update
Browse filesThis view is limited to 50 files because it contains too many changes.
See raw diff
- .DS_Store +0 -0
- app.py +63 -0
- configs/.DS_Store +0 -0
- configs/_base_/.DS_Store +0 -0
- configs/_base_/datasets/ade20k.py +54 -0
- configs/_base_/datasets/chase_db1.py +59 -0
- configs/_base_/datasets/cityscapes.py +54 -0
- configs/_base_/datasets/cityscapes_769x769.py +35 -0
- configs/_base_/datasets/drive.py +59 -0
- configs/_base_/datasets/hrf.py +59 -0
- configs/_base_/datasets/pascal_context.py +60 -0
- configs/_base_/datasets/pascal_context_59.py +60 -0
- configs/_base_/datasets/pascal_voc12.py +57 -0
- configs/_base_/datasets/pascal_voc12_aug.py +9 -0
- configs/_base_/datasets/stare.py +59 -0
- configs/_base_/default_runtime.py +14 -0
- configs/_base_/models/ann_r50-d8.py +46 -0
- configs/_base_/models/apcnet_r50-d8.py +44 -0
- configs/_base_/models/ccnet_r50-d8.py +44 -0
- configs/_base_/models/cgnet.py +35 -0
- configs/_base_/models/danet_r50-d8.py +44 -0
- configs/_base_/models/deeplabv3_r50-d8.py +44 -0
- configs/_base_/models/deeplabv3_unet_s5-d16.py +50 -0
- configs/_base_/models/deeplabv3plus_r50-d8.py +46 -0
- configs/_base_/models/dmnet_r50-d8.py +44 -0
- configs/_base_/models/dnl_r50-d8.py +46 -0
- configs/_base_/models/emanet_r50-d8.py +47 -0
- configs/_base_/models/encnet_r50-d8.py +48 -0
- configs/_base_/models/fast_scnn.py +57 -0
- configs/_base_/models/fcn_hr18.py +52 -0
- configs/_base_/models/fcn_r50-d8.py +45 -0
- configs/_base_/models/fcn_unet_s5-d16.py +51 -0
- configs/_base_/models/fpn_r50.py +36 -0
- configs/_base_/models/fpn_uniformer.py +35 -0
- configs/_base_/models/gcnet_r50-d8.py +46 -0
- configs/_base_/models/lraspp_m-v3-d8.py +25 -0
- configs/_base_/models/nonlocal_r50-d8.py +46 -0
- configs/_base_/models/ocrnet_hr18.py +68 -0
- configs/_base_/models/ocrnet_r50-d8.py +47 -0
- configs/_base_/models/pointrend_r50.py +56 -0
- configs/_base_/models/psanet_r50-d8.py +49 -0
- configs/_base_/models/pspnet_r50-d8.py +44 -0
- configs/_base_/models/pspnet_unet_s5-d16.py +50 -0
- configs/_base_/models/upernet_r50.py +44 -0
- configs/_base_/models/upernet_uniformer.py +43 -0
- configs/_base_/schedules/schedule_160k.py +9 -0
- configs/_base_/schedules/schedule_20k.py +9 -0
- configs/_base_/schedules/schedule_40k.py +9 -0
- configs/_base_/schedules/schedule_80k.py +9 -0
- configs/ann/README.md +52 -0
.DS_Store
ADDED
|
Binary file (6.15 kB). View file
|
|
|
app.py
ADDED
|
@@ -0,0 +1,63 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
import os
|
| 2 |
+
|
| 3 |
+
import torch
|
| 4 |
+
import torch.nn.functional as F
|
| 5 |
+
import torchvision.transforms as T
|
| 6 |
+
from mmseg.apis import init_segmentor, inference_segmentor, show_result_pyplot
|
| 7 |
+
from mmseg.core.evaluation import get_palette
|
| 8 |
+
import mmcv
|
| 9 |
+
|
| 10 |
+
import gradio as gr
|
| 11 |
+
from huggingface_hub import hf_hub_download
|
| 12 |
+
|
| 13 |
+
# Device on which to run the model
|
| 14 |
+
# Set to cuda to load on GPU
|
| 15 |
+
device = "cpu"
|
| 16 |
+
checkpoint_file = hf_hub_download(repo_id="Andy1621/uniformer", filename="upernet_global_small.pth")
|
| 17 |
+
config_file = './exp/upernet_hybrid_small/config.py'
|
| 18 |
+
# init detector
|
| 19 |
+
# build the model from a config file and a checkpoint file
|
| 20 |
+
model = init_segmentor(config_file, checkpoint_file, device='cpu')
|
| 21 |
+
|
| 22 |
+
|
| 23 |
+
def set_example_image(example: list) -> dict:
|
| 24 |
+
return gr.Image.update(value=example[0])
|
| 25 |
+
|
| 26 |
+
|
| 27 |
+
def inference(img):
|
| 28 |
+
result = inference_segmentor(model, img)
|
| 29 |
+
res_img = show_result_pyplot(model, img, result, get_palette('cityscapes'))
|
| 30 |
+
return res_img
|
| 31 |
+
|
| 32 |
+
|
| 33 |
+
demo = gr.Blocks()
|
| 34 |
+
with demo:
|
| 35 |
+
gr.Markdown(
|
| 36 |
+
"""
|
| 37 |
+
# UniFormer-S
|
| 38 |
+
Gradio demo for <a href='https://github.com/Sense-X/UniFormer' target='_blank'>UniFormer</a>: To use it, simply upload your image, or click one of the examples to load them. Read more at the links below.
|
| 39 |
+
"""
|
| 40 |
+
)
|
| 41 |
+
|
| 42 |
+
with gr.Box():
|
| 43 |
+
with gr.Row():
|
| 44 |
+
with gr.Column():
|
| 45 |
+
with gr.Row():
|
| 46 |
+
input_image = gr.Image(label='Input Image', type='numpy')
|
| 47 |
+
with gr.Row():
|
| 48 |
+
submit_button = gr.Button('Submit')
|
| 49 |
+
with gr.Column():
|
| 50 |
+
res_image = gr.Image(type='numpy', label='Segmentation Resutls')
|
| 51 |
+
with gr.Row():
|
| 52 |
+
example_images = gr.Dataset(components=[input_image], samples=[['demo.jpg']])
|
| 53 |
+
|
| 54 |
+
gr.Markdown(
|
| 55 |
+
"""
|
| 56 |
+
<p style='text-align: center'><a href='https://arxiv.org/abs/2201.09450' target='_blank'>UniFormer: Unifying Convolution and Self-attention for Visual Recognition</a> | <a href='https://github.com/Sense-X/UniFormer' target='_blank'>Github Repo</a></p>
|
| 57 |
+
"""
|
| 58 |
+
)
|
| 59 |
+
|
| 60 |
+
submit_button.click(fn=inference, inputs=input_image, outputs=res_image)
|
| 61 |
+
example_images.click(fn=set_example_image, inputs=example_images, outputs=example_images.components)
|
| 62 |
+
|
| 63 |
+
demo.launch(enable_queue=True)
|
configs/.DS_Store
ADDED
|
Binary file (6.15 kB). View file
|
|
|
configs/_base_/.DS_Store
ADDED
|
Binary file (6.15 kB). View file
|
|
|
configs/_base_/datasets/ade20k.py
ADDED
|
@@ -0,0 +1,54 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
# dataset settings
|
| 2 |
+
dataset_type = 'ADE20KDataset'
|
| 3 |
+
data_root = 'data/ade/ADEChallengeData2016'
|
| 4 |
+
img_norm_cfg = dict(
|
| 5 |
+
mean=[123.675, 116.28, 103.53], std=[58.395, 57.12, 57.375], to_rgb=True)
|
| 6 |
+
crop_size = (512, 512)
|
| 7 |
+
train_pipeline = [
|
| 8 |
+
dict(type='LoadImageFromFile'),
|
| 9 |
+
dict(type='LoadAnnotations', reduce_zero_label=True),
|
| 10 |
+
dict(type='Resize', img_scale=(2048, 512), ratio_range=(0.5, 2.0)),
|
| 11 |
+
dict(type='RandomCrop', crop_size=crop_size, cat_max_ratio=0.75),
|
| 12 |
+
dict(type='RandomFlip', prob=0.5),
|
| 13 |
+
dict(type='PhotoMetricDistortion'),
|
| 14 |
+
dict(type='Normalize', **img_norm_cfg),
|
| 15 |
+
dict(type='Pad', size=crop_size, pad_val=0, seg_pad_val=255),
|
| 16 |
+
dict(type='DefaultFormatBundle'),
|
| 17 |
+
dict(type='Collect', keys=['img', 'gt_semantic_seg']),
|
| 18 |
+
]
|
| 19 |
+
test_pipeline = [
|
| 20 |
+
dict(type='LoadImageFromFile'),
|
| 21 |
+
dict(
|
| 22 |
+
type='MultiScaleFlipAug',
|
| 23 |
+
img_scale=(2048, 512),
|
| 24 |
+
# img_ratios=[0.5, 0.75, 1.0, 1.25, 1.5, 1.75],
|
| 25 |
+
flip=False,
|
| 26 |
+
transforms=[
|
| 27 |
+
dict(type='Resize', keep_ratio=True),
|
| 28 |
+
dict(type='RandomFlip'),
|
| 29 |
+
dict(type='Normalize', **img_norm_cfg),
|
| 30 |
+
dict(type='ImageToTensor', keys=['img']),
|
| 31 |
+
dict(type='Collect', keys=['img']),
|
| 32 |
+
])
|
| 33 |
+
]
|
| 34 |
+
data = dict(
|
| 35 |
+
samples_per_gpu=4,
|
| 36 |
+
workers_per_gpu=4,
|
| 37 |
+
train=dict(
|
| 38 |
+
type=dataset_type,
|
| 39 |
+
data_root=data_root,
|
| 40 |
+
img_dir='images/training',
|
| 41 |
+
ann_dir='annotations/training',
|
| 42 |
+
pipeline=train_pipeline),
|
| 43 |
+
val=dict(
|
| 44 |
+
type=dataset_type,
|
| 45 |
+
data_root=data_root,
|
| 46 |
+
img_dir='images/validation',
|
| 47 |
+
ann_dir='annotations/validation',
|
| 48 |
+
pipeline=test_pipeline),
|
| 49 |
+
test=dict(
|
| 50 |
+
type=dataset_type,
|
| 51 |
+
data_root=data_root,
|
| 52 |
+
img_dir='images/validation',
|
| 53 |
+
ann_dir='annotations/validation',
|
| 54 |
+
pipeline=test_pipeline))
|
configs/_base_/datasets/chase_db1.py
ADDED
|
@@ -0,0 +1,59 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
# dataset settings
|
| 2 |
+
dataset_type = 'ChaseDB1Dataset'
|
| 3 |
+
data_root = 'data/CHASE_DB1'
|
| 4 |
+
img_norm_cfg = dict(
|
| 5 |
+
mean=[123.675, 116.28, 103.53], std=[58.395, 57.12, 57.375], to_rgb=True)
|
| 6 |
+
img_scale = (960, 999)
|
| 7 |
+
crop_size = (128, 128)
|
| 8 |
+
train_pipeline = [
|
| 9 |
+
dict(type='LoadImageFromFile'),
|
| 10 |
+
dict(type='LoadAnnotations'),
|
| 11 |
+
dict(type='Resize', img_scale=img_scale, ratio_range=(0.5, 2.0)),
|
| 12 |
+
dict(type='RandomCrop', crop_size=crop_size, cat_max_ratio=0.75),
|
| 13 |
+
dict(type='RandomFlip', prob=0.5),
|
| 14 |
+
dict(type='PhotoMetricDistortion'),
|
| 15 |
+
dict(type='Normalize', **img_norm_cfg),
|
| 16 |
+
dict(type='Pad', size=crop_size, pad_val=0, seg_pad_val=255),
|
| 17 |
+
dict(type='DefaultFormatBundle'),
|
| 18 |
+
dict(type='Collect', keys=['img', 'gt_semantic_seg'])
|
| 19 |
+
]
|
| 20 |
+
test_pipeline = [
|
| 21 |
+
dict(type='LoadImageFromFile'),
|
| 22 |
+
dict(
|
| 23 |
+
type='MultiScaleFlipAug',
|
| 24 |
+
img_scale=img_scale,
|
| 25 |
+
# img_ratios=[0.5, 0.75, 1.0, 1.25, 1.5, 1.75, 2.0],
|
| 26 |
+
flip=False,
|
| 27 |
+
transforms=[
|
| 28 |
+
dict(type='Resize', keep_ratio=True),
|
| 29 |
+
dict(type='RandomFlip'),
|
| 30 |
+
dict(type='Normalize', **img_norm_cfg),
|
| 31 |
+
dict(type='ImageToTensor', keys=['img']),
|
| 32 |
+
dict(type='Collect', keys=['img'])
|
| 33 |
+
])
|
| 34 |
+
]
|
| 35 |
+
|
| 36 |
+
data = dict(
|
| 37 |
+
samples_per_gpu=4,
|
| 38 |
+
workers_per_gpu=4,
|
| 39 |
+
train=dict(
|
| 40 |
+
type='RepeatDataset',
|
| 41 |
+
times=40000,
|
| 42 |
+
dataset=dict(
|
| 43 |
+
type=dataset_type,
|
| 44 |
+
data_root=data_root,
|
| 45 |
+
img_dir='images/training',
|
| 46 |
+
ann_dir='annotations/training',
|
| 47 |
+
pipeline=train_pipeline)),
|
| 48 |
+
val=dict(
|
| 49 |
+
type=dataset_type,
|
| 50 |
+
data_root=data_root,
|
| 51 |
+
img_dir='images/validation',
|
| 52 |
+
ann_dir='annotations/validation',
|
| 53 |
+
pipeline=test_pipeline),
|
| 54 |
+
test=dict(
|
| 55 |
+
type=dataset_type,
|
| 56 |
+
data_root=data_root,
|
| 57 |
+
img_dir='images/validation',
|
| 58 |
+
ann_dir='annotations/validation',
|
| 59 |
+
pipeline=test_pipeline))
|
configs/_base_/datasets/cityscapes.py
ADDED
|
@@ -0,0 +1,54 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
# dataset settings
|
| 2 |
+
dataset_type = 'CityscapesDataset'
|
| 3 |
+
data_root = 'data/cityscapes/'
|
| 4 |
+
img_norm_cfg = dict(
|
| 5 |
+
mean=[123.675, 116.28, 103.53], std=[58.395, 57.12, 57.375], to_rgb=True)
|
| 6 |
+
crop_size = (512, 1024)
|
| 7 |
+
train_pipeline = [
|
| 8 |
+
dict(type='LoadImageFromFile'),
|
| 9 |
+
dict(type='LoadAnnotations'),
|
| 10 |
+
dict(type='Resize', img_scale=(2048, 1024), ratio_range=(0.5, 2.0)),
|
| 11 |
+
dict(type='RandomCrop', crop_size=crop_size, cat_max_ratio=0.75),
|
| 12 |
+
dict(type='RandomFlip', prob=0.5),
|
| 13 |
+
dict(type='PhotoMetricDistortion'),
|
| 14 |
+
dict(type='Normalize', **img_norm_cfg),
|
| 15 |
+
dict(type='Pad', size=crop_size, pad_val=0, seg_pad_val=255),
|
| 16 |
+
dict(type='DefaultFormatBundle'),
|
| 17 |
+
dict(type='Collect', keys=['img', 'gt_semantic_seg']),
|
| 18 |
+
]
|
| 19 |
+
test_pipeline = [
|
| 20 |
+
dict(type='LoadImageFromFile'),
|
| 21 |
+
dict(
|
| 22 |
+
type='MultiScaleFlipAug',
|
| 23 |
+
img_scale=(2048, 1024),
|
| 24 |
