32_jpu_psp_512x512_80k_ade20k_20210930_225137.log.json
Paper:
Title: 'FastFCN: Rethinking Dilated Convolution in the Backbone for Semantic Segmentation'
URL: https://arxiv.org/abs/1903.11816
Code: https://github.com/open-mmlab/mmsegmentation/blob/v0.18.0/mmseg/models/necks/jpu.py#L12
Framework: PyTorch
- Name: fastfcn_r50-d32_jpu_psp_4xb4-160k_ade20k-512x512
In Collection: FastFCN
Results:
Task: Semantic Segmentation
Dataset: ADE20K
Metrics:
mIoU: 42.63
mIoU(ms+flip): 43.71
Config: configs/fastfcn/fastfcn_r50-d32_jpu_psp_4xb4-160k_ade20k-512x512.py
Metadata:
Training Data: ADE20K
Batch Size: 16
Architecture:
- R-50-D32
- FastFCN
- PSPNet
Training Resources: 4x V100 GPUS
Weights: https://download.openmmlab.com/mmsegmentation/v0.5/fastfcn/fastfcn_r50-d32_jpu_psp_512x512_160k_ade20k/fastfcn_r50-d32_jpu_psp_512x512_160k_ade20k_20211008_105455-e8f5a2fd.pth
Training log: https://download.openmmlab.com/mmsegmentation/v0.5/fastfcn/fastfcn_r50-d32_jpu_psp_512x512_160k_ade20k/fastfcn_r50-d32_jpu_psp_512x512_160k_ade20k_20211008_105455.log.json
Paper:
Title: 'FastFCN: Rethinking Dilated Convolution in the Backbone for Semantic Segmentation'
URL: https://arxiv.org/abs/1903.11816
Code: https://github.com/open-mmlab/mmsegmentation/blob/v0.18.0/mmseg/models/necks/jpu.py#L12
Framework: PyTorch
- Name: fastfcn_r50-d32_jpu_enc_4xb4-80k_ade20k-512x512
In Collection: FastFCN
Results:
Task: Semantic Segmentation
Dataset: ADE20K
Metrics:
mIoU: 40.88
mIoU(ms+flip): 42.36
Config: configs/fastfcn/fastfcn_r50-d32_jpu_enc_4xb4-80k_ade20k-512x512.py
Metadata:
Training Data: ADE20K
Batch Size: 16
Architecture:
- R-50-D32
- FastFCN
- EncNet
Training Resources: 4x V100 GPUS
Memory (GB): 9.67
Weights: https://download.openmmlab.com/mmsegmentation/v0.5/fastfcn/fastfcn_r50-d32_jpu_enc_512x512_80k_ade20k/fastfcn_r50-d32_jpu_enc_512x512_80k_ade20k_20210930_225214-65aef6dd.pth
Training log: https://download.openmmlab.com/mmsegmentation/v0.5/fastfcn/fastfcn_r50-d32_jpu_enc_512x512_80k_ade20k/fastfcn_r50-d32_jpu_enc_512x512_80k_ade20k_20210930_225214.log.json
Paper:
Title: 'FastFCN: Rethinking Dilated Convolution in the Backbone for Semantic Segmentation'
URL: https://arxiv.org/abs/1903.11816
Code: https://github.com/open-mmlab/mmsegmentation/blob/v0.18.0/mmseg/models/necks/jpu.py#L12
Framework: PyTorch
- Name: fastfcn_r50-d32_jpu_enc_4xb4-160k_ade20k-512x512
In Collection: FastFCN
Results:
Task: Semantic Segmentation
Dataset: ADE20K
Metrics:
mIoU: 42.5
mIoU(ms+flip): 44.21
Config: configs/fastfcn/fastfcn_r50-d32_jpu_enc_4xb4-160k_ade20k-512x512.py
Metadata:
Training Data: ADE20K
Batch Size: 16
Architecture:
- R-50-D32
- FastFCN
- EncNet
Training Resources: 4x V100 GPUS
Weights: https://download.openmmlab.com/mmsegmentation/v0.5/fastfcn/fastfcn_r50-d32_jpu_enc_512x512_160k_ade20k/fastfcn_r50-d32_jpu_enc_512x512_160k_ade20k_20211008_105456-d875ce3c.pth
Training log: https://download.openmmlab.com/mmsegmentation/v0.5/fastfcn/fastfcn_r50-d32_jpu_enc_512x512_160k_ade20k/fastfcn_r50-d32_jpu_enc_512x512_160k_ade20k_20211008_105456.log.json
Paper:
Title: 'FastFCN: Rethinking Dilated Convolution in the Backbone for Semantic Segmentation'
URL: https://arxiv.org/abs/1903.11816
Code: https://github.com/open-mmlab/mmsegmentation/blob/v0.18.0/mmseg/models/necks/jpu.py#L12
Framework: PyTorch

