Skip to content

Commit 8cf333c

Browse files
MengzhangLIMengzhangLI
authored
[Fix] Update correct In Collection in metafile of each configs. (open-mmlab#1239)
* change md2yml file * update metafile * update twins In Collection automatically * fix twins metafile * fix twins metafile * all metafile use value of Method * update collect name * update collect name * fix some typo * fix FCN D6 * change JPU to FastFCN * fix some typos in DNLNet, NonLocalNet, SETR, Segmenter, STDC, FastSCNN * fix typo in stdc * fix typo in DNLNet and UNet * fix NonLocalNet typo
1 parent 6ff724e commit 8cf333c

File tree

52 files changed

+718
-810
lines changed

Some content is hidden

Large Commits have some content hidden by default. Use the searchbox below for content that may be hidden.

52 files changed

+718
-810
lines changed

‎.dev/md2yml.py‎

Lines changed: 18 additions & 3 deletions
Original file line numberDiff line numberDiff line change
@@ -81,6 +81,13 @@ def parse_md(md_file):
8181
code_version = None
8282
repo_url = None
8383

84+
# To avoid re-counting number of backbone model in OpenMMLab,
85+
# if certain model in configs folder is backbone whose name is already
86+
# recorded in MMClassification, then the `COLLECTION` dict of this model
87+
# in MMSegmentation should be deleted, and `In Collection` in `Models`
88+
# should be set with head or neck of this config file.
89+
is_backbone = None
90+
8491
with open(md_file, 'r') as md:
8592
lines = md.readlines()
8693
i = 0
@@ -117,9 +124,13 @@ def parse_md(md_file):
117124
datasets.append(line[4:])
118125
current_dataset = line[4:]
119126
i += 2
127+
elif line[:15] == '<!-- [BACKBONE]':
128+
is_backbone = True
129+
i += 1
120130
elif line[0] == '|' and (
121131
i + 1) < len(lines) and lines[i + 1][:3] == '| -':
122132
cols = [col.strip() for col in line.split('|')]
133+
method_id = cols.index('Method')
123134
backbone_id = cols.index('Backbone')
124135
crop_size_id = cols.index('Crop Size')
125136
lr_schd_id = cols.index('Lr schd')
@@ -155,11 +166,12 @@ def parse_md(md_file):
155166
mem_id] != '' else -1
156167
crop_size = els[crop_size_id].split('x')
157168
assert len(crop_size) == 2
169+
method = els[method_id].split()[0].split('-')[-1]
158170
model = {
159171
'Name':
160172
model_name,
161173
'In Collection':
162-
collection_name,
174+
method,
163175
'Metadata': {
164176
'backbone': els[backbone_id],
165177
'crop size': f'({crop_size[0]},{crop_size[1]})',
@@ -213,6 +225,7 @@ def parse_md(md_file):
213225
flag = (code_url is not None) and (paper_url is not None) and (repo_url
214226
is not None)
215227
assert flag, f'{collection_name} readme error'
228+
collection['Name'] = method
216229
collection['Metadata']['Training Data'] = datasets
217230
collection['Code']['URL'] = code_url
218231
collection['Code']['Version'] = code_version
@@ -232,8 +245,10 @@ def parse_md(md_file):
232245
collection.pop(check_key)
233246
else:
234247
collection[check_key].pop(key)
235-
236-
result = {'Collections': [collection], 'Models': models}
248+
if is_backbone:
249+
result = {'Models': models}
250+
else:
251+
result = {'Collections': [collection], 'Models': models}
237252
yml_file = f'{md_file[:-9]}{collection_name}.yml'
238253
return dump_yaml_and_check_difference(result, yml_file)
239254