+
# img_ratios=[0.5, 0.75, 1.0, 1.25, 1.5, 1.75],
|
| 25 |
+
flip=False,
|
| 26 |
+
transforms=[
|
| 27 |
+
dict(type='Resize', keep_ratio=True),
|
| 28 |
+
dict(type='RandomFlip'),
|
| 29 |
+
dict(type='Normalize', **img_norm_cfg),
|
| 30 |
+
dict(type='ImageToTensor', keys=['img']),
|
| 31 |
+
dict(type='Collect', keys=['img']),
|
| 32 |
+
])
|
| 33 |
+
]
|
| 34 |
+
data = dict(
|
| 35 |
+
samples_per_gpu=2,
|
| 36 |
+
workers_per_gpu=2,
|
| 37 |
+
train=dict(
|
| 38 |
+
type=dataset_type,
|
| 39 |
+
data_root=data_root,
|
| 40 |
+
img_dir='leftImg8bit/train',
|
| 41 |
+
ann_dir='gtFine/train',
|
| 42 |
+
pipeline=train_pipeline),
|
| 43 |
+
val=dict(
|
| 44 |
+
type=dataset_type,
|
| 45 |
+
data_root=data_root,
|
| 46 |
+
img_dir='leftImg8bit/val',
|
| 47 |
+
ann_dir='gtFine/val',
|
| 48 |
+
pipeline=test_pipeline),
|
| 49 |
+
test=dict(
|
| 50 |
+
type=dataset_type,
|
| 51 |
+
data_root=data_root,
|
| 52 |
+
img_dir='leftImg8bit/val',
|
| 53 |
+
ann_dir='gtFine/val',
|
| 54 |
+
pipeline=test_pipeline))
|
configs/_base_/datasets/cityscapes_769x769.py
ADDED
|
@@ -0,0 +1,35 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
_base_ = './cityscapes.py'
|
| 2 |
+
img_norm_cfg = dict(
|
| 3 |
+
mean=[123.675, 116.28, 103.53], std=[58.395, 57.12, 57.375], to_rgb=True)
|
| 4 |
+
crop_size = (769, 769)
|
| 5 |
+
train_pipeline = [
|
| 6 |
+
dict(type='LoadImageFromFile'),
|
| 7 |
+
dict(type='LoadAnnotations'),
|
| 8 |
+
dict(type='Resize', img_scale=(2049, 1025), ratio_range=(0.5, 2.0)),
|
| 9 |
+
dict(type='RandomCrop', crop_size=crop_size, cat_max_ratio=0.75),
|
| 10 |
+
dict(type='RandomFlip', prob=0.5),
|
| 11 |
+
dict(type='PhotoMetricDistortion'),
|
| 12 |
+
dict(type='Normalize', **img_norm_cfg),
|
| 13 |
+
dict(type='Pad', size=crop_size, pad_val=0, seg_pad_val=255),
|
| 14 |
+
dict(type='DefaultFormatBundle'),
|
| 15 |
+
dict(type='Collect', keys=['img', 'gt_semantic_seg']),
|
| 16 |
+
]
|
| 17 |
+
test_pipeline = [
|
| 18 |
+
dict(type='LoadImageFromFile'),
|
| 19 |
+
dict(
|
| 20 |
+
type='MultiScaleFlipAug',
|
| 21 |
+
img_scale=(2049, 1025),
|
| 22 |
+
# img_ratios=[0.5, 0.75, 1.0, 1.25, 1.5, 1.75],
|
| 23 |
+
flip=False,
|
| 24 |
+
transforms=[
|
| 25 |
+
dict(type='Resize', keep_ratio=True),
|
| 26 |
+
dict(type='RandomFlip'),
|
| 27 |
+
dict(type='Normalize', **img_norm_cfg),
|
| 28 |
+
dict(type='ImageToTensor', keys=['img']),
|
| 29 |
+
dict(type='Collect', keys=['img']),
|
| 30 |
+
])
|
| 31 |
+
]
|
| 32 |
+
data = dict(
|
| 33 |
+
train=dict(pipeline=train_pipeline),
|
| 34 |
+
val=dict(pipeline=test_pipeline),
|
| 35 |
+
test=dict(pipeline=test_pipeline))
|
configs/_base_/datasets/drive.py
ADDED
|
@@ -0,0 +1,59 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
# dataset settings
|
| 2 |
+
dataset_type = 'DRIVEDataset'
|
| 3 |
+
data_root = 'data/DRIVE'
|
| 4 |
+
img_norm_cfg = dict(
|
| 5 |
+
mean=[123.675, 116.28, 103.53], std=[58.395, 57.12, 57.375], to_rgb=True)
|
| 6 |
+
img_scale = (584, 565)
|
| 7 |
+
crop_size = (64, 64)
|
| 8 |
+
train_pipeline = [
|
| 9 |
+
dict(type='LoadImageFromFile'),
|
| 10 |
+
dict(type='LoadAnnotations'),
|
| 11 |
+
dict(type='Resize', img_scale=img_scale, ratio_range=(0.5, 2.0)),
|
| 12 |
+
dict(type='RandomCrop', crop_size=crop_size, cat_max_ratio=0.75),
|
| 13 |
+
dict(type='RandomFlip', prob=0.5),
|
| 14 |
+
dict(type='PhotoMetricDistortion'),
|
| 15 |
+
dict(type='Normalize', **img_norm_cfg),
|
| 16 |
+
dict(type='Pad', size=crop_size, pad_val=0, seg_pad_val=255),
|
| 17 |
+
dict(type='DefaultFormatBundle'),
|
| 18 |
+
dict(type='Collect', keys=['img', 'gt_semantic_seg'])
|
| 19 |
+
]
|
| 20 |
+
test_pipeline = [
|
| 21 |
+
dict(type='LoadImageFromFile'),
|
| 22 |
+
dict(
|
| 23 |
+
type='MultiScaleFlipAug',
|
| 24 |
+
img_scale=img_scale,
|
| 25 |
+
# img_ratios=[0.5, 0.75, 1.0, 1.25, 1.5, 1.75, 2.0],
|
| 26 |
+
flip=False,
|
| 27 |
+
transforms=[
|
| 28 |
+
dict(type='Resize', keep_ratio=True),
|
| 29 |
+
dict(type='RandomFlip'),
|
| 30 |
+
dict(type='Normalize', **img_norm_cfg),
|
| 31 |
+
dict(type='ImageToTensor', keys=['img']),
|
| 32 |
+
dict(type='Collect', keys=['img'])
|
| 33 |
+
])
|
| 34 |
+
]
|
| 35 |
+
|
| 36 |
+
data = dict(
|
| 37 |
+
samples_per_gpu=4,
|
| 38 |
+
workers_per_gpu=4,
|
| 39 |
+
train=dict(
|
| 40 |
+
type='RepeatDataset',
|
| 41 |
+
times=40000,
|
| 42 |
+
dataset=dict(
|
| 43 |
+
type=dataset_type,
|
| 44 |
+
data_root=data_root,
|
| 45 |
+
img_dir='images/training',
|
| 46 |
+
ann_dir='annotations/training',
|
| 47 |
+
pipeline=train_pipeline)),
|
| 48 |
+
val=dict(
|
| 49 |
+
type=dataset_type,
|
| 50 |
+
data_root=data_root,
|
| 51 |
+
img_dir='images/validation',
|
| 52 |
+
ann_dir='annotations/validation',
|
| 53 |
+
pipeline=test_pipeline),
|
| 54 |
+
test=dict(
|
| 55 |
+
type=dataset_type,
|
| 56 |
+
data_root=data_root,
|
| 57 |
+
img_dir='images/validation',
|
| 58 |
+
ann_dir='annotations/validation',
|
| 59 |
+
pipeline=test_pipeline))
|
configs/_base_/datasets/hrf.py
ADDED
|
@@ -0,0 +1,59 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
# dataset settings
|
| 2 |
+
dataset_type = 'HRFDataset'
|
| 3 |
+
data_root = 'data/HRF'
|
| 4 |
+
img_norm_cfg = dict(
|
| 5 |
+
mean=[123.675, 116.28, 103.53], std=[58.395, 57.12, 57.375], to_rgb=True)
|
| 6 |
+
img_scale = (2336, 3504)
|
| 7 |
+
crop_size = (256, 256)
|
| 8 |
+
train_pipeline = [
|
| 9 |
+
dict(type='LoadImageFromFile'),
|
| 10 |
+
dict(type='LoadAnnotations'),
|
| 11 |
+
dict(type='Resize', img_scale=img_scale, ratio_range=(0.5, 2.0)),
|
| 12 |
+
dict(type='RandomCrop', crop_size=crop_size, cat_max_ratio=0.75),
|
| 13 |
+
dict(type='RandomFlip', prob=0.5),
|
| 14 |
+
dict(type='PhotoMetricDistortion'),
|
| 15 |
+
dict(type='Normalize', **img_norm_cfg),
|
| 16 |
+
dict(type='Pad', size=crop_size, pad_val=0, seg_pad_val=255),
|
| 17 |
+
dict(type='DefaultFormatBundle'),
|
| 18 |
+
dict(type='Collect', keys=['img', 'gt_semantic_seg'])
|
| 19 |
+
]
|
| 20 |
+
test_pipeline = [
|
| 21 |
+
dict(type='LoadImageFromFile'),
|
| 22 |
+
dict(
|
| 23 |
+
type='MultiScaleFlipAug',
|
| 24 |
+
img_scale=img_scale,
|
| 25 |
+
# img_ratios=[0.5, 0.75, 1.0, 1.25, 1.5, 1.75, 2.0],
|
| 26 |
+
flip=False,
|
| 27 |
+
transforms=[
|
| 28 |
+
dict(type='Resize', keep_ratio=True),
|
| 29 |
+
dict(type='RandomFlip'),
|
| 30 |
+
dict(type='Normalize', **img_norm_cfg),
|
| 31 |
+
dict(type='ImageToTensor', keys=['img']),
|
| 32 |
+
dict(type='Collect', keys=['img'])
|
| 33 |
+
])
|
| 34 |
+
]
|
| 35 |
+
|
| 36 |
+
data = dict(
|
| 37 |
+
samples_per_gpu=4,
|
| 38 |
+
workers_per_gpu=4,
|
| 39 |
+
train=dict(
|
| 40 |
+
type='RepeatDataset',
|
| 41 |
+
times=40000,
|
| 42 |
+
dataset=dict(
|
| 43 |
+
type=dataset_type,
|
| 44 |
+
data_root=data_root,
|
| 45 |
+
img_dir='images/training',
|
| 46 |
+
ann_dir='annotations/training',
|
| 47 |
+
pipeline=train_pipeline)),
|
| 48 |
+
val=dict(
|
| 49 |
+
type=dataset_type,
|
| 50 |
+
data_root=data_root,
|
| 51 |
+
img_dir='images/validation',
|
| 52 |
+
ann_dir='annotations/validation',
|
| 53 |
+
pipeline=test_pipeline),
|
| 54 |
+
test=dict(
|
| 55 |
+
type=dataset_type,
|
| 56 |
+
data_root=data_root,
|
| 57 |
+
img_dir='images/validation',
|
| 58 |
+
ann_dir='annotations/validation',
|
| 59 |
+
pipeline=test_pipeline))
|
configs/_base_/datasets/pascal_context.py
ADDED
|
@@ -0,0 +1,60 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
# dataset settings
|
| 2 |
+
dataset_type = 'PascalContextDataset'
|
| 3 |
+
data_root = 'data/VOCdevkit/VOC2010/'
|
| 4 |
+
img_norm_cfg = dict(
|
| 5 |
+
mean=[123.675, 116.28, 103.53], std=[58.395, 57.12, 57.375], to_rgb=True)
|
| 6 |
+
|
| 7 |
+
img_scale = (520, 520)
|
| 8 |
+
crop_size = (480, 480)
|
| 9 |
+
|
| 10 |
+
train_pipeline = [
|
| 11 |
+
dict(type='LoadImageFromFile'),
|
| 12 |
+
dict(type='LoadAnnotations'),
|
| 13 |
+
dict(type='Resize', img_scale=img_scale, ratio_range=(0.5, 2.0)),
|
| 14 |
+
dict(type='RandomCrop', crop_size=crop_size, cat_max_ratio=0.75),
|
| 15 |
+
dict(type='RandomFlip', prob=0.5),
|
| 16 |
+
dict(type='PhotoMetricDistortion'),
|
| 17 |
+
dict(type='Normalize', **img_norm_cfg),
|
| 18 |
+
dict(type='Pad', size=crop_size, pad_val=0, seg_pad_val=255),
|
| 19 |
+
dict(type='DefaultFormatBundle'),
|
| 20 |
+
dict(type='Collect', keys=['img', 'gt_semantic_seg']),
|
| 21 |
+
]
|
| 22 |
+
test_pipeline = [
|
| 23 |
+
dict(type='LoadImageFromFile'),
|
| 24 |
+
dict(
|
| 25 |
+
type='MultiScaleFlipAug',
|
| 26 |
+
img_scale=img_scale,
|
| 27 |
+
# img_ratios=[0.5, 0.75, 1.0, 1.25, 1.5, 1.75],
|
| 28 |
+
flip=False,
|
| 29 |
+
transforms=[
|
| 30 |
+
dict(type='Resize', keep_ratio=True),
|
| 31 |
+
dict(type='RandomFlip'),
|
| 32 |
+
dict(type='Normalize', **img_norm_cfg),
|
| 33 |
+
dict(type='ImageToTensor', keys=['img']),
|
| 34 |
+
dict(type='Collect', keys=['img']),
|
| 35 |
+
])
|
| 36 |
+
]
|
| 37 |
+
data = dict(
|
| 38 |
+
samples_per_gpu=4,
|
| 39 |
+
workers_per_gpu=4,
|
| 40 |
+
train=dict(
|
| 41 |
+
type=dataset_type,
|
| 42 |
+
data_root=data_root,
|
| 43 |
+
img_dir='JPEGImages',
|
| 44 |
+
ann_dir='SegmentationClassContext',
|
| 45 |
+
split='ImageSets/SegmentationContext/train.txt',
|
| 46 |
+
pipeline=train_pipeline),
|
| 47 |
+
val=dict(
|
| 48 |
+
type=dataset_type,
|
| 49 |
+
data_root=data_root,
|
| 50 |
+
img_dir='JPEGImages',
|
| 51 |
+
ann_dir='SegmentationClassContext',
|
| 52 |
+
split='ImageSets/SegmentationContext/val.txt',
|
| 53 |
+
pipeline=test_pipeline),
|
| 54 |
+
test=dict(
|
| 55 |
+
type=dataset_type,
|
| 56 |
+
data_root=data_root,
|
| 57 |
+
img_dir='JPEGImages',
|
| 58 |
+
ann_dir='SegmentationClassContext',
|
| 59 |
+
split='ImageSets/SegmentationContext/val.txt',
|
| 60 |
+
pipeline=test_pipeline))
|
configs/_base_/datasets/pascal_context_59.py
ADDED
|
@@ -0,0 +1,60 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
# dataset settings
|
| 2 |
+
dataset_type = 'PascalContextDataset59'
|
| 3 |
+
data_root = 'data/VOCdevkit/VOC2010/'
|
| 4 |
+
img_norm_cfg = dict(
|
| 5 |
+
mean=[123.675, 116.28, 103.53], std=[58.395, 57.12, 57.375], to_rgb=True)
|
| 6 |
+
|
| 7 |
+
img_scale = (520, 520)
|
| 8 |
+
crop_size = (480, 480)
|
| 9 |
+
|
| 10 |
+
train_pipeline = [
|
| 11 |
+
dict(type='LoadImageFromFile'),
|
| 12 |
+
dict(type='LoadAnnotations', reduce_zero_label=True),
|
| 13 |
+
dict(type='Resize', img_scale=img_scale, ratio_range=(0.5, 2.0)),
|
| 14 |
+
dict(type='RandomCrop', crop_size=crop_size, cat_max_ratio=0.75),
|
| 15 |
+
dict(type='RandomFlip', prob=0.5),
|
| 16 |
+
dict(type='PhotoMetricDistortion'),
|
| 17 |
+
dict(type='Normalize', **img_norm_cfg),
|
| 18 |
+
dict(type='Pad', size=crop_size, pad_val=0, seg_pad_val=255),
|
| 19 |
+
dict(type='DefaultFormatBundle'),
|
| 20 |
+
dict(type='Collect', keys=['img', 'gt_semantic_seg']),
|
| 21 |
+
]
|
| 22 |
+
test_pipeline = [
|
| 23 |
+
dict(type='LoadImageFromFile'),
|
| 24 |
+
dict(
|
| 25 |
+
type='MultiScaleFlipAug',
|
| 26 |
+
img_scale=img_scale,
|
| 27 |
+
# img_ratios=[0.5, 0.75, 1.0, 1.25, 1.5, 1.75],
|
| 28 |
+
flip=False,
|
| 29 |
+
transforms=[
|
| 30 |
+