112
Seg_All_In_One_MMSeg/configs/fastfcn/my_fastfcn_r50_neck_r101_Pre_jpu_aspp_g1-40k_check_4000_my_dataset_model-512x512.py Normal file
View File

@@ -0,0 +1,112 @@
_base_ = [
'../_base_/models/fastfcn_r50-d32_jpu_psp.py',
'../_base_/datasets/my_dataset_model.py',
'../_base_/default_runtime.py',
'../_base_/schedules/schedule_40k_check_4000.py',
]
norm_cfg = dict(
type='BN',
)
crop_size = (512, 512)
data_preprocessor = dict(
size=(512, 512),
mean=[
94.94709810464303,
61.72942233949928,
75.93763705236906,
],
std=[
44.005506081132594,
42.69595666984776,
44.99354156225523,
],
bgr_to_rgb=False,
)
model = dict(
backbone=dict(
norm_cfg=dict(
type='BN',
),
depth=101,
),
data_preprocessor=dict(
size=(512, 512),
mean=[
94.94709810464303,
61.72942233949928,
75.93763705236906,
],
std=[
44.005506081132594,
42.69595666984776,
44.99354156225523,
],
bgr_to_rgb=False,
),
decode_head=dict(
type='PSPHead',
in_channels=2048,
in_index=2,
channels=512,
pool_scales=(1, 2, 3, 6),
dropout_ratio=0.1,
num_classes=19,
norm_cfg=dict(
type='BN',
),
align_corners=False,
loss_decode=dict(
type='DiceLoss',
use_sigmoid=False,
loss_weight=1.0,
),
),
auxiliary_head=dict(
loss_decode=dict(
type='DiceLoss',
use_sigmoid=False,
loss_weight=0.4,
),
norm_cfg=dict(
type='BN',
),
num_classes=36,
),
)
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=False,
begin=0,
end=1500,
),
dict(
type='PolyLR',
power=0.9,
begin=1500,
end=40000,
eta_min=1e-05,
by_epoch=False,
),
]

112
Seg_All_In_One_MMSeg/configs/fastfcn/my_fastfcn_r50_neck_r50_Pre_jpu_aspp_g1-300e_val1_check10_publicdataset_autolaparo-512x512.py Normal file
View File

@@ -0,0 +1,112 @@
_base_ = [
'../_base_/models/fastfcn_r50-d32_jpu_psp.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,
)
model = dict(
backbone=dict(
norm_cfg=dict(
type='BN',
),
depth=50,
),
data_preprocessor=dict(
size=(512, 512),
mean=[
123.62464353460942,
85.34836259209033,
82.31539425671558,
],
std=[
47.172211618459315,
47.08256715323592,
48.135121265163605,
],
bgr_to_rgb=False,
),
decode_head=dict(
type='PSPHead',
in_channels=2048,
in_index=2,
channels=512,
pool_scales=(1, 2, 3, 6),
dropout_ratio=0.1,
num_classes=19,
norm_cfg=dict(
type='BN',
),
align_corners=False,
loss_decode=dict(
type='DiceLoss',
use_sigmoid=False,
loss_weight=1.0,
),
),
auxiliary_head=dict(
loss_decode=dict(
type='DiceLoss',
use_sigmoid=False,
loss_weight=0.4,
),
norm_cfg=dict(
type='BN',
),
num_classes=10,
),
)
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,
),
]