dict(type='Resize', keep_ratio=True),
|
| 31 |
+
dict(type='RandomFlip'),
|
| 32 |
+
dict(type='Normalize', **img_norm_cfg),
|
| 33 |
+
dict(type='ImageToTensor', keys=['img']),
|
| 34 |
+
dict(type='Collect', keys=['img']),
|
| 35 |
+
])
|
| 36 |
+
]
|
| 37 |
+
data = dict(
|
| 38 |
+
samples_per_gpu=4,
|
| 39 |
+
workers_per_gpu=4,
|
| 40 |
+
train=dict(
|
| 41 |
+
type=dataset_type,
|
| 42 |
+
data_root=data_root,
|
| 43 |
+
img_dir='JPEGImages',
|
| 44 |
+
ann_dir='SegmentationClassContext',
|
| 45 |
+
split='ImageSets/SegmentationContext/train.txt',
|
| 46 |
+
pipeline=train_pipeline),
|
| 47 |
+
val=dict(
|
| 48 |
+
type=dataset_type,
|
| 49 |
+
data_root=data_root,
|
| 50 |
+
img_dir='JPEGImages',
|
| 51 |
+
ann_dir='SegmentationClassContext',
|
| 52 |
+
split='ImageSets/SegmentationContext/val.txt',
|
| 53 |
+
pipeline=test_pipeline),
|
| 54 |
+
test=dict(
|
| 55 |
+
type=dataset_type,
|
| 56 |
+
data_root=data_root,
|
| 57 |
+
img_dir='JPEGImages',
|
| 58 |
+
ann_dir='SegmentationClassContext',
|
| 59 |
+
split='ImageSets/SegmentationContext/val.txt',
|
| 60 |
+
pipeline=test_pipeline))
|
configs/_base_/datasets/pascal_voc12.py
ADDED
|
@@ -0,0 +1,57 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
# dataset settings
|
| 2 |
+
dataset_type = 'PascalVOCDataset'
|
| 3 |
+
data_root = 'data/VOCdevkit/VOC2012'
|
| 4 |
+
img_norm_cfg = dict(
|
| 5 |
+
mean=[123.675, 116.28, 103.53], std=[58.395, 57.12, 57.375], to_rgb=True)
|
| 6 |
+
crop_size = (512, 512)
|
| 7 |
+
train_pipeline = [
|
| 8 |
+
dict(type='LoadImageFromFile'),
|
| 9 |
+
dict(type='LoadAnnotations'),
|
| 10 |
+
dict(type='Resize', img_scale=(2048, 512), ratio_range=(0.5, 2.0)),
|
| 11 |
+
dict(type='RandomCrop', crop_size=crop_size, cat_max_ratio=0.75),
|
| 12 |
+
dict(type='RandomFlip', prob=0.5),
|
| 13 |
+
dict(type='PhotoMetricDistortion'),
|
| 14 |
+
dict(type='Normalize', **img_norm_cfg),
|
| 15 |
+
dict(type='Pad', size=crop_size, pad_val=0, seg_pad_val=255),
|
| 16 |
+
dict(type='DefaultFormatBundle'),
|
| 17 |
+
dict(type='Collect', keys=['img', 'gt_semantic_seg']),
|
| 18 |
+
]
|
| 19 |
+
test_pipeline = [
|
| 20 |
+
dict(type='LoadImageFromFile'),
|
| 21 |
+
dict(
|
| 22 |
+
type='MultiScaleFlipAug',
|
| 23 |
+
img_scale=(2048, 512),
|
| 24 |
+
# img_ratios=[0.5, 0.75, 1.0, 1.25, 1.5, 1.75],
|
| 25 |
+
flip=False,
|
| 26 |
+
transforms=[
|
| 27 |
+
dict(type='Resize', keep_ratio=True),
|
| 28 |
+
dict(type='RandomFlip'),
|
| 29 |
+
dict(type='Normalize', **img_norm_cfg),
|
| 30 |
+
dict(type='ImageToTensor', keys=['img']),
|
| 31 |
+
dict(type='Collect', keys=['img']),
|
| 32 |
+
])
|
| 33 |
+
]
|
| 34 |
+
data = dict(
|
| 35 |
+
samples_per_gpu=4,
|
| 36 |
+
workers_per_gpu=4,
|
| 37 |
+
train=dict(
|
| 38 |
+
type=dataset_type,
|
| 39 |
+
data_root=data_root,
|
| 40 |
+
img_dir='JPEGImages',
|
| 41 |
+
ann_dir='SegmentationClass',
|
| 42 |
+
split='ImageSets/Segmentation/train.txt',
|
| 43 |
+
pipeline=train_pipeline),
|
| 44 |
+
val=dict(
|
| 45 |
+
type=dataset_type,
|
| 46 |
+
data_root=data_root,
|
| 47 |
+
img_dir='JPEGImages',
|
| 48 |
+
ann_dir='SegmentationClass',
|
| 49 |
+
split='ImageSets/Segmentation/val.txt',
|
| 50 |
+
pipeline=test_pipeline),
|
| 51 |
+
test=dict(
|
| 52 |
+
type=dataset_type,
|
| 53 |
+
data_root=data_root,
|
| 54 |
+
img_dir='JPEGImages',
|
| 55 |
+
ann_dir='SegmentationClass',
|
| 56 |
+
split='ImageSets/Segmentation/val.txt',
|
| 57 |
+
pipeline=test_pipeline))
|
configs/_base_/datasets/pascal_voc12_aug.py
ADDED
|
@@ -0,0 +1,9 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
_base_ = './pascal_voc12.py'
|
| 2 |
+
# dataset settings
|
| 3 |
+
data = dict(
|
| 4 |
+
train=dict(
|
| 5 |
+
ann_dir=['SegmentationClass', 'SegmentationClassAug'],
|
| 6 |
+
split=[
|
| 7 |
+
'ImageSets/Segmentation/train.txt',
|
| 8 |
+
'ImageSets/Segmentation/aug.txt'
|
| 9 |
+
]))
|
configs/_base_/datasets/stare.py
ADDED
|
@@ -0,0 +1,59 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
# dataset settings
|
| 2 |
+
dataset_type = 'STAREDataset'
|
| 3 |
+
data_root = 'data/STARE'
|
| 4 |
+
img_norm_cfg = dict(
|
| 5 |
+
mean=[123.675, 116.28, 103.53], std=[58.395, 57.12, 57.375], to_rgb=True)
|
| 6 |
+
img_scale = (605, 700)
|
| 7 |
+
crop_size = (128, 128)
|
| 8 |
+
train_pipeline = [
|
| 9 |
+
dict(type='LoadImageFromFile'),
|
| 10 |
+
dict(type='LoadAnnotations'),
|
| 11 |
+
dict(type='Resize', img_scale=img_scale, ratio_range=(0.5, 2.0)),
|
| 12 |
+
dict(type='RandomCrop', crop_size=crop_size, cat_max_ratio=0.75),
|
| 13 |
+
dict(type='RandomFlip', prob=0.5),
|
| 14 |
+
dict(type='PhotoMetricDistortion'),
|
| 15 |
+
dict(type='Normalize', **img_norm_cfg),
|
| 16 |
+
dict(type='Pad', size=crop_size, pad_val=0, seg_pad_val=255),
|
| 17 |
+
dict(type='DefaultFormatBundle'),
|
| 18 |
+
dict(type='Collect', keys=['img', 'gt_semantic_seg'])
|
| 19 |
+
]
|
| 20 |
+
test_pipeline = [
|
| 21 |
+
dict(type='LoadImageFromFile'),
|
| 22 |
+
dict(
|
| 23 |
+
type='MultiScaleFlipAug',
|
| 24 |
+
img_scale=img_scale,
|
| 25 |
+
# img_ratios=[0.5, 0.75, 1.0, 1.25, 1.5, 1.75, 2.0],
|
| 26 |
+
flip=False,
|
| 27 |
+
transforms=[
|
| 28 |
+
dict(type='Resize', keep_ratio=True),
|
| 29 |
+
dict(type='RandomFlip'),
|
| 30 |
+
dict(type='Normalize', **img_norm_cfg),
|
| 31 |
+
dict(type='ImageToTensor', keys=['img']),
|
| 32 |
+
dict(type='Collect', keys=['img'])
|
| 33 |
+
])
|
| 34 |
+
]
|
| 35 |
+
|
| 36 |
+
data = dict(
|
| 37 |
+
samples_per_gpu=4,
|
| 38 |
+
workers_per_gpu=4,
|
| 39 |
+
train=dict(
|
| 40 |
+
type='RepeatDataset',
|
| 41 |
+
times=40000,
|
| 42 |
+
dataset=dict(
|
| 43 |
+
type=dataset_type,
|
| 44 |
+
data_root=data_root,
|
| 45 |
+
img_dir='images/training',
|
| 46 |
+
ann_dir='annotations/training',
|
| 47 |
+
pipeline=train_pipeline)),
|
| 48 |
+
val=dict(
|
| 49 |
+
type=dataset_type,
|
| 50 |
+
data_root=data_root,
|
| 51 |
+
img_dir='images/validation',
|
| 52 |
+
ann_dir='annotations/validation',
|
| 53 |
+
pipeline=test_pipeline),
|
| 54 |
+
test=dict(
|
| 55 |
+
type=dataset_type,
|
| 56 |
+
data_root=data_root,
|
| 57 |
+
img_dir='images/validation',
|
| 58 |
+
ann_dir='annotations/validation',
|
| 59 |
+
pipeline=test_pipeline))
|
configs/_base_/default_runtime.py
ADDED
|
@@ -0,0 +1,14 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
# yapf:disable
|
| 2 |
+
log_config = dict(
|
| 3 |
+
interval=50,
|
| 4 |
+
hooks=[
|
| 5 |
+
dict(type='TextLoggerHook', by_epoch=False),
|
| 6 |
+
# dict(type='TensorboardLoggerHook')
|
| 7 |
+
])
|
| 8 |
+
# yapf:enable
|
| 9 |
+
dist_params = dict(backend='nccl')
|
| 10 |
+
log_level = 'INFO'
|
| 11 |
+
load_from = None
|
| 12 |
+
resume_from = None
|
| 13 |
+
workflow = [('train', 1)]
|
| 14 |
+
cudnn_benchmark = True
|
configs/_base_/models/ann_r50-d8.py
ADDED
|
@@ -0,0 +1,46 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
# model settings
|
| 2 |
+
norm_cfg = dict(type='SyncBN', requires_grad=True)
|
| 3 |
+
model = dict(
|
| 4 |
+
type='EncoderDecoder',
|
| 5 |
+
pretrained='open-mmlab://resnet50_v1c',
|
| 6 |
+
backbone=dict(
|
| 7 |
+
type='ResNetV1c',
|
| 8 |
+
depth=50,
|
| 9 |
+
num_stages=4,
|
| 10 |
+
out_indices=(0, 1, 2, 3),
|
| 11 |
+
dilations=(1, 1, 2, 4),
|
| 12 |
+
strides=(1, 2, 1, 1),
|
| 13 |
+
norm_cfg=norm_cfg,
|
| 14 |
+
norm_eval=False,
|
| 15 |
+
style='pytorch',
|
| 16 |
+
contract_dilation=True),
|
| 17 |
+
decode_head=dict(
|
| 18 |
+
type='ANNHead',
|
| 19 |
+
in_channels=[1024, 2048],
|
| 20 |
+
in_index=[2, 3],
|
| 21 |
+
channels=512,
|
| 22 |
+
project_channels=256,
|
| 23 |
+
query_scales=(1, ),
|
| 24 |
+
key_pool_scales=(1, 3, 6, 8),
|
| 25 |
+
dropout_ratio=0.1,
|
| 26 |
+
num_classes=19,
|
| 27 |
+
norm_cfg=norm_cfg,
|
| 28 |
+
align_corners=False,
|
| 29 |
+
loss_decode=dict(
|
| 30 |
+
type='CrossEntropyLoss', use_sigmoid=False, loss_weight=1.0)),
|
| 31 |
+
auxiliary_head=dict(
|
| 32 |
+
type='FCNHead',
|
| 33 |
+
in_channels=1024,
|
| 34 |
+
in_index=2,
|
| 35 |
+
channels=256,
|
| 36 |
+
num_convs=1,
|
| 37 |
+
concat_input=False,
|
| 38 |
+
dropout_ratio=0.1,
|
| 39 |
+
num_classes=19,
|
| 40 |
+
norm_cfg=norm_cfg,
|
| 41 |
+
align_corners=False,
|
| 42 |
+
loss_decode=dict(
|
| 43 |
+
type='CrossEntropyLoss', use_sigmoid=False, loss_weight=0.4)),
|
| 44 |
+
# model training and testing settings
|
| 45 |
+
train_cfg=dict(),
|
| 46 |
+
test_cfg=dict(mode='whole'))
|
configs/_base_/models/apcnet_r50-d8.py
ADDED
|
@@ -0,0 +1,44 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
# model settings
|
| 2 |
+
norm_cfg = dict(type='SyncBN', requires_grad=True)
|
| 3 |
+
model = dict(
|
| 4 |
+
type='EncoderDecoder',
|
| 5 |
+
pretrained='open-mmlab://resnet50_v1c',
|
| 6 |
+
backbone=dict(
|
| 7 |
+
type='ResNetV1c',
|
| 8 |
+
depth=50,
|
| 9 |
+
num_stages=4,
|
| 10 |
+
out_indices=(0, 1, 2, 3),
|
| 11 |
+
dilations=(1, 1, 2, 4),
|
| 12 |
+
strides=(1, 2, 1, 1),
|
| 13 |
+
norm_cfg=norm_cfg,
|
| 14 |
+
norm_eval=False,
|
| 15 |
+
style='pytorch',
|
| 16 |
+
contract_dilation=True),
|
| 17 |
+
decode_head=dict(
|
| 18 |
+
type='APCHead',
|
| 19 |
+
in_channels=2048,
|
| 20 |
+
in_index=3,
|
| 21 |
+
channels=512,
|
| 22 |
+
pool_scales=(1, 2, 3, 6),
|
| 23 |
+
dropout_ratio=0.1,
|
| 24 |
+
num_classes=19,
|
| 25 |
+
norm_cfg=dict(type='SyncBN', requires_grad=True),
|
| 26 |
+
align_corners=False,
|
| 27 |
+
loss_decode=dict(
|
| 28 |
+
type='CrossEntropyLoss', use_sigmoid=False, loss_weight=1.0)),
|
| 29 |
+
auxiliary_head=dict(
|
| 30 |
+
type='FCNHead',
|
| 31 |
+
in_channels=1024,
|
| 32 |
+
in_index=2,
|
| 33 |
+
channels=256,
|
| 34 |
+
num_convs=1,
|
| 35 |
+
concat_input=False,
|
| 36 |
+
dropout_ratio=0.1,
|
| 37 |
+
num_classes=19,
|
| 38 |
+
norm_cfg=norm_cfg,
|
| 39 |
+
align_corners=False,
|
| 40 |
+
loss_decode=dict(
|
| 41 |
+
type='CrossEntropyLoss', use_sigmoid=False, loss_weight=0.4)),
|
| 42 |
+
# model training and testing settings
|
| 43 |
+
train_cfg=dict(),
|
| 44 |
+
test_cfg=dict(mode='whole'))
|
configs/_base_/models/ccnet_r50-d8.py
ADDED
|
@@ -0,0 +1,44 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
# model settings
|
| 2 |
+
norm_cfg = dict(type='SyncBN', requires_grad=True)
|
| 3 |
+
model = dict(
|
| 4 |
+
type='EncoderDecoder',
|
| 5 |
+
pretrained='open-mmlab://resnet50_v1c',
|
| 6 |
+
backbone=dict(
|
| 7 |
+
type='ResNetV1c',
|
| 8 |
+
depth=50,
|
| 9 |
+
num_stages=4,
|
| 10 |
+
out_indices=(0, 1, 2, 3),
|
| 11 |
+
dilations=(1, 1, 2, 4),
|
| 12 |
+
strides=(1, 2, 1, 1),
|
| 13 |
+
norm_cfg=norm_cfg,
|
| 14 |
+
norm_eval=False,
|
| 15 |
+
style='pytorch',
|
| 16 |
+
contract_dilation=True),
|
| 17 |
+
decode_head=dict(
|
| 18 |
+
type='CCHead',
|
| 19 |
+
in_channels=2048,
|
| 20 |
+
in_index=3,
|
| 21 |
+
channels=512,
|
| 22 |
+
recurrence=2,
|
| 23 |
+
dropout_ratio=0.1,
|
| 24 |
+
num_classes=19,
|
| 25 |
+
norm_cfg=norm_cfg,
|
| 26 |
+
align_corners=False,
|
| 27 |
+
loss_decode=dict(
|
| 28 |
+
type='CrossEntropyLoss', use_sigmoid=False, loss_weight=1.0)),
|
| 29 |
+
auxiliary_head=dict(
|
| 30 |
+
type='FCNHead',
|
| 31 |
+
in_channels=1024,
|
| 32 |
+
in_index=2,
|
| 33 |
+
channels=256,
|
| 34 |
+
num_convs=1,
|
| 35 |
+
concat_input=False,
|
| 36 |
+
dropout_ratio=0.1,
|
| 37 |
+
num_classes=19,
|
| 38 |
+
norm_cfg=norm_cfg,
|
| 39 |
+
align_corners=False,
|
| 40 |
+
loss_decode=dict(
|
| 41 |
+
type='CrossEntropyLoss', use_sigmoid=False, loss_weight=0.4)),
|
| 42 |
+
# model training and testing settings
|
| 43 |
+
train_cfg=dict(),
|
| 44 |
+
test_cfg=dict(mode='whole'))
|
configs/_base_/models/cgnet.py
ADDED
|
@@ -0,0 +1,35 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
# model settings
|
| 2 |
+
norm_cfg = dict(type='SyncBN', eps=1e-03, requires_grad=True)
|
| 3 |
+
model = dict(
|
| 4 |
+
type='EncoderDecoder',
|
| 5 |
+
backbone=dict(
|
| 6 |
+
type='CGNet',
|
| 7 |
+
norm_cfg=norm_cfg,
|
| 8 |
+
in_channels=3,
|
| 9 |
+
num_channels=(32, 64, 128),
|
| 10 |
+
num_blocks=(3, 21),
|
| 11 |
+
dilations=(2, 4),
|
| 12 |
+
reductions=(8, 16)),
|
| 13 |
+
decode_head=dict(
|
| 14 |
+
type='FCNHead',
|
| 15 |
+
in_channels=256,
|
| 16 |
+
in_index=2,
|
| 17 |
+
channels=256,
|
| 18 |
+
num_convs=0,
|
| 19 |
+
concat_input=False,
|
| 20 |
+
dropout_ratio=0,
|
| 21 |
+
num_classes=19,
|
| 22 |
+
norm_cfg=norm_cfg,
|
| 23 |
+
loss_decode=dict(
|
| 24 |
+
type='CrossEntropyLoss',
|
| 25 |
+
use_sigmoid=False,
|
| 26 |
+
loss_weight=1.0,
|
| 27 |
+
class_weight=[
|
| 28 |
+
2.5959933, 6.7415504, 3.5354059, 9.8663225, 9.690899, 9.369352,
|
| 29 |
+
10.289121, 9.953208, 4.3097677, 9.490387, 7.674431, 9.396905,
|
| 30 |
+
10.347791, 6.3927646, 10.226669, 10.241062, 10.280587,
|
| 31 |
+
10.396974, 10.055647
|
| 32 |
+
])),
|
| 33 |
+
# model training and testing settings
|
| 34 |
+
train_cfg=dict(sampler=None),
|
| 35 |
+
test_cfg=dict(mode='whole'))
|
configs/_base_/models/danet_r50-d8.py
ADDED
|
@@ -0,0 +1,44 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
# model settings
|
| 2 |
+
norm_cfg = dict(type='SyncBN', requires_grad=True)
|
| 3 |
+
model = dict(
|
| 4 |
+
type='EncoderDecoder',
|
| 5 |
+
pretrained='open-mmlab://resnet50_v1c',
|
| 6 |
+
backbone=dict(
|
| 7 |
+
type='ResNetV1c',
|
| 8 |
+
depth=50,
|
| 9 |
+
num_stages=4,
|
| 10 |
+
out_indices=(0, 1, 2, 3),
|
| 11 |
+
dilations=(1, 1, 2, 4),
|
| 12 |
+
strides=(1, 2, 1, 1),
|
| 13 |
+
norm_cfg=norm_cfg,
|
| 14 |
+
norm_eval=False,
|
| 15 |
+
style='pytorch',
|
| 16 |
+
contract_dilation=True),
|
| 17 |
+
decode_head=dict(
|
| 18 |
+
type='DAHead',
|
| 19 |
+
in_channels=2048,
|
| 20 |
+
in_index=3,
|
| 21 |
+
channels=512,
|
| 22 |
+
pam_channels=64,
|
| 23 |
+
dropout_ratio=0.1,
|
| 24 |
+
num_classes=19,
|
| 25 |
+
norm_cfg=norm_cfg,
|
| 26 |
+
align_corners=False,
|
| 27 |
+
loss_decode=dict(
|
| 28 |
+
type='CrossEntropyLoss', use_sigmoid=False, loss_weight=1.0)),
|
| 29 |
+
auxiliary_head=dict(
|
| 30 |
+
type='FCNHead',
|
| 31 |
+
in_channels=1024,
|
| 32 |
+
in_index=2,
|
| 33 |
+
channels=256,
|
| 34 |
+
num_convs=1,
|
| 35 |
+
concat_input=False,
|
| 36 |
+
dropout_ratio=0.1,
|
| 37 |
+
num_classes=19,
|
| 38 |
+
norm_cfg=norm_cfg,
|
| 39 |
+
align_corners=False,
|
| 40 |
+
loss_decode=dict(
|
| 41 |
+
type='CrossEntropyLoss', use_sigmoid=False, loss_weight=0.4)),
|
| 42 |
+
# model training and testing settings
|
| 43 |
+
train_cfg=dict(),
|
| 44 |
+
test_cfg=dict(mode='whole'))
|
configs/_base_/models/deeplabv3_r50-d8.py
ADDED
|
@@ -0,0 +1,44 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
# model settings
|
| 2 |
+
norm_cfg = dict(type='SyncBN', requires_grad=True)
|
| 3 |
+
model = dict(
|
| 4 |
+
type='EncoderDecoder',
|
| 5 |
+
pretrained='open-mmlab://resnet50_v1c',
|
| 6 |
+
backbone=dict(
|
| 7 |
+
type='ResNetV1c',
|
| 8 |
+
depth=50,
|
| 9 |
+
num_stages=4,
|
| 10 |
+
out_indices=(0, 1, 2, 3),
|
| 11 |
+
dilations=(1, 1, 2, 4),
|
| 12 |
+
strides=(1, 2, 1, 1),
|
| 13 |
+
norm_cfg=norm_cfg,
|
| 14 |
+
norm_eval=False,
|
| 15 |
+
style='pytorch',
|
| 16 |
+
contract_dilation=True),
|
| 17 |
+
decode_head=dict(
|
| 18 |
+
type='ASPPHead',
|
| 19 |
+
in_channels=2048,
|
| 20 |
+
in_index=3,
|
| 21 |
+
channels=512,
|
| 22 |
+
dilations=(1, 12, 24, 36),
|
| 23 |
+
dropout_ratio=0.1,
|
| 24 |
+
num_classes=19,
|
| 25 |
+
norm_cfg=norm_cfg,
|
| 26 |
+
align_corners=False,
|
| 27 |
+
loss_decode=dict(
|
| 28 |
+
type='CrossEntropyLoss', use_sigmoid=False, loss_weight=1.0)),
|
| 29 |
+
auxiliary_head=dict(
|
| 30 |
+
type='FCNHead',
|
| 31 |
+
in_channels=1024,
|
| 32 |
+
in_index=2,
|
| 33 |
+
channels=256,
|
| 34 |
+
num_convs=1,
|
| 35 |
+
concat_input=False,
|
| 36 |
+
dropout_ratio=0.1,
|
| 37 |
+
num_classes=19,
|
| 38 |
+
norm_cfg=norm_cfg,
|
| 39 |
+
align_corners=False,
|
| 40 |
+
loss_decode=dict(
|
| 41 |
+
type='CrossEntropyLoss', use_sigmoid=False, loss_weight=0.4)),
|
| 42 |
+
# model training and testing settings
|
| 43 |
+
train_cfg=dict(),
|
| 44 |
+
test_cfg=dict(mode='whole'))
|
configs/_base_/models/deeplabv3_unet_s5-d16.py
ADDED
|
@@ -0,0 +1,50 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
# model settings
|
| 2 |
+
norm_cfg = dict(type='SyncBN', requires_grad=True)
|
| 3 |
+
model = dict(
|
| 4 |
+
type='EncoderDecoder',
|
| 5 |
+
pretrained=None,
|
| 6 |
+
backbone=dict(
|
| 7 |
+
type='UNet',
|
| 8 |
+
in_channels=3,
|
| 9 |
+
base_channels=64,
|
| 10 |
+
num_stages=5,
|
| 11 |
+
strides=(1, 1, 1, 1, 1),
|
| 12 |
+
enc_num_convs=(2, 2, 2, 2, 2),
|
| 13 |
+
dec_num_convs=(2, 2, 2, 2),
|
| 14 |
+
downsamples=(True, True, True, True),
|
| 15 |
+
enc_dilations=(1, 1, 1, 1, 1),
|
| 16 |
+
dec_dilations=(1, 1, 1, 1),
|
| 17 |
+
with_cp=False,
|
| 18 |
+
conv_cfg=None,
|
| 19 |
+
norm_cfg=norm_cfg,
|
| 20 |
+
act_cfg=dict(type='ReLU'),
|
| 21 |
+
upsample_cfg=dict(type='InterpConv'),
|
| 22 |
+
norm_eval=False),
|
| 23 |
+
decode_head=dict(
|
| 24 |
+
type='ASPPHead',
|
| 25 |
+
in_channels=64,
|
| 26 |
+
in_index=4,
|
| 27 |
+
channels=16,
|
| 28 |
+
dilations=(1, 12, 24, 36),
|
| 29 |
+
dropout_ratio=0.1,
|
| 30 |
+
num_classes=2,
|
| 31 |
+
norm_cfg=norm_cfg,
|
| 32 |
+
align_corners=False,
|
| 33 |
+
loss_decode=dict(
|
| 34 |
+
type='CrossEntropyLoss', use_sigmoid=False, loss_weight=1.0)),
|
| 35 |
+
auxiliary_head=dict(
|
| 36 |
+
type='FCNHead',
|
| 37 |
+
in_channels=128,
|
| 38 |
+
in_index=3,
|
| 39 |
+
channels=64,
|
| 40 |
+
num_convs=1,
|
| 41 |
+
concat_input=False,
|
| 42 |
+
dropout_ratio=0.1,
|
| 43 |
+
num_classes=2,
|
| 44 |
+
norm_cfg=norm_cfg,
|
| 45 |
+
align_corners=False,
|
| 46 |
+
loss_decode=dict(
|
| 47 |
+
type='CrossEntropyLoss', use_sigmoid=False, loss_weight=0.4)),
|
| 48 |
+
# model training and testing settings
|
| 49 |
+
train_cfg=dict(),
|
| 50 |
+
test_cfg=dict(mode='slide', crop_size=256, stride=170))
|
configs/_base_/models/deeplabv3plus_r50-d8.py
ADDED
|
@@ -0,0 +1,46 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
# model settings
|
| 2 |
+
norm_cfg = dict(type='SyncBN', requires_grad=True)
|
| 3 |
+
model = dict(
|
| 4 |
+
type='EncoderDecoder',
|
| 5 |
+
pretrained='open-mmlab://resnet50_v1c',
|
| 6 |
+
backbone=dict(
|
| 7 |
+
type='ResNetV1c',
|
| 8 |
+
depth=50,
|
| 9 |
+
num_stages=4,
|
| 10 |
+
out_indices=(0, 1, 2, 3),
|
| 11 |
+
dilations=(1, 1, 2, 4),
|
| 12 |
+
strides=(1, 2, 1, 1),
|
| 13 |
+
norm_cfg=norm_cfg,
|
| 14 |
+
norm_eval=False,
|
| 15 |
+
style='pytorch',
|
| 16 |
+
contract_dilation=True),
|
| 17 |
+
decode_head=dict(
|
| 18 |
+
type='DepthwiseSeparableASPPHead',
|
| 19 |
+
in_channels=2048,
|
| 20 |
+
in_index=3,
|
| 21 |
+
channels=512,
|
| 22 |
+
dilations=(1, 12, 24, 36),
|
| 23 |
+
c1_in_channels=256,
|
| 24 |
+
c1_channels=48,
|
| 25 |
+
dropout_ratio=0.1,
|
| 26 |
+
num_classes=19,
|
| 27 |
+
norm_cfg=norm_cfg,
|
| 28 |
+
align_corners=False,
|
| 29 |
+
loss_decode=dict(
|
| 30 |
+
type='CrossEntropyLoss', use_sigmoid=False, loss_weight=1.0)),
|
| 31 |
+
auxiliary_head=dict(
|
| 32 |
+
type='FCNHead',
|
| 33 |
+
in_channels=1024,
|
| 34 |
+
in_index=2,
|
| 35 |
+
channels=256,
|
| 36 |
+
num_convs=1,
|
| 37 |
+
concat_input=False,
|
| 38 |
+
dropout_ratio=0.1,
|
| 39 |
+
num_classes=19,
|
| 40 |
+
norm_cfg=norm_cfg,
|
| 41 |
+
align_corners=False,
|
| 42 |
+
loss_decode=dict(
|
| 43 |
+
type='CrossEntropyLoss', use_sigmoid=False, loss_weight=0.4)),
|
| 44 |
+
# model training and testing settings
|
| 45 |
+
train_cfg=dict(),
|
| 46 |
+
test_cfg=dict(mode='whole'))
|
configs/_base_/models/dmnet_r50-d8.py
ADDED
|
@@ -0,0 +1,44 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
# model settings
|
| 2 |
+
norm_cfg = dict(type='SyncBN', requires_grad=True)
|
| 3 |
+
model = dict(
|
| 4 |
+
type='EncoderDecoder',
|
| 5 |
+
pretrained='open-mmlab://resnet50_v1c',
|
| 6 |
+
backbone=dict(
|
| 7 |
+
type='ResNetV1c',
|
| 8 |
+
depth=50,
|
| 9 |
+
num_stages=4,
|
| 10 |
+
out_indices=(0, 1, 2, 3),
|
| 11 |
+
dilations=(1, 1, 2, 4),
|
| 12 |
+
strides=(1, 2, 1, 1),
|
| 13 |
+
norm_cfg=norm_cfg,
|
| 14 |
+
norm_eval=False,
|
| 15 |
+
style='pytorch',
|
| 16 |
+
contract_dilation=True),
|
| 17 |
+
decode_head=dict(
|
| 18 |
+
type='DMHead',
|
| 19 |
+
in_channels=2048,
|
| 20 |
+
in_index=3,
|
| 21 |
+
channels=512,
|
| 22 |
+
filter_sizes=(1, 3, 5, 7),
|
| 23 |
+
dropout_ratio=0.1,
|
| 24 |
+
num_classes=19,
|
| 25 |
+
norm_cfg=dict(type='SyncBN', requires_grad=True),
|
| 26 |
+
align_corners=False,
|
| 27 |
+
loss_decode=dict(
|
| 28 |
+
type='CrossEntropyLoss', use_sigmoid=False, loss_weight=1.0)),
|
| 29 |
+
auxiliary_head=dict(
|
| 30 |
+
type='FCNHead',
|
| 31 |
+
in_channels=1024,
|
| 32 |
+
in_index=2,
|
| 33 |
+
channels=256,
|
| 34 |
+
num_convs=1,
|
| 35 |
+
concat_input=False,
|
| 36 |
+
dropout_ratio=0.1,
|
| 37 |
+
num_classes=19,
|
| 38 |
+
norm_cfg=norm_cfg,
|
| 39 |
+
align_corners=False,
|
| 40 |
+
loss_decode=dict(
|
| 41 |
+
type='CrossEntropyLoss', use_sigmoid=False, loss_weight=0.4)),
|
| 42 |
+
# model training and testing settings
|
| 43 |
+
train_cfg=dict(),
|
| 44 |
+
test_cfg=dict(mode='whole'))
|
configs/_base_/models/dnl_r50-d8.py
ADDED
|
@@ -0,0 +1,46 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
# model settings
|
| 2 |
+
norm_cfg = dict(type='SyncBN', requires_grad=True)
|
| 3 |
+
model = dict(
|
| 4 |
+
type='EncoderDecoder',
|
| 5 |
+
pretrained='open-mmlab://resnet50_v1c',
|
| 6 |
+
backbone=dict(
|
| 7 |
+
type='ResNetV1c',
|
| 8 |
+
depth=50,
|
| 9 |
+
num_stages=4,
|
| 10 |
+
out_indices=(0, 1, 2, 3),
|
| 11 |
+
dilations=(1, 1, 2, 4),
|
| 12 |
+
strides=(1, 2, 1, 1),
|
| 13 |
+
norm_cfg=norm_cfg,
|
| 14 |
+
norm_eval=False,
|
| 15 |
+
style='pytorch',
|
| 16 |
+
contract_dilation=True),
|
| 17 |
+
decode_head=dict(
|
| 18 |
+
type='DNLHead',
|
| 19 |
+
in_channels=2048,
|
| 20 |
+
in_index=3,
|
| 21 |
+
channels=512,
|
| 22 |
+
dropout_ratio=0.1,
|
| 23 |
+
reduction=2,
|
| 24 |
+
use_scale=True,
|
| 25 |
+
mode='embedded_gaussian',
|
| 26 |
+
num_classes=19,
|
| 27 |
+
norm_cfg=norm_cfg,
|
| 28 |
+
align_corners=False,
|
| 29 |
+
loss_decode=dict(
|
| 30 |
+
type='CrossEntropyLoss', use_sigmoid=False, loss_weight=1.0)),
|
| 31 |
+
auxiliary_head=dict(
|
| 32 |
+
type='FCNHead',
|
| 33 |
+
in_channels=1024,
|
| 34 |
+
in_index=2,
|
| 35 |
+
channels=256,
|
| 36 |