112
Seg_All_In_One_MMSeg/configs/fastfcn/my_fastfcn_r50_neck_r50_Pre_jpu_aspp_g1-300e_val1_check10_publicdataset_cholecseg8k-512x512.py Normal file
View File

@@ -0,0 +1,112 @@
_base_ = [
'../_base_/models/fastfcn_r50-d32_jpu_psp.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,
)
model = dict(
backbone=dict(
norm_cfg=dict(
type='BN',
),
depth=50,
),
data_preprocessor=dict(
size=(512, 512),
mean=[
85.65740418979115,
53.99282220050495,
46.074045888534535,
],
std=[
72.24589167201978,
56.76979155397199,
49.056637115061775,
],
bgr_to_rgb=False,
),
decode_head=dict(
type='PSPHead',
in_channels=2048,
in_index=2,
channels=512,
pool_scales=(1, 2, 3, 6),
dropout_ratio=0.1,
num_classes=19,
norm_cfg=dict(
type='BN',
),
align_corners=False,
loss_decode=dict(
type='DiceLoss',
use_sigmoid=False,
loss_weight=1.0,
),
),
auxiliary_head=dict(
loss_decode=dict(
type='DiceLoss',
use_sigmoid=False,
loss_weight=0.4,
),
norm_cfg=dict(
type='BN',
),
num_classes=13,
),
)
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,
),
]

112
Seg_All_In_One_MMSeg/configs/fastfcn/my_fastfcn_r50_neck_r50_Pre_jpu_aspp_g1-300e_val1_check10_publicdataset_dresden-512x512.py Normal file
View File

@@ -0,0 +1,112 @@
_base_ = [
'../_base_/models/fastfcn_r50-d32_jpu_psp.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,
)
model = dict(
backbone=dict(
norm_cfg=dict(
type='BN',
),
depth=50,
),
data_preprocessor=dict(
size=(512, 512),
mean=[
103.172638338208,
61.44762740851152,
51.407770213021976,
],
std=[
75.77031253622098,
54.63616729031377,
49.45572239497569,
],
bgr_to_rgb=False,
),
decode_head=dict(
type='PSPHead',
in_channels=2048,
in_index=2,
channels=512,
pool_scales=(1, 2, 3, 6),
dropout_ratio=0.1,
num_classes=19,
norm_cfg=dict(
type='BN',
),
align_corners=False,
loss_decode=dict(
type='DiceLoss',
use_sigmoid=False,
loss_weight=1.0,
),
),
auxiliary_head=dict(
loss_decode=dict(
type='DiceLoss',
use_sigmoid=False,
loss_weight=0.4,
),
norm_cfg=dict(
type='BN',
),
num_classes=11,
),
)
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,
),
]

112
Seg_All_In_One_MMSeg/configs/fastfcn/my_fastfcn_r50_neck_r50_Pre_jpu_aspp_g1-300e_val1_check10_publicdataset_endovis_2017-512x512.py Normal file
View File

@@ -0,0 +1,112 @@
_base_ = [
'../_base_/models/fastfcn_r50-d32_jpu_psp.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,
)
model = dict(
backbone=dict(
norm_cfg=dict(
type='BN',
),
depth=50,
),
data_preprocessor=dict(
size=(512, 512),
mean=[
122.21429912990676,
77.0821859677977,
87.03836664626716,
],
std=[
50.53335800365262,
42.895340354037465,
47.739426483390446,
],
bgr_to_rgb=False,
),
decode_head=dict(
type='PSPHead',
in_channels=2048,
in_index=2,
channels=512,
pool_scales=(1, 2, 3, 6),
dropout_ratio=0.1,
num_classes=19,
norm_cfg=dict(
type='BN',
),
align_corners=False,
loss_decode=dict(
type='DiceLoss',
use_sigmoid=False,
loss_weight=1.0,
),
),
auxiliary_head=dict(
loss_decode=dict(
type='DiceLoss',
use_sigmoid=False,
loss_weight=0.4,
),
norm_cfg=dict(
type='BN',
),
num_classes=8,
),
)
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,
),
]