+
num_convs=1,
|
| 37 |
+
concat_input=False,
|
| 38 |
+
dropout_ratio=0.1,
|
| 39 |
+
num_classes=19,
|
| 40 |
+
norm_cfg=norm_cfg,
|
| 41 |
+
align_corners=False,
|
| 42 |
+
loss_decode=dict(
|
| 43 |
+
type='CrossEntropyLoss', use_sigmoid=False, loss_weight=0.4)),
|
| 44 |
+
# model training and testing settings
|
| 45 |
+
train_cfg=dict(),
|
| 46 |
+
test_cfg=dict(mode='whole'))
|
configs/_base_/models/emanet_r50-d8.py
ADDED
|
@@ -0,0 +1,47 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
# model settings
|
| 2 |
+
norm_cfg = dict(type='SyncBN', requires_grad=True)
|
| 3 |
+
model = dict(
|
| 4 |
+
type='EncoderDecoder',
|
| 5 |
+
pretrained='open-mmlab://resnet50_v1c',
|
| 6 |
+
backbone=dict(
|
| 7 |
+
type='ResNetV1c',
|
| 8 |
+
depth=50,
|
| 9 |
+
num_stages=4,
|
| 10 |
+
out_indices=(0, 1, 2, 3),
|
| 11 |
+
dilations=(1, 1, 2, 4),
|
| 12 |
+
strides=(1, 2, 1, 1),
|
| 13 |
+
norm_cfg=norm_cfg,
|
| 14 |
+
norm_eval=False,
|
| 15 |
+
style='pytorch',
|
| 16 |
+
contract_dilation=True),
|
| 17 |
+
decode_head=dict(
|
| 18 |
+
type='EMAHead',
|
| 19 |
+
in_channels=2048,
|
| 20 |
+
in_index=3,
|
| 21 |
+
channels=256,
|
| 22 |
+
ema_channels=512,
|
| 23 |
+
num_bases=64,
|
| 24 |
+
num_stages=3,
|
| 25 |
+
momentum=0.1,
|
| 26 |
+
dropout_ratio=0.1,
|
| 27 |
+
num_classes=19,
|
| 28 |
+
norm_cfg=norm_cfg,
|
| 29 |
+
align_corners=False,
|
| 30 |
+
loss_decode=dict(
|
| 31 |
+
type='CrossEntropyLoss', use_sigmoid=False, loss_weight=1.0)),
|
| 32 |
+
auxiliary_head=dict(
|
| 33 |
+
type='FCNHead',
|
| 34 |
+
in_channels=1024,
|
| 35 |
+
in_index=2,
|
| 36 |
+
channels=256,
|
| 37 |
+
num_convs=1,
|
| 38 |
+
concat_input=False,
|
| 39 |
+
dropout_ratio=0.1,
|
| 40 |
+
num_classes=19,
|
| 41 |
+
norm_cfg=norm_cfg,
|
| 42 |
+
align_corners=False,
|
| 43 |
+
loss_decode=dict(
|
| 44 |
+
type='CrossEntropyLoss', use_sigmoid=False, loss_weight=0.4)),
|
| 45 |
+
# model training and testing settings
|
| 46 |
+
train_cfg=dict(),
|
| 47 |
+
test_cfg=dict(mode='whole'))
|
configs/_base_/models/encnet_r50-d8.py
ADDED
|
@@ -0,0 +1,48 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
# model settings
|
| 2 |
+
norm_cfg = dict(type='SyncBN', requires_grad=True)
|
| 3 |
+
model = dict(
|
| 4 |
+
type='EncoderDecoder',
|
| 5 |
+
pretrained='open-mmlab://resnet50_v1c',
|
| 6 |
+
backbone=dict(
|
| 7 |
+
type='ResNetV1c',
|
| 8 |
+
depth=50,
|
| 9 |
+
num_stages=4,
|
| 10 |
+
out_indices=(0, 1, 2, 3),
|
| 11 |
+
dilations=(1, 1, 2, 4),
|
| 12 |
+
strides=(1, 2, 1, 1),
|
| 13 |
+
norm_cfg=norm_cfg,
|
| 14 |
+
norm_eval=False,
|
| 15 |
+
style='pytorch',
|
| 16 |
+
contract_dilation=True),
|
| 17 |
+
decode_head=dict(
|
| 18 |
+
type='EncHead',
|
| 19 |
+
in_channels=[512, 1024, 2048],
|
| 20 |
+
in_index=(1, 2, 3),
|
| 21 |
+
channels=512,
|
| 22 |
+
num_codes=32,
|
| 23 |
+
use_se_loss=True,
|
| 24 |
+
add_lateral=False,
|
| 25 |
+
dropout_ratio=0.1,
|
| 26 |
+
num_classes=19,
|
| 27 |
+
norm_cfg=norm_cfg,
|
| 28 |
+
align_corners=False,
|
| 29 |
+
loss_decode=dict(
|
| 30 |
+
type='CrossEntropyLoss', use_sigmoid=False, loss_weight=1.0),
|
| 31 |
+
loss_se_decode=dict(
|
| 32 |
+
type='CrossEntropyLoss', use_sigmoid=True, loss_weight=0.2)),
|
| 33 |
+
auxiliary_head=dict(
|
| 34 |
+
type='FCNHead',
|
| 35 |
+
in_channels=1024,
|
| 36 |
+
in_index=2,
|
| 37 |
+
channels=256,
|
| 38 |
+
num_convs=1,
|
| 39 |
+
concat_input=False,
|
| 40 |
+
dropout_ratio=0.1,
|
| 41 |
+
num_classes=19,
|
| 42 |
+
norm_cfg=norm_cfg,
|
| 43 |
+
align_corners=False,
|
| 44 |
+
loss_decode=dict(
|
| 45 |
+
type='CrossEntropyLoss', use_sigmoid=False, loss_weight=0.4)),
|
| 46 |
+
# model training and testing settings
|
| 47 |
+
train_cfg=dict(),
|
| 48 |
+
test_cfg=dict(mode='whole'))
|
configs/_base_/models/fast_scnn.py
ADDED
|
@@ -0,0 +1,57 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
# model settings
|
| 2 |
+
norm_cfg = dict(type='SyncBN', requires_grad=True, momentum=0.01)
|
| 3 |
+
model = dict(
|
| 4 |
+
type='EncoderDecoder',
|
| 5 |
+
backbone=dict(
|
| 6 |
+
type='FastSCNN',
|
| 7 |
+
downsample_dw_channels=(32, 48),
|
| 8 |
+
global_in_channels=64,
|
| 9 |
+
global_block_channels=(64, 96, 128),
|
| 10 |
+
global_block_strides=(2, 2, 1),
|
| 11 |
+
global_out_channels=128,
|
| 12 |
+
higher_in_channels=64,
|
| 13 |
+
lower_in_channels=128,
|
| 14 |
+
fusion_out_channels=128,
|
| 15 |
+
out_indices=(0, 1, 2),
|
| 16 |
+
norm_cfg=norm_cfg,
|
| 17 |
+
align_corners=False),
|
| 18 |
+
decode_head=dict(
|
| 19 |
+
type='DepthwiseSeparableFCNHead',
|
| 20 |
+
in_channels=128,
|
| 21 |
+
channels=128,
|
| 22 |
+
concat_input=False,
|
| 23 |
+
num_classes=19,
|
| 24 |
+
in_index=-1,
|
| 25 |
+
norm_cfg=norm_cfg,
|
| 26 |
+
align_corners=False,
|
| 27 |
+
loss_decode=dict(
|
| 28 |
+
type='CrossEntropyLoss', use_sigmoid=True, loss_weight=0.4)),
|
| 29 |
+
auxiliary_head=[
|
| 30 |
+
dict(
|
| 31 |
+
type='FCNHead',
|
| 32 |
+
in_channels=128,
|
| 33 |
+
channels=32,
|
| 34 |
+
num_convs=1,
|
| 35 |
+
num_classes=19,
|
| 36 |
+
in_index=-2,
|
| 37 |
+
norm_cfg=norm_cfg,
|
| 38 |
+
concat_input=False,
|
| 39 |
+
align_corners=False,
|
| 40 |
+
loss_decode=dict(
|
| 41 |
+
type='CrossEntropyLoss', use_sigmoid=True, loss_weight=0.4)),
|
| 42 |
+
dict(
|
| 43 |
+
type='FCNHead',
|
| 44 |
+
in_channels=64,
|
| 45 |
+
channels=32,
|
| 46 |
+
num_convs=1,
|
| 47 |
+
num_classes=19,
|
| 48 |
+
in_index=-3,
|
| 49 |
+
norm_cfg=norm_cfg,
|
| 50 |
+
concat_input=False,
|
| 51 |
+
align_corners=False,
|
| 52 |
+
loss_decode=dict(
|
| 53 |
+
type='CrossEntropyLoss', use_sigmoid=True, loss_weight=0.4)),
|
| 54 |
+
],
|
| 55 |
+
# model training and testing settings
|
| 56 |
+
train_cfg=dict(),
|
| 57 |
+
test_cfg=dict(mode='whole'))
|
configs/_base_/models/fcn_hr18.py
ADDED
|
@@ -0,0 +1,52 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
# model settings
|
| 2 |
+
norm_cfg = dict(type='SyncBN', requires_grad=True)
|
| 3 |
+
model = dict(
|
| 4 |
+
type='EncoderDecoder',
|
| 5 |
+
pretrained='open-mmlab://msra/hrnetv2_w18',
|
| 6 |
+
backbone=dict(
|
| 7 |
+
type='HRNet',
|
| 8 |
+
norm_cfg=norm_cfg,
|
| 9 |
+
norm_eval=False,
|
| 10 |
+
extra=dict(
|
| 11 |
+
stage1=dict(
|
| 12 |
+
num_modules=1,
|
| 13 |
+
num_branches=1,
|
| 14 |
+
block='BOTTLENECK',
|
| 15 |
+
num_blocks=(4, ),
|
| 16 |
+
num_channels=(64, )),
|
| 17 |
+
stage2=dict(
|
| 18 |
+
num_modules=1,
|
| 19 |
+
num_branches=2,
|
| 20 |
+
block='BASIC',
|
| 21 |
+
num_blocks=(4, 4),
|
| 22 |
+
num_channels=(18, 36)),
|
| 23 |
+
stage3=dict(
|
| 24 |
+
num_modules=4,
|
| 25 |
+
num_branches=3,
|
| 26 |
+
block='BASIC',
|
| 27 |
+
num_blocks=(4, 4, 4),
|
| 28 |
+
num_channels=(18, 36, 72)),
|
| 29 |
+
stage4=dict(
|
| 30 |
+
num_modules=3,
|
| 31 |
+
num_branches=4,
|
| 32 |
+
block='BASIC',
|
| 33 |
+
num_blocks=(4, 4, 4, 4),
|
| 34 |
+
num_channels=(18, 36, 72, 144)))),
|
| 35 |
+
decode_head=dict(
|
| 36 |
+
type='FCNHead',
|
| 37 |
+
in_channels=[18, 36, 72, 144],
|
| 38 |
+
in_index=(0, 1, 2, 3),
|
| 39 |
+
channels=sum([18, 36, 72, 144]),
|
| 40 |
+
input_transform='resize_concat',
|
| 41 |
+
kernel_size=1,
|
| 42 |
+
num_convs=1,
|
| 43 |
+
concat_input=False,
|
| 44 |
+
dropout_ratio=-1,
|
| 45 |
+
num_classes=19,
|
| 46 |
+
norm_cfg=norm_cfg,
|
| 47 |
+
align_corners=False,
|
| 48 |
+
loss_decode=dict(
|
| 49 |
+
type='CrossEntropyLoss', use_sigmoid=False, loss_weight=1.0)),
|
| 50 |
+
# model training and testing settings
|
| 51 |
+
train_cfg=dict(),
|
| 52 |
+
test_cfg=dict(mode='whole'))
|
configs/_base_/models/fcn_r50-d8.py
ADDED
|
@@ -0,0 +1,45 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
# model settings
|
| 2 |
+
norm_cfg = dict(type='SyncBN', requires_grad=True)
|
| 3 |
+
model = dict(
|
| 4 |
+
type='EncoderDecoder',
|
| 5 |
+
pretrained='open-mmlab://resnet50_v1c',
|
| 6 |
+
backbone=dict(
|
| 7 |
+
type='ResNetV1c',
|
| 8 |
+
depth=50,
|
| 9 |
+
num_stages=4,
|
| 10 |
+
out_indices=(0, 1, 2, 3),
|
| 11 |
+
dilations=(1, 1, 2, 4),
|
| 12 |
+
strides=(1, 2, 1, 1),
|
| 13 |
+
norm_cfg=norm_cfg,
|
| 14 |
+
norm_eval=False,
|
| 15 |
+
style='pytorch',
|
| 16 |
+
contract_dilation=True),
|
| 17 |
+
decode_head=dict(
|
| 18 |
+
type='FCNHead',
|
| 19 |
+
in_channels=2048,
|
| 20 |
+
in_index=3,
|
| 21 |
+
channels=512,
|
| 22 |
+
num_convs=2,
|
| 23 |
+
concat_input=True,
|
| 24 |
+
dropout_ratio=0.1,
|
| 25 |
+
num_classes=19,
|
| 26 |
+
norm_cfg=norm_cfg,
|
| 27 |
+
align_corners=False,
|
| 28 |
+
loss_decode=dict(
|
| 29 |
+
type='CrossEntropyLoss', use_sigmoid=False, loss_weight=1.0)),
|
| 30 |
+
auxiliary_head=dict(
|
| 31 |
+
type='FCNHead',
|
| 32 |
+
in_channels=1024,
|
| 33 |
+
in_index=2,
|
| 34 |
+
channels=256,
|
| 35 |
+
num_convs=1,
|
| 36 |
+
concat_input=False,
|
| 37 |
+
dropout_ratio=0.1,
|
| 38 |
+
num_classes=19,
|
| 39 |
+
norm_cfg=norm_cfg,
|
| 40 |
+
align_corners=False,
|
| 41 |
+
loss_decode=dict(
|
| 42 |
+
type='CrossEntropyLoss', use_sigmoid=False, loss_weight=0.4)),
|
| 43 |
+
# model training and testing settings
|
| 44 |
+
train_cfg=dict(),
|
| 45 |
+
test_cfg=dict(mode='whole'))
|
configs/_base_/models/fcn_unet_s5-d16.py
ADDED
|
@@ -0,0 +1,51 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
# model settings
|
| 2 |
+
norm_cfg = dict(type='SyncBN', requires_grad=True)
|
| 3 |
+
model = dict(
|
| 4 |
+
type='EncoderDecoder',
|
| 5 |
+
pretrained=None,
|
| 6 |
+
backbone=dict(
|
| 7 |
+
type='UNet',
|
| 8 |
+
in_channels=3,
|
| 9 |
+
base_channels=64,
|
| 10 |
+
num_stages=5,
|
| 11 |
+
strides=(1, 1, 1, 1, 1),
|
| 12 |
+
enc_num_convs=(2, 2, 2, 2, 2),
|
| 13 |
+
dec_num_convs=(2, 2, 2, 2),
|
| 14 |
+
downsamples=(True, True, True, True),
|
| 15 |
+
enc_dilations=(1, 1, 1, 1, 1),
|
| 16 |
+
dec_dilations=(1, 1, 1, 1),
|
| 17 |
+
with_cp=False,
|
| 18 |
+
conv_cfg=None,
|
| 19 |
+
norm_cfg=norm_cfg,
|
| 20 |
+
act_cfg=dict(type='ReLU'),
|
| 21 |
+
upsample_cfg=dict(type='InterpConv'),
|
| 22 |
+
norm_eval=False),
|
| 23 |
+
decode_head=dict(
|
| 24 |
+
type='FCNHead',
|
| 25 |
+
in_channels=64,
|
| 26 |
+
in_index=4,
|
| 27 |
+
channels=64,
|
| 28 |
+
num_convs=1,
|
| 29 |
+
concat_input=False,
|
| 30 |
+
dropout_ratio=0.1,
|
| 31 |
+
num_classes=2,
|
| 32 |
+
norm_cfg=norm_cfg,
|
| 33 |
+
align_corners=False,
|
| 34 |
+
loss_decode=dict(
|
| 35 |
+
type='CrossEntropyLoss', use_sigmoid=False, loss_weight=1.0)),
|
| 36 |
+
auxiliary_head=dict(
|
| 37 |
+
type='FCNHead',
|
| 38 |
+
in_channels=128,
|
| 39 |
+
in_index=3,
|
| 40 |
+
channels=64,
|
| 41 |
+
num_convs=1,
|
| 42 |
+
concat_input=False,
|
| 43 |
+
dropout_ratio=0.1,
|
| 44 |
+
num_classes=2,
|
| 45 |
+
norm_cfg=norm_cfg,
|
| 46 |
+
align_corners=False,
|
| 47 |
+
loss_decode=dict(
|
| 48 |
+
type='CrossEntropyLoss', use_sigmoid=False, loss_weight=0.4)),
|
| 49 |
+
# model training and testing settings
|
| 50 |
+
train_cfg=dict(),
|
| 51 |
+
test_cfg=dict(mode='slide', crop_size=256, stride=170))
|
configs/_base_/models/fpn_r50.py
ADDED
|
@@ -0,0 +1,36 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
# model settings
|
| 2 |
+
norm_cfg = dict(type='SyncBN', requires_grad=True)
|
| 3 |
+
model = dict(
|
| 4 |
+
type='EncoderDecoder',
|
| 5 |
+
pretrained='open-mmlab://resnet50_v1c',
|
| 6 |
+
backbone=dict(
|
| 7 |
+
type='ResNetV1c',
|
| 8 |
+
depth=50,
|
| 9 |
+
num_stages=4,
|
| 10 |
+
out_indices=(0, 1, 2, 3),
|
| 11 |
+
dilations=(1, 1, 1, 1),
|
| 12 |
+
strides=(1, 2, 2, 2),
|
| 13 |
+
norm_cfg=norm_cfg,
|
| 14 |
+
norm_eval=False,
|
| 15 |
+
style='pytorch',
|
| 16 |
+
contract_dilation=True),
|
| 17 |
+
neck=dict(
|
| 18 |
+
type='FPN',
|
| 19 |
+
in_channels=[256, 512, 1024, 2048],
|
| 20 |
+
out_channels=256,
|
| 21 |
+
num_outs=4),
|
| 22 |
+
decode_head=dict(
|
| 23 |
+
type='FPNHead',
|
| 24 |
+
in_channels=[256, 256, 256, 256],
|
| 25 |
+
in_index=[0, 1, 2, 3],
|
| 26 |
+
feature_strides=[4, 8, 16, 32],
|
| 27 |
+
channels=128,
|
| 28 |
+
dropout_ratio=0.1,
|
| 29 |
+
num_classes=19,
|
| 30 |
+
norm_cfg=norm_cfg,
|
| 31 |
+
align_corners=False,
|
| 32 |
+
loss_decode=dict(
|
| 33 |
+
type='CrossEntropyLoss', use_sigmoid=False, loss_weight=1.0)),
|
| 34 |
+
# model training and testing settings
|
| 35 |
+
train_cfg=dict(),
|
| 36 |
+
test_cfg=dict(mode='whole'))
|
configs/_base_/models/fpn_uniformer.py
ADDED
|
@@ -0,0 +1,35 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
# model settings
|
| 2 |
+
norm_cfg = dict(type='SyncBN', requires_grad=True)
|
| 3 |
+
model = dict(
|
| 4 |
+
type='EncoderDecoder',
|
| 5 |
+
backbone=dict(
|
| 6 |
+
type='UniFormer',
|
| 7 |
+
embed_dim=[64, 128, 320, 512],
|
| 8 |
+
layers=[3, 4, 8, 3],
|
| 9 |
+
head_dim=64,
|
| 10 |
+
mlp_ratio=4.,
|
| 11 |
+
qkv_bias=True,
|
| 12 |
+
drop_rate=0.,
|
| 13 |
+
attn_drop_rate=0.,
|
| 14 |
+
drop_path_rate=0.1),
|
| 15 |
+
neck=dict(
|
| 16 |
+
type='FPN',
|
| 17 |
+
in_channels=[64, 128, 320, 512],
|
| 18 |
+
out_channels=256,
|
| 19 |
+
num_outs=4),
|
| 20 |
+
decode_head=dict(
|
| 21 |
+
type='FPNHead',
|
| 22 |
+
in_channels=[256, 256, 256, 256],
|
| 23 |
+
in_index=[0, 1, 2, 3],
|
| 24 |
+
feature_strides=[4, 8, 16, 32],
|
| 25 |
+
channels=128,
|
| 26 |
+
dropout_ratio=0.1,
|
| 27 |
+
num_classes=150,
|
| 28 |
+
norm_cfg=norm_cfg,
|
| 29 |
+
align_corners=False,
|
| 30 |
+
loss_decode=dict(
|
| 31 |
+
type='CrossEntropyLoss', use_sigmoid=False, loss_weight=1.0)),
|
| 32 |
+
# model training and testing settings
|
| 33 |
+
train_cfg=dict(),
|
| 34 |
+
test_cfg=dict(mode='whole')
|
| 35 |
+
)
|
configs/_base_/models/gcnet_r50-d8.py
ADDED
|
@@ -0,0 +1,46 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
# model settings
|
| 2 |
+
norm_cfg = dict(type='SyncBN', requires_grad=True)
|
| 3 |
+
model = dict(
|
| 4 |
+
type='EncoderDecoder',
|
| 5 |
+
pretrained='open-mmlab://resnet50_v1c',
|
| 6 |
+
backbone=dict(
|
| 7 |
+
type='ResNetV1c',
|
| 8 |
+
depth=50,
|
| 9 |
+
num_stages=4,
|
| 10 |
+
out_indices=(0, 1, 2, 3),
|
| 11 |
+
dilations=(1, 1, 2, 4),
|
| 12 |
+
strides=(1, 2, 1, 1),
|
| 13 |
+
norm_cfg=norm_cfg,
|
| 14 |
+
norm_eval=False,
|
| 15 |
+
style='pytorch',
|
| 16 |
+
contract_dilation=True),
|
| 17 |
+
decode_head=dict(
|
| 18 |
+
type='GCHead',
|
| 19 |
+
in_channels=2048,
|
| 20 |
+
in_index=3,
|
| 21 |
+
channels=512,
|
| 22 |
+
ratio=1 / 4.,
|
| 23 |
+
pooling_type='att',
|
| 24 |
+
fusion_types=('channel_add', ),
|
| 25 |
+
dropout_ratio=0.1,
|
| 26 |
+
num_classes=19,
|
| 27 |
+
norm_cfg=norm_cfg,
|
| 28 |
+
align_corners=False,
|
| 29 |
+
loss_decode=dict(
|
| 30 |
+
type='CrossEntropyLoss', use_sigmoid=False, loss_weight=1.0)),
|
| 31 |
+
auxiliary_head=dict(
|
| 32 |
+
type='FCNHead',
|
| 33 |
+
in_channels=1024,
|
| 34 |
+
in_index=2,
|
| 35 |
+
channels=256,
|
| 36 |
+
num_convs=1,
|
| 37 |
+
concat_input=False,
|
| 38 |
+
dropout_ratio=0.1,
|
| 39 |
+
num_classes=19,
|
| 40 |
+
norm_cfg=norm_cfg,
|
| 41 |
+
align_corners=False,
|
| 42 |
+
loss_decode=dict(
|
| 43 |
+
type='CrossEntropyLoss', use_sigmoid=False, loss_weight=0.4)),
|
| 44 |
+
# model training and testing settings
|
| 45 |
+
train_cfg=dict(),
|
| 46 |
+
test_cfg=dict(mode='whole'))
|
configs/_base_/models/lraspp_m-v3-d8.py
ADDED
|
@@ -0,0 +1,25 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
# model settings
|
| 2 |
+
norm_cfg = dict(type='SyncBN', eps=0.001, requires_grad=True)
|
| 3 |
+
model = dict(
|
| 4 |
+
type='EncoderDecoder',
|
| 5 |
+
backbone=dict(
|
| 6 |
+
type='MobileNetV3',
|
| 7 |
+
arch='large',
|
| 8 |
+
out_indices=(1, 3, 16),
|
| 9 |
+
norm_cfg=norm_cfg),
|
| 10 |
+
decode_head=dict(
|
| 11 |
+
type='LRASPPHead',
|
| 12 |
+
in_channels=(16, 24, 960),
|
| 13 |
+
in_index=(0, 1, 2),
|
| 14 |
+
channels=128,
|
| 15 |
+
input_transform='multiple_select',
|
| 16 |
+
dropout_ratio=0.1,
|
| 17 |
+
num_classes=19,
|
| 18 |
+
norm_cfg=norm_cfg,
|
| 19 |
+
act_cfg=dict(type='ReLU'),
|
| 20 |
+
align_corners=False,
|
| 21 |
+
loss_decode=dict(
|
| 22 |
+
type='CrossEntropyLoss', use_sigmoid=False, loss_weight=1.0)),
|
| 23 |
+
# model training and testing settings
|
| 24 |
+
train_cfg=dict(),
|
| 25 |
+
test_cfg=dict(mode='whole'))
|
configs/_base_/models/nonlocal_r50-d8.py
ADDED
|
@@ -0,0 +1,46 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
# model settings
|
| 2 |
+
norm_cfg = dict(type='SyncBN', requires_grad=True)
|
| 3 |
+
model = dict(
|
| 4 |
+
type='EncoderDecoder',
|
| 5 |
+
pretrained='open-mmlab://resnet50_v1c',
|
| 6 |
+
backbone=dict(
|
| 7 |
+
type='ResNetV1c',
|
| 8 |
+
depth=50,
|
| 9 |
+
num_stages=4,
|
| 10 |
+
out_indices=(0, 1, 2, 3),
|
| 11 |
+
dilations=(1, 1, 2, 4),
|
| 12 |
+
strides=(1, 2, 1, 1),
|
| 13 |
+
norm_cfg=norm_cfg,
|
| 14 |
+
norm_eval=False,
|
| 15 |
+
style='pytorch',
|
| 16 |
+
contract_dilation=True),
|
| 17 |
+
decode_head=dict(
|
| 18 |
+
type='NLHead',
|
| 19 |
+
in_channels=2048,
|
| 20 |
+
in_index=3,
|
| 21 |
+
channels=512,
|
| 22 |
+
dropout_ratio=0.1,
|
| 23 |
+
reduction=2,
|
| 24 |
+
use_scale=True,
|
| 25 |
+
mode='embedded_gaussian',
|
| 26 |
+
num_classes=19,
|
| 27 |
+
norm_cfg=norm_cfg,
|
| 28 |
+
align_corners=False,
|
| 29 |
+
loss_decode=dict(
|
| 30 |
+
type='CrossEntropyLoss', use_sigmoid=False, loss_weight=1.0)),
|
| 31 |
+
auxiliary_head=dict(
|
| 32 |
+
type='FCNHead',
|
| 33 |
+
in_channels=1024,
|
| 34 |
+
in_index=2,
|
| 35 |
+
channels=256,
|
| 36 |
+
num_convs=1,
|
| 37 |
+
concat_input=False,
|
| 38 |
+
dropout_ratio=0.1,
|
| 39 |
+
num_classes=19,
|
| 40 |
+
norm_cfg=norm_cfg,
|
| 41 |
+
align_corners=False,
|
| 42 |
+
loss_decode=dict(
|
| 43 |
+
type='CrossEntropyLoss', use_sigmoid=False, loss_weight=0.4)),
|
| 44 |
+
# model training and testing settings
|
| 45 |
+
train_cfg=dict(),
|
| 46 |
+
test_cfg=dict(mode='whole'))
|
configs/_base_/models/ocrnet_hr18.py
ADDED
|
@@ -0,0 +1,68 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
# model settings
|
| 2 |
+
norm_cfg = dict(type='SyncBN', requires_grad=True)
|
| 3 |
+
model = dict(
|
| 4 |
+
type='CascadeEncoderDecoder',
|
| 5 |
+
num_stages=2,
|
| 6 |
+
pretrained='open-mmlab://msra/hrnetv2_w18',
|
| 7 |
+
backbone=dict(
|
| 8 |
+
type='HRNet',
|
| 9 |
+
norm_cfg=norm_cfg,
|
| 10 |
+
norm_eval=False,
|
| 11 |
+
extra=dict(
|
| 12 |
+
stage1=dict(
|
| 13 |
+
num_modules=1,
|
| 14 |
+
num_branches=1,
|
| 15 |
+
block='BOTTLENECK',
|
| 16 |
+
num_blocks=(4, ),
|
| 17 |
+
num_channels=(64, )),
|
| 18 |
+
stage2=dict(
|
| 19 |
+
num_modules=1,
|
| 20 |
+
num_branches=2,
|
| 21 |
+
block='BASIC',
|
| 22 |
+
num_blocks=(4, 4),
|
| 23 |
+
num_channels=(18, 36)),
|
| 24 |
+
stage3=dict(
|
| 25 |
+
num_modules=4,
|
| 26 |
+
num_branches=3,
|
| 27 |
+
block='BASIC',
|
| 28 |
+
num_blocks=(4, 4, 4),
|
| 29 |
+
num_channels=(18, 36, 72)),
|
| 30 |
+
stage4=dict(
|
| 31 |
+
num_modules=3,
|
| 32 |
+
num_branches=4,
|
| 33 |
+
block='BASIC',
|
| 34 |
+
num_blocks=(4, 4, 4, 4),
|
| 35 |
+
num_channels=(18, 36, 72, 144)))),
|
| 36 |
+
decode_head=[
|
| 37 |
+
dict(
|
| 38 |
+
type='FCNHead',
|
| 39 |
+
in_channels=[18, 36, 72, 144],
|
| 40 |
+
channels=sum([18, 36, 72, 144]),
|
| 41 |
+
in_index=(0, 1, 2, 3),
|
| 42 |
+
input_transform='resize_concat',
|
| 43 |
+
kernel_size=1,
|
| 44 |
+
num_convs=1,
|
| 45 |
+
concat_input=False,
|
| 46 |
+
dropout_ratio=-1,
|
| 47 |
+
num_classes=19,
|
| 48 |
+
norm_cfg=norm_cfg,
|
| 49 |
+
align_corners=False,
|
| 50 |
+
loss_decode=dict(
|
| 51 |
+
type='CrossEntropyLoss', use_sigmoid=False, loss_weight=0.4)),
|
| 52 |
+
dict(
|
| 53 |
+
type='OCRHead',
|
| 54 |
+
in_channels=[18, 36, 72, 144],
|
| 55 |
+
in_index=(0, 1, 2, 3),
|
| 56 |
+
input_transform='resize_concat',
|
| 57 |
+
channels=512,
|
| 58 |
+
ocr_channels=256,
|
| 59 |
+
dropout_ratio=-1,
|
| 60 |
+
num_classes=19,
|
| 61 |
+
norm_cfg=norm_cfg,
|
| 62 |
+
align_corners=False,
|
| 63 |
+
loss_decode=dict(
|
| 64 |
+
type='CrossEntropyLoss', use_sigmoid=False, loss_weight=1.0)),
|
| 65 |
+
],
|
| 66 |
+
# model training and testing settings
|
| 67 |
+
train_cfg=dict(),
|
| 68 |
+
test_cfg=dict(mode='whole'))
|
configs/_base_/models/ocrnet_r50-d8.py
ADDED
|
@@ -0,0 +1,47 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
# model settings
|
| 2 |
+
norm_cfg = dict(type='SyncBN', requires_grad=True)
|
| 3 |
+
model = dict(
|
| 4 |
+
type='CascadeEncoderDecoder',
|
| 5 |
+
num_stages=2,
|
| 6 |
+
pretrained='open-mmlab://resnet50_v1c',
|
| 7 |
+
backbone=dict(
|
| 8 |
+
type='ResNetV1c',
|
| 9 |
+
depth=50,
|
| 10 |
+
num_stages=4,
|
| 11 |
+
out_indices=(0, 1, 2, 3),
|
| 12 |
+
dilations=(1, 1, 2, 4),
|
| 13 |
+
strides=(1, 2, 1, 1),
|
| 14 |
+
norm_cfg=norm_cfg,
|
| 15 |
+
norm_eval=False,
|
| 16 |
+
style='pytorch',
|
| 17 |
+
contract_dilation=True),
|
| 18 |
+
decode_head=[
|
| 19 |
+
dict(
|
| 20 |
+
type='FCNHead',
|
| 21 |
+
in_channels=1024,
|
| 22 |
+
in_index=2,
|
| 23 |
+
channels=256,
|
| 24 |
+
num_convs=1,
|
| 25 |
+
concat_input=False,
|
| 26 |
+
dropout_ratio=0.1,
|
| 27 |
+
num_classes=19,
|
| 28 |
+
norm_cfg=norm_cfg,
|
| 29 |
+
align_corners=False,
|
| 30 |
+
loss_decode=dict(
|
| 31 |
+
type='CrossEntropyLoss', use_sigmoid=False, loss_weight=0.4)),
|
| 32 |
+
dict(
|
| 33 |
+
type='OCRHead',
|
| 34 |
+
in_channels=2048,
|
| 35 |
+
in_index=3,
|
| 36 |
+
channels=512,
|
| 37 |
+
ocr_channels=256,
|
| 38 |
+
dropout_ratio=0.1,
|
| 39 |
+
num_classes=19,
|
| 40 |
+
norm_cfg=norm_cfg,
|
| 41 |
+
align_corners=False,
|
| 42 |
+
loss_decode=dict(
|
| 43 |
+
type='CrossEntropyLoss', use_sigmoid=False, loss_weight=1.0))
|
| 44 |
+
],
|
| 45 |
+
# model training and testing settings
|
| 46 |
+
train_cfg=dict(),
|
| 47 |
+
test_cfg=dict(mode='whole'))
|
configs/_base_/models/pointrend_r50.py
ADDED
|
@@ -0,0 +1,56 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
# model settings
|
| 2 |
+
norm_cfg = dict(type='SyncBN', requires_grad=True)
|
| 3 |
+
model = dict(
|
| 4 |
+
type='CascadeEncoderDecoder',
|
| 5 |
+
num_stages=2,
|
| 6 |
+
pretrained='open-mmlab://resnet50_v1c',
|
| 7 |
+
backbone=dict(
|
| 8 |
+
type='ResNetV1c',
|
| 9 |
+
depth=50,
|
| 10 |
+
num_stages=4,
|
| 11 |
+
out_indices=(0, 1, 2, 3),
|
| 12 |
+
dilations=(1, 1, 1, 1),
|
| 13 |
+
strides=(1, 2, 2, 2),
|
| 14 |
+
norm_cfg=norm_cfg,
|
| 15 |
+
norm_eval=False,
|
| 16 |
+
style='pytorch',