112
Seg_All_In_One_MMSeg/configs/fastfcn/my_fastfcn_r50_neck_r50_Pre_jpu_aspp_g1-300e_val1_check10_publicdataset_endovis_2018-512x512.py Normal file
View File

@@ -0,0 +1,112 @@
_base_ = [
'../_base_/models/fastfcn_r50-d32_jpu_psp.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,
)
model = dict(
backbone=dict(
norm_cfg=dict(
type='BN',
),
depth=50,
),
data_preprocessor=dict(
size=(512, 512),
mean=[
122.21429912990676,
77.0821859677977,
87.03836664626716,
],
std=[
50.53335800365262,
42.895340354037465,
47.739426483390446,
],
bgr_to_rgb=False,
),
decode_head=dict(
type='PSPHead',
in_channels=2048,
in_index=2,
channels=512,
pool_scales=(1, 2, 3, 6),
dropout_ratio=0.1,
num_classes=19,
norm_cfg=dict(
type='BN',
),
align_corners=False,
loss_decode=dict(
type='DiceLoss',
use_sigmoid=False,
loss_weight=1.0,
),
),
auxiliary_head=dict(
loss_decode=dict(
type='DiceLoss',
use_sigmoid=False,
loss_weight=0.4,
),
norm_cfg=dict(
type='BN',
),
num_classes=8,
),
)
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,
),
]

120
Seg_All_In_One_MMSeg/configs/fastfcn/my_fastfcn_r50_neck_r50_Pre_jpu_aspp_g1-40k_check_4000_my_dataset_model-512x512.py Normal file
View File

@@ -0,0 +1,120 @@
_base_ = [
'../_base_/models/fastfcn_r50-d32_jpu_psp.py',
'../_base_/datasets/my_dataset_model.py',
'../_base_/default_runtime.py',
'../_base_/schedules/schedule_40k_check_4000.py',
]
norm_cfg = dict(
type='BN',
)
crop_size = (512, 512)
data_preprocessor = dict(
size=(512, 512),
mean=[
94.94709810464303,
61.72942233949928,
75.93763705236906,
],
std=[
44.005506081132594,
42.69595666984776,
44.99354156225523,
],
bgr_to_rgb=False,
)
model = dict(
backbone=dict(
norm_cfg=dict(
type='BN',
),
depth=50,
),
data_preprocessor=dict(
size=(512, 512),
mean=[
94.94709810464303,
61.72942233949928,
75.93763705236906,
],
std=[
44.005506081132594,
42.69595666984776,
44.99354156225523,
],
bgr_to_rgb=False,
),
decode_head=dict(
_delete_=True,
type='EncHead',
in_channels=[
512,
1024,
2048,
],
in_index=(0, 1, 2),
channels=512,
num_codes=32,
use_se_loss=True,
add_lateral=False,
dropout_ratio=0.1,
num_classes=36,
norm_cfg=dict(
type='BN',
),
align_corners=False,
loss_decode=dict(
type='DiceLoss',
use_sigmoid=False,
loss_weight=1.0,
),
loss_se_decode=dict(
type='DiceLoss',
use_sigmoid=True,
loss_weight=0.2,
),
),
auxiliary_head=dict(
loss_decode=dict(
type='DiceLoss',
use_sigmoid=False,
loss_weight=0.4,
),
),
)
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=False,
begin=0,
end=1500,
),
dict(
type='PolyLR',
power=0.9,
begin=1500,
end=40000,
eta_min=1e-05,
by_epoch=False,
),
]