|
| 17 |
+
contract_dilation=True),
|
| 18 |
+
neck=dict(
|
| 19 |
+
type='FPN',
|
| 20 |
+
in_channels=[256, 512, 1024, 2048],
|
| 21 |
+
out_channels=256,
|
| 22 |
+
num_outs=4),
|
| 23 |
+
decode_head=[
|
| 24 |
+
dict(
|
| 25 |
+
type='FPNHead',
|
| 26 |
+
in_channels=[256, 256, 256, 256],
|
| 27 |
+
in_index=[0, 1, 2, 3],
|
| 28 |
+
feature_strides=[4, 8, 16, 32],
|
| 29 |
+
channels=128,
|
| 30 |
+
dropout_ratio=-1,
|
| 31 |
+
num_classes=19,
|
| 32 |
+
norm_cfg=norm_cfg,
|
| 33 |
+
align_corners=False,
|
| 34 |
+
loss_decode=dict(
|
| 35 |
+
type='CrossEntropyLoss', use_sigmoid=False, loss_weight=1.0)),
|
| 36 |
+
dict(
|
| 37 |
+
type='PointHead',
|
| 38 |
+
in_channels=[256],
|
| 39 |
+
in_index=[0],
|
| 40 |
+
channels=256,
|
| 41 |
+
num_fcs=3,
|
| 42 |
+
coarse_pred_each_layer=True,
|
| 43 |
+
dropout_ratio=-1,
|
| 44 |
+
num_classes=19,
|
| 45 |
+
align_corners=False,
|
| 46 |
+
loss_decode=dict(
|
| 47 |
+
type='CrossEntropyLoss', use_sigmoid=False, loss_weight=1.0))
|
| 48 |
+
],
|
| 49 |
+
# model training and testing settings
|
| 50 |
+
train_cfg=dict(
|
| 51 |
+
num_points=2048, oversample_ratio=3, importance_sample_ratio=0.75),
|
| 52 |
+
test_cfg=dict(
|
| 53 |
+
mode='whole',
|
| 54 |
+
subdivision_steps=2,
|
| 55 |
+
subdivision_num_points=8196,
|
| 56 |
+
scale_factor=2))
|
configs/_base_/models/psanet_r50-d8.py
ADDED
|
@@ -0,0 +1,49 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
# model settings
|
| 2 |
+
norm_cfg = dict(type='SyncBN', requires_grad=True)
|
| 3 |
+
model = dict(
|
| 4 |
+
type='EncoderDecoder',
|
| 5 |
+
pretrained='open-mmlab://resnet50_v1c',
|
| 6 |
+
backbone=dict(
|
| 7 |
+
type='ResNetV1c',
|
| 8 |
+
depth=50,
|
| 9 |
+
num_stages=4,
|
| 10 |
+
out_indices=(0, 1, 2, 3),
|
| 11 |
+
dilations=(1, 1, 2, 4),
|
| 12 |
+
strides=(1, 2, 1, 1),
|
| 13 |
+
norm_cfg=norm_cfg,
|
| 14 |
+
norm_eval=False,
|
| 15 |
+
style='pytorch',
|
| 16 |
+
contract_dilation=True),
|
| 17 |
+
decode_head=dict(
|
| 18 |
+
type='PSAHead',
|
| 19 |
+
in_channels=2048,
|
| 20 |
+
in_index=3,
|
| 21 |
+
channels=512,
|
| 22 |
+
mask_size=(97, 97),
|
| 23 |
+
psa_type='bi-direction',
|
| 24 |
+
compact=False,
|
| 25 |
+
shrink_factor=2,
|
| 26 |
+
normalization_factor=1.0,
|
| 27 |
+
psa_softmax=True,
|
| 28 |
+
dropout_ratio=0.1,
|
| 29 |
+
num_classes=19,
|
| 30 |
+
norm_cfg=norm_cfg,
|
| 31 |
+
align_corners=False,
|
| 32 |
+
loss_decode=dict(
|
| 33 |
+
type='CrossEntropyLoss', use_sigmoid=False, loss_weight=1.0)),
|
| 34 |
+
auxiliary_head=dict(
|
| 35 |
+
type='FCNHead',
|
| 36 |
+
in_channels=1024,
|
| 37 |
+
in_index=2,
|
| 38 |
+
channels=256,
|
| 39 |
+
num_convs=1,
|
| 40 |
+
concat_input=False,
|
| 41 |
+
dropout_ratio=0.1,
|
| 42 |
+
num_classes=19,
|
| 43 |
+
norm_cfg=norm_cfg,
|
| 44 |
+
align_corners=False,
|
| 45 |
+
loss_decode=dict(
|
| 46 |
+
type='CrossEntropyLoss', use_sigmoid=False, loss_weight=0.4)),
|
| 47 |
+
# model training and testing settings
|
| 48 |
+
train_cfg=dict(),
|
| 49 |
+
test_cfg=dict(mode='whole'))
|
configs/_base_/models/pspnet_r50-d8.py
ADDED
|
@@ -0,0 +1,44 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
# model settings
|
| 2 |
+
norm_cfg = dict(type='SyncBN', requires_grad=True)
|
| 3 |
+
model = dict(
|
| 4 |
+
type='EncoderDecoder',
|
| 5 |
+
pretrained='open-mmlab://resnet50_v1c',
|
| 6 |
+
backbone=dict(
|
| 7 |
+
type='ResNetV1c',
|
| 8 |
+
depth=50,
|
| 9 |
+
num_stages=4,
|
| 10 |
+
out_indices=(0, 1, 2, 3),
|
| 11 |
+
dilations=(1, 1, 2, 4),
|
| 12 |
+
strides=(1, 2, 1, 1),
|
| 13 |
+
norm_cfg=norm_cfg,
|
| 14 |
+
norm_eval=False,
|
| 15 |
+
style='pytorch',
|
| 16 |
+
contract_dilation=True),
|
| 17 |
+
decode_head=dict(
|
| 18 |
+
type='PSPHead',
|
| 19 |
+
in_channels=2048,
|
| 20 |
+
in_index=3,
|
| 21 |
+
channels=512,
|
| 22 |
+
pool_scales=(1, 2, 3, 6),
|
| 23 |
+
dropout_ratio=0.1,
|
| 24 |
+
num_classes=19,
|
| 25 |
+
norm_cfg=norm_cfg,
|
| 26 |
+
align_corners=False,
|
| 27 |
+
loss_decode=dict(
|
| 28 |
+
type='CrossEntropyLoss', use_sigmoid=False, loss_weight=1.0)),
|
| 29 |
+
auxiliary_head=dict(
|
| 30 |
+
type='FCNHead',
|
| 31 |
+
in_channels=1024,
|
| 32 |
+
in_index=2,
|
| 33 |
+
channels=256,
|
| 34 |
+
num_convs=1,
|
| 35 |
+
concat_input=False,
|
| 36 |
+
dropout_ratio=0.1,
|
| 37 |
+
num_classes=19,
|
| 38 |
+
norm_cfg=norm_cfg,
|
| 39 |
+
align_corners=False,
|
| 40 |
+
loss_decode=dict(
|
| 41 |
+
type='CrossEntropyLoss', use_sigmoid=False, loss_weight=0.4)),
|
| 42 |
+
# model training and testing settings
|
| 43 |
+
train_cfg=dict(),
|
| 44 |
+
test_cfg=dict(mode='whole'))
|
configs/_base_/models/pspnet_unet_s5-d16.py
ADDED
|
@@ -0,0 +1,50 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
# model settings
|
| 2 |
+
norm_cfg = dict(type='SyncBN', requires_grad=True)
|
| 3 |
+
model = dict(
|
| 4 |
+
type='EncoderDecoder',
|
| 5 |
+
pretrained=None,
|
| 6 |
+
backbone=dict(
|
| 7 |
+
type='UNet',
|
| 8 |
+
in_channels=3,
|
| 9 |
+
base_channels=64,
|
| 10 |
+
num_stages=5,
|
| 11 |
+
strides=(1, 1, 1, 1, 1),
|
| 12 |
+
enc_num_convs=(2, 2, 2, 2, 2),
|
| 13 |
+
dec_num_convs=(2, 2, 2, 2),
|
| 14 |
+
downsamples=(True, True, True, True),
|
| 15 |
+
enc_dilations=(1, 1, 1, 1, 1),
|
| 16 |
+
dec_dilations=(1, 1, 1, 1),
|
| 17 |
+
with_cp=False,
|
| 18 |
+
conv_cfg=None,
|
| 19 |
+
norm_cfg=norm_cfg,
|
| 20 |
+
act_cfg=dict(type='ReLU'),
|
| 21 |
+
upsample_cfg=dict(type='InterpConv'),
|
| 22 |
+
norm_eval=False),
|
| 23 |
+
decode_head=dict(
|
| 24 |
+
type='PSPHead',
|
| 25 |
+
in_channels=64,
|
| 26 |
+
in_index=4,
|
| 27 |
+
channels=16,
|
| 28 |
+
pool_scales=(1, 2, 3, 6),
|
| 29 |
+
dropout_ratio=0.1,
|
| 30 |
+
num_classes=2,
|
| 31 |
+
norm_cfg=norm_cfg,
|
| 32 |
+
align_corners=False,
|
| 33 |
+
loss_decode=dict(
|
| 34 |
+
type='CrossEntropyLoss', use_sigmoid=False, loss_weight=1.0)),
|
| 35 |
+
auxiliary_head=dict(
|
| 36 |
+
type='FCNHead',
|
| 37 |
+
in_channels=128,
|
| 38 |
+
in_index=3,
|
| 39 |
+
channels=64,
|
| 40 |
+
num_convs=1,
|
| 41 |
+
concat_input=False,
|
| 42 |
+
dropout_ratio=0.1,
|
| 43 |
+
num_classes=2,
|
| 44 |
+
norm_cfg=norm_cfg,
|
| 45 |
+
align_corners=False,
|
| 46 |
+
loss_decode=dict(
|
| 47 |
+
type='CrossEntropyLoss', use_sigmoid=False, loss_weight=0.4)),
|
| 48 |
+
# model training and testing settings
|
| 49 |
+
train_cfg=dict(),
|
| 50 |
+
test_cfg=dict(mode='slide', crop_size=256, stride=170))
|
configs/_base_/models/upernet_r50.py
ADDED
|
@@ -0,0 +1,44 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
# model settings
|
| 2 |
+
norm_cfg = dict(type='SyncBN', requires_grad=True)
|
| 3 |
+
model = dict(
|
| 4 |
+
type='EncoderDecoder',
|
| 5 |
+
pretrained='open-mmlab://resnet50_v1c',
|
| 6 |
+
backbone=dict(
|
| 7 |
+
type='ResNetV1c',
|
| 8 |
+
depth=50,
|
| 9 |
+
num_stages=4,
|
| 10 |
+
out_indices=(0, 1, 2, 3),
|
| 11 |
+
dilations=(1, 1, 1, 1),
|
| 12 |
+
strides=(1, 2, 2, 2),
|
| 13 |
+
norm_cfg=norm_cfg,
|
| 14 |
+
norm_eval=False,
|
| 15 |
+
style='pytorch',
|
| 16 |
+
contract_dilation=True),
|
| 17 |
+
decode_head=dict(
|
| 18 |
+
type='UPerHead',
|
| 19 |
+
in_channels=[256, 512, 1024, 2048],
|
| 20 |
+
in_index=[0, 1, 2, 3],
|
| 21 |
+
pool_scales=(1, 2, 3, 6),
|
| 22 |
+
channels=512,
|
| 23 |
+
dropout_ratio=0.1,
|
| 24 |
+
num_classes=19,
|
| 25 |
+
norm_cfg=norm_cfg,
|
| 26 |
+
align_corners=False,
|
| 27 |
+
loss_decode=dict(
|
| 28 |
+
type='CrossEntropyLoss', use_sigmoid=False, loss_weight=1.0)),
|
| 29 |
+
auxiliary_head=dict(
|
| 30 |
+
type='FCNHead',
|
| 31 |
+
in_channels=1024,
|
| 32 |
+
in_index=2,
|
| 33 |
+
channels=256,
|
| 34 |
+
num_convs=1,
|
| 35 |
+
concat_input=False,
|
| 36 |
+
dropout_ratio=0.1,
|
| 37 |
+
num_classes=19,
|
| 38 |
+
norm_cfg=norm_cfg,
|
| 39 |
+
align_corners=False,
|
| 40 |
+
loss_decode=dict(
|
| 41 |
+
type='CrossEntropyLoss', use_sigmoid=False, loss_weight=0.4)),
|
| 42 |
+
# model training and testing settings
|
| 43 |
+
train_cfg=dict(),
|
| 44 |
+
test_cfg=dict(mode='whole'))
|
configs/_base_/models/upernet_uniformer.py
ADDED
|
@@ -0,0 +1,43 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
# model settings
|
| 2 |
+
norm_cfg = dict(type='SyncBN', requires_grad=True)
|
| 3 |
+
model = dict(
|
| 4 |
+
type='EncoderDecoder',
|
| 5 |
+
pretrained=None,
|
| 6 |
+
backbone=dict(
|
| 7 |
+
type='UniFormer',
|
| 8 |
+
embed_dim=[64, 128, 320, 512],
|
| 9 |
+
layers=[3, 4, 8, 3],
|
| 10 |
+
head_dim=64,
|
| 11 |
+
mlp_ratio=4.,
|
| 12 |
+
qkv_bias=True,
|
| 13 |
+
drop_rate=0.,
|
| 14 |
+
attn_drop_rate=0.,
|
| 15 |
+
drop_path_rate=0.1),
|
| 16 |
+
decode_head=dict(
|
| 17 |
+
type='UPerHead',
|
| 18 |
+
in_channels=[64, 128, 320, 512],
|
| 19 |
+
in_index=[0, 1, 2, 3],
|
| 20 |
+
pool_scales=(1, 2, 3, 6),
|
| 21 |
+
channels=512,
|
| 22 |
+
dropout_ratio=0.1,
|
| 23 |
+
num_classes=19,
|
| 24 |
+
norm_cfg=norm_cfg,
|
| 25 |
+
align_corners=False,
|
| 26 |
+
loss_decode=dict(
|
| 27 |
+
type='CrossEntropyLoss', use_sigmoid=False, loss_weight=1.0)),
|
| 28 |
+
auxiliary_head=dict(
|
| 29 |
+
type='FCNHead',
|
| 30 |
+
in_channels=320,
|
| 31 |
+
in_index=2,
|
| 32 |
+
channels=256,
|
| 33 |
+
num_convs=1,
|
| 34 |
+
concat_input=False,
|
| 35 |
+
dropout_ratio=0.1,
|
| 36 |
+
num_classes=19,
|
| 37 |
+
norm_cfg=norm_cfg,
|
| 38 |
+
align_corners=False,
|
| 39 |
+
loss_decode=dict(
|
| 40 |
+
type='CrossEntropyLoss', use_sigmoid=False, loss_weight=0.4)),
|
| 41 |
+
# model training and testing settings
|
| 42 |
+
train_cfg=dict(),
|
| 43 |
+
test_cfg=dict(mode='whole'))
|
configs/_base_/schedules/schedule_160k.py
ADDED
|
@@ -0,0 +1,9 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
# optimizer
|
| 2 |
+
optimizer = dict(type='SGD', lr=0.01, momentum=0.9, weight_decay=0.0005)
|
| 3 |
+
optimizer_config = dict()
|
| 4 |
+
# learning policy
|
| 5 |
+
lr_config = dict(policy='poly', power=0.9, min_lr=1e-4, by_epoch=False)
|
| 6 |
+
# runtime settings
|
| 7 |
+
runner = dict(type='IterBasedRunner', max_iters=160000)
|
| 8 |
+
checkpoint_config = dict(by_epoch=False, interval=16000)
|
| 9 |
+
evaluation = dict(interval=16000, metric='mIoU')
|
configs/_base_/schedules/schedule_20k.py
ADDED
|
@@ -0,0 +1,9 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
# optimizer
|
| 2 |
+
optimizer = dict(type='SGD', lr=0.01, momentum=0.9, weight_decay=0.0005)
|
| 3 |
+
optimizer_config = dict()
|
| 4 |
+
# learning policy
|
| 5 |
+
lr_config = dict(policy='poly', power=0.9, min_lr=1e-4, by_epoch=False)
|
| 6 |
+
# runtime settings
|
| 7 |
+
runner = dict(type='IterBasedRunner', max_iters=20000)
|
| 8 |
+
checkpoint_config = dict(by_epoch=False, interval=2000)
|
| 9 |
+
evaluation = dict(interval=2000, metric='mIoU')
|
configs/_base_/schedules/schedule_40k.py
ADDED
|
@@ -0,0 +1,9 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
# optimizer
|
| 2 |
+
optimizer = dict(type='SGD', lr=0.01, momentum=0.9, weight_decay=0.0005)
|
| 3 |
+
optimizer_config = dict()
|
| 4 |
+
# learning policy
|
| 5 |
+
lr_config = dict(policy='poly', power=0.9, min_lr=1e-4, by_epoch=False)
|
| 6 |
+
# runtime settings
|
| 7 |
+
runner = dict(type='IterBasedRunner', max_iters=40000)
|
| 8 |
+
checkpoint_config = dict(by_epoch=False, interval=4000)
|
| 9 |
+
evaluation = dict(interval=4000, metric='mIoU')
|
configs/_base_/schedules/schedule_80k.py
ADDED
|
@@ -0,0 +1,9 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
# optimizer
|
| 2 |
+
optimizer = dict(type='SGD', lr=0.01, momentum=0.9, weight_decay=0.0005)
|
| 3 |
+
optimizer_config = dict()
|
| 4 |
+
# learning policy
|
| 5 |
+
lr_config = dict(policy='poly', power=0.9, min_lr=1e-4, by_epoch=False)
|
| 6 |
+
# runtime settings
|
| 7 |
+
runner = dict(type='IterBasedRunner', max_iters=80000)
|
| 8 |
+
checkpoint_config = dict(by_epoch=False, interval=8000)
|
| 9 |
+
evaluation = dict(interval=8000, metric='mIoU')
|
configs/ann/README.md
ADDED
|
@@ -0,0 +1,52 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
# Asymmetric Non-local Neural Networks for Semantic Segmentation
|
| 2 |
+
|
| 3 |
+
## Introduction
|
| 4 |
+
|
| 5 |
+
<!-- [ALGORITHM] -->
|
| 6 |
+
|
| 7 |
+
```latex
|
| 8 |
+
@inproceedings{annn,
|
| 9 |
+
author = {Zhen Zhu and
|
| 10 |
+
Mengde Xu and
|
| 11 |
+
Song Bai and
|
| 12 |
+
Tengteng Huang and
|
| 13 |
+
Xiang Bai},
|
| 14 |
+
title = {Asymmetric Non-local Neural Networks for Semantic Segmentation},
|
| 15 |
+
booktitle={International Conference on Computer Vision},
|
| 16 |
+
year = {2019},
|
| 17 |
+
url = {http://arxiv.org/abs/1908.07678},
|
| 18 |
+
}
|
| 19 |
+
```
|
| 20 |
+
|
| 21 |
+
## Results and models
|
| 22 |
+
|
| 23 |
+
### Cityscapes
|
| 24 |
+
|
| 25 |
+
| Method | Backbone | Crop Size | Lr schd | Mem (GB) | Inf time (fps) | mIoU | mIoU(ms+flip) | config | download |
|
| 26 |
+
| ------ | -------- | --------- | ------: | -------- | -------------- | ----: | ------------: | --------------------------------------------------------------------------------------------------------------------- | ------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------ |
|
| 27 |
+
| ANN | R-50-D8 | 512x1024 | 40000 | 6 | 3.71 | 77.40 | 78.57 | [config](https://github.com/open-mmlab/mmsegmentation/blob/master/configs/ann/ann_r50-d8_512x1024_40k_cityscapes.py) | [model](https://download.openmmlab.com/mmsegmentation/v0.5/ann/ann_r50-d8_512x1024_40k_cityscapes/ann_r50-d8_512x1024_40k_cityscapes_20200605_095211-049fc292.pth) | [log](https://download.openmmlab.com/mmsegmentation/v0.5/ann/ann_r50-d8_512x1024_40k_cityscapes/ann_r50-d8_512x1024_40k_cityscapes_20200605_095211.log.json) |
|
| 28 |
+
| ANN | R-101-D8 | 512x1024 | 40000 | 9.5 | 2.55 | 76.55 | 78.85 | [config](https://github.com/open-mmlab/mmsegmentation/blob/master/configs/ann/ann_r101-d8_512x1024_40k_cityscapes.py) | [model](https://download.openmmlab.com/mmsegmentation/v0.5/ann/ann_r101-d8_512x1024_40k_cityscapes/ann_r101-d8_512x1024_40k_cityscapes_20200605_095243-adf6eece.pth) | [log](https://download.openmmlab.com/mmsegmentation/v0.5/ann/ann_r101-d8_512x1024_40k_cityscapes/ann_r101-d8_512x1024_40k_cityscapes_20200605_095243.log.json) |
|
| 29 |
+
| ANN | R-50-D8 | 769x769 | 40000 | 6.8 | 1.70 | 78.89 | 80.46 | [config](https://github.com/open-mmlab/mmsegmentation/blob/master/configs/ann/ann_r50-d8_769x769_40k_cityscapes.py) | [model](https://download.openmmlab.com/mmsegmentation/v0.5/ann/ann_r50-d8_769x769_40k_cityscapes/ann_r50-d8_769x769_40k_cityscapes_20200530_025712-2b46b04d.pth) | [log](https://download.openmmlab.com/mmsegmentation/v0.5/ann/ann_r50-d8_769x769_40k_cityscapes/ann_r50-d8_769x769_40k_cityscapes_20200530_025712.log.json) |
|
| 30 |
+
| ANN | R-101-D8 | 769x769 | 40000 | 10.7 | 1.15 | 79.32 | 80.94 | [config](https://github.com/open-mmlab/mmsegmentation/blob/master/configs/ann/ann_r101-d8_769x769_40k_cityscapes.py) | [model](https://download.openmmlab.com/mmsegmentation/v0.5/ann/ann_r101-d8_769x769_40k_cityscapes/ann_r101-d8_769x769_40k_cityscapes_20200530_025720-059bff28.pth) | [log](https://download.openmmlab.com/mmsegmentation/v0.5/ann/ann_r101-d8_769x769_40k_cityscapes/ann_r101-d8_769x769_40k_cityscapes_20200530_025720.log.json) |
|
| 31 |
+
| ANN | R-50-D8 | 512x1024 | 80000 | - | - | 77.34 | 78.65 | [config](https://github.com/open-mmlab/mmsegmentation/blob/master/configs/ann/ann_r50-d8_512x1024_80k_cityscapes.py) | [model](https://download.openmmlab.com/mmsegmentation/v0.5/ann/ann_r50-d8_512x1024_80k_cityscapes/ann_r50-d8_512x1024_80k_cityscapes_20200607_101911-5a9ad545.pth) | [log](https://download.openmmlab.com/mmsegmentation/v0.5/ann/ann_r50-d8_512x1024_80k_cityscapes/ann_r50-d8_512x1024_80k_cityscapes_20200607_101911.log.json) |
|
| 32 |
+
| ANN | R-101-D8 | 512x1024 | 80000 | - | - | 77.14 | 78.81 | [config](https://github.com/open-mmlab/mmsegmentation/blob/master/configs/ann/ann_r101-d8_512x1024_80k_cityscapes.py) | [model](https://download.openmmlab.com/mmsegmentation/v0.5/ann/ann_r101-d8_512x1024_80k_cityscapes/ann_r101-d8_512x1024_80k_cityscapes_20200607_013728-aceccc6e.pth) | [log](https://download.openmmlab.com/mmsegmentation/v0.5/ann/ann_r101-d8_512x1024_80k_cityscapes/ann_r101-d8_512x1024_80k_cityscapes_20200607_013728.log.json) |
|
| 33 |
+
| ANN | R-50-D8 | 769x769 | 80000 | - | - | 78.88 | 80.57 | [config](https://github.com/open-mmlab/mmsegmentation/blob/master/configs/ann/ann_r50-d8_769x769_80k_cityscapes.py) | [model](https://download.openmmlab.com/mmsegmentation/v0.5/ann/ann_r50-d8_769x769_80k_cityscapes/ann_r50-d8_769x769_80k_cityscapes_20200607_044426-cc7ff323.pth) | [log](https://download.openmmlab.com/mmsegmentation/v0.5/ann/ann_r50-d8_769x769_80k_cityscapes/ann_r50-d8_769x769_80k_cityscapes_20200607_044426.log.json) |
|
| 34 |
+
| ANN | R-101-D8 | 769x769 | 80000 | - | - | 78.80 | 80.34 | [config](https://github.com/open-mmlab/mmsegmentation/blob/master/configs/ann/ann_r101-d8_769x769_80k_cityscapes.py) | [model](https://download.openmmlab.com/mmsegmentation/v0.5/ann/ann_r101-d8_769x769_80k_cityscapes/ann_r101-d8_769x769_80k_cityscapes_20200607_013713-a9d4be8d.pth) | [log](https://download.openmmlab.com/mmsegmentation/v0.5/ann/ann_r101-d8_769x769_80k_cityscapes/ann_r101-d8_769x769_80k_cityscapes_20200607_013713.log.json) |
|
| 35 |
+
|
| 36 |
+
### ADE20K
|
| 37 |
+
|
| 38 |
+
| Method | Backbone | Crop Size | Lr schd | Mem (GB) | Inf time (fps) | mIoU | mIoU(ms+flip) | config | download |
|
| 39 |
+
| ------ | -------- | --------- | ------: | -------- | -------------- | ----: | ------------: | ----------------------------------------------------------------------------------------------------------------- | -------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
|
| 40 |
+
| ANN | R-50-D8 | 512x512 | 80000 | 9.1 | 21.01 | 41.01 | 42.30 | [config](https://github.com/open-mmlab/mmsegmentation/blob/master/configs/ann/ann_r50-d8_512x512_80k_ade20k.py) | [model](https://download.openmmlab.com/mmsegmentation/v0.5/ann/ann_r50-d8_512x512_80k_ade20k/ann_r50-d8_512x512_80k_ade20k_20200615_014818-26f75e11.pth) | [log](https://download.openmmlab.com/mmsegmentation/v0.5/ann/ann_r50-d8_512x512_80k_ade20k/ann_r50-d8_512x512_80k_ade20k_20200615_014818.log.json) |
|
| 41 |
+
| ANN | R-101-D8 | 512x512 | 80000 | 12.5 | 14.12 | 42.94 | 44.18 | [config](https://github.com/open-mmlab/mmsegmentation/blob/master/configs/ann/ann_r101-d8_512x512_80k_ade20k.py) | [model](https://download.openmmlab.com/mmsegmentation/v0.5/ann/ann_r101-d8_512x512_80k_ade20k/ann_r101-d8_512x512_80k_ade20k_20200615_014818-c0153543.pth) | [log](https://download.openmmlab.com/mmsegmentation/v0.5/ann/ann_r101-d8_512x512_80k_ade20k/ann_r101-d8_512x512_80k_ade20k_20200615_014818.log.json) |
|
| 42 |
+
| ANN | R-50-D8 | 512x512 | 160000 | - | - | 41.74 | 42.62 | [config](https://github.com/open-mmlab/mmsegmentation/blob/master/configs/ann/ann_r50-d8_512x512_160k_ade20k.py) | [model](https://download.openmmlab.com/mmsegmentation/v0.5/ann/ann_r50-d8_512x512_160k_ade20k/ann_r50-d8_512x512_160k_ade20k_20200615_231733-892247bc.pth) | [log](https://download.openmmlab.com/mmsegmentation/v0.5/ann/ann_r50-d8_512x512_160k_ade20k/ann_r50-d8_512x512_160k_ade20k_20200615_231733.log.json) |
|
| 43 |
+
| ANN | R-101-D8 | 512x512 | 160000 | - | - | 42.94 | 44.06 | [config](https://github.com/open-mmlab/mmsegmentation/blob/master/configs/ann/ann_r101-d8_512x512_160k_ade20k.py) | [model](https://download.openmmlab.com/mmsegmentation/v0.5/ann/ann_r101-d8_512x512_160k_ade20k/ann_r101-d8_512x512_160k_ade20k_20200615_231733-955eb1ec.pth) | [log](https://download.openmmlab.com/mmsegmentation/v0.5/ann/ann_r101-d8_512x512_160k_ade20k/ann_r101-d8_512x512_160k_ade20k_20200615_231733.log.json) |
|
| 44 |
+
|
| 45 |
+
### Pascal VOC 2012 + Aug
|
| 46 |
+
|
| 47 |
+
| Method | Backbone | Crop Size | Lr schd | Mem (GB) | Inf time (fps) | mIoU | mIoU(ms+flip) | config | download |
|
| 48 |
+
| ------ | -------- | --------- | ------: | -------- | -------------- | ----: | ------------: | ------------------------------------------------------------------------------------------------------------------ | ------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------ |
|
| 49 |
+
| ANN | R-50-D8 | 512x512 | 20000 | 6 | 20.92 | 74.86 | 76.13 | [config](https://github.com/open-mmlab/mmsegmentation/blob/master/configs/ann/ann_r50-d8_512x512_20k_voc12aug.py) | [model](https://download.openmmlab.com/mmsegmentation/v0.5/ann/ann_r50-d8_512x512_20k_voc12aug/ann_r50-d8_512x512_20k_voc12aug_20200617_222246-dfcb1c62.pth) | [log](https://download.openmmlab.com/mmsegmentation/v0.5/ann/ann_r50-d8_512x512_20k_voc12aug/ann_r50-d8_512x512_20k_voc12aug_20200617_222246.log.json) |
|
| 50 |
+
| ANN | R-101-D8 | 512x512 | 20000 | 9.5 | 13.94 | 77.47 | 78.70 | [config](https://github.com/open-mmlab/mmsegmentation/blob/master/configs/ann/ann_r101-d8_512x512_20k_voc12aug.py) | [model](https://download.openmmlab.com/mmsegmentation/v0.5/ann/ann_r101-d8_512x512_20k_voc12aug/ann_r101-d8_512x512_20k_voc12aug_20200617_222246-2fad0042.pth) | [log](https://download.openmmlab.com/mmsegmentation/v0.5/ann/ann_r101-d8_512x512_20k_voc12aug/ann_r101-d8_512x512_20k_voc12aug_20200617_222246.log.json) |
|
| 51 |
+
| ANN | R-50-D8 | 512x512 | 40000 | - | - | 76.56 | 77.51 | [config](https://github.com/open-mmlab/mmsegmentation/blob/master/configs/ann/ann_r50-d8_512x512_40k_voc12aug.py) | [model](https://download.openmmlab.com/mmsegmentation/v0.5/ann/ann_r50-d8_512x512_40k_voc12aug/ann_r50-d8_512x512_40k_voc12aug_20200613_231314-b5dac322.pth) | [log](https://download.openmmlab.com/mmsegmentation/v0.5/ann/ann_r50-d8_512x512_40k_voc12aug/ann_r50-d8_512x512_40k_voc12aug_20200613_231314.log.json) |
|
| 52 |
+
| ANN | R-101-D8 | 512x512 | 40000 | - | - | 76.70 | 78.06 | [config](https://github.com/open-mmlab/mmsegmentation/blob/master/configs/ann/ann_r101-d8_512x512_40k_voc12aug.py) | [model](https://download.openmmlab.com/mmsegmentation/v0.5/ann/ann_r101-d8_512x512_40k_voc12aug/ann_r101-d8_512x512_40k_voc12aug_20200613_231314-bd205bbe.pth) | [log](https://download.openmmlab.com/mmsegmentation/v0.5/ann/ann_r101-d8_512x512_40k_voc12aug/ann_r101-d8_512x512_40k_voc12aug_20200613_231314.log.json) |
|