‎configs/ann/ann.yml‎

Lines changed: 17 additions & 17 deletions
Original file line numberDiff line numberDiff line change
@@ -1,5 +1,5 @@
11
Collections:
2-
- Name: ann
2+
- Name: ANN
33
Metadata:
44
Training Data:
55
- Cityscapes
@@ -16,7 +16,7 @@ Collections:
1616
Code: https://github.com/MendelXu/ANN
1717
Models:
1818
- Name: ann_r50-d8_512x1024_40k_cityscapes
19-
In Collection: ann
19+
In Collection: ANN
2020
Metadata:
2121
backbone: R-50-D8
2222
crop size: (512,1024)
@@ -38,7 +38,7 @@ Models:
3838
Config: configs/ann/ann_r50-d8_512x1024_40k_cityscapes.py
3939
Weights: https://download.openmmlab.com/mmsegmentation/v0.5/ann/ann_r50-d8_512x1024_40k_cityscapes/ann_r50-d8_512x1024_40k_cityscapes_20200605_095211-049fc292.pth
4040
- Name: ann_r101-d8_512x1024_40k_cityscapes
41-
In Collection: ann
41+
In Collection: ANN
4242
Metadata:
4343
backbone: R-101-D8
4444
crop size: (512,1024)
@@ -60,7 +60,7 @@ Models:
6060
Config: configs/ann/ann_r101-d8_512x1024_40k_cityscapes.py
6161
Weights: https://download.openmmlab.com/mmsegmentation/v0.5/ann/ann_r101-d8_512x1024_40k_cityscapes/ann_r101-d8_512x1024_40k_cityscapes_20200605_095243-adf6eece.pth
6262
- Name: ann_r50-d8_769x769_40k_cityscapes
63-
In Collection: ann
63+
In Collection: ANN
6464
Metadata:
6565
backbone: R-50-D8
6666
crop size: (769,769)
@@ -82,7 +82,7 @@ Models:
8282
Config: configs/ann/ann_r50-d8_769x769_40k_cityscapes.py
8383
Weights: https://download.openmmlab.com/mmsegmentation/v0.5/ann/ann_r50-d8_769x769_40k_cityscapes/ann_r50-d8_769x769_40k_cityscapes_20200530_025712-2b46b04d.pth
8484
- Name: ann_r101-d8_769x769_40k_cityscapes
85-
In Collection: ann
85+
In Collection: ANN
8686
Metadata:
8787
backbone: R-101-D8
8888
crop size: (769,769)
@@ -104,7 +104,7 @@ Models:
104104
Config: configs/ann/ann_r101-d8_769x769_40k_cityscapes.py
105105
Weights: https://download.openmmlab.com/mmsegmentation/v0.5/ann/ann_r101-d8_769x769_40k_cityscapes/ann_r101-d8_769x769_40k_cityscapes_20200530_025720-059bff28.pth
106106
- Name: ann_r50-d8_512x1024_80k_cityscapes
107-
In Collection: ann
107+
In Collection: ANN
108108
Metadata:
109109
backbone: R-50-D8
110110
crop size: (512,1024)
@@ -118,7 +118,7 @@ Models:
118118
Config: configs/ann/ann_r50-d8_512x1024_80k_cityscapes.py
119119
Weights: https://download.openmmlab.com/mmsegmentation/v0.5/ann/ann_r50-d8_512x1024_80k_cityscapes/ann_r50-d8_512x1024_80k_cityscapes_20200607_101911-5a9ad545.pth
120120
- Name: ann_r101-d8_512x1024_80k_cityscapes
121-
In Collection: ann
121+
In Collection: ANN
122122
Metadata:
123123
backbone: R-101-D8
124124
crop size: (512,1024)
@@ -132,7 +132,7 @@ Models:
132132
Config: configs/ann/ann_r101-d8_512x1024_80k_cityscapes.py
133133
Weights: https://download.openmmlab.com/mmsegmentation/v0.5/ann/ann_r101-d8_512x1024_80k_cityscapes/ann_r101-d8_512x1024_80k_cityscapes_20200607_013728-aceccc6e.pth
134134
- Name: ann_r50-d8_769x769_80k_cityscapes
135-
In Collection: ann
135+
In Collection: ANN
136136
Metadata:
137137
backbone: R-50-D8
138138
crop size: (769,769)
@@ -146,7 +146,7 @@ Models:
146146
Config: configs/ann/ann_r50-d8_769x769_80k_cityscapes.py
147147
Weights: https://download.openmmlab.com/mmsegmentation/v0.5/ann/ann_r50-d8_769x769_80k_cityscapes/ann_r50-d8_769x769_80k_cityscapes_20200607_044426-cc7ff323.pth
148148
- Name: ann_r101-d8_769x769_80k_cityscapes
149-
In Collection: ann
149+
In Collection: ANN
150150
Metadata:
151151
backbone: R-101-D8
152152
crop size: (769,769)
@@ -160,7 +160,7 @@ Models:
160160
Config: configs/ann/ann_r101-d8_769x769_80k_cityscapes.py
161161
Weights: https://download.openmmlab.com/mmsegmentation/v0.5/ann/ann_r101-d8_769x769_80k_cityscapes/ann_r101-d8_769x769_80k_cityscapes_20200607_013713-a9d4be8d.pth
162162
- Name: ann_r50-d8_512x512_80k_ade20k
163-
In Collection: ann
163+
In Collection: ANN
164164
Metadata:
165165
backbone: R-50-D8
166166
crop size: (512,512)
@@ -182,7 +182,7 @@ Models:
182182
Config: configs/ann/ann_r50-d8_512x512_80k_ade20k.py
183183
Weights: https://download.openmmlab.com/mmsegmentation/v0.5/ann/ann_r50-d8_512x512_80k_ade20k/ann_r50-d8_512x512_80k_ade20k_20200615_014818-26f75e11.pth
184184
- Name: ann_r101-d8_512x512_80k_ade20k
185-
In Collection: ann
185+
In Collection: ANN
186186
Metadata:
187187
backbone: R-101-D8
188188
crop size: (512,512)
@@ -204,7 +204,7 @@ Models:
204204
Config: configs/ann/ann_r101-d8_512x512_80k_ade20k.py
205205
Weights: https://download.openmmlab.com/mmsegmentation/v0.5/ann/ann_r101-d8_512x512_80k_ade20k/ann_r101-d8_512x512_80k_ade20k_20200615_014818-c0153543.pth
206206
- Name: ann_r50-d8_512x512_160k_ade20k
207-
In Collection: ann
207+
In Collection: ANN
208208
Metadata:
209209
backbone: R-50-D8
210210
crop size: (512,512)
@@ -218,7 +218,7 @@ Models:
218218
Config: configs/ann/ann_r50-d8_512x512_160k_ade20k.py
219219
Weights: https://download.openmmlab.com/mmsegmentation/v0.5/ann/ann_r50-d8_512x512_160k_ade20k/ann_r50-d8_512x512_160k_ade20k_20200615_231733-892247bc.pth
220220
- Name: ann_r101-d8_512x512_160k_ade20k
221-
In Collection: ann
221+
In Collection: ANN
222222
Metadata:
223223
backbone: R-101-D8
224224
crop size: (512,512)
@@ -232,7 +232,7 @@ Models:
232232
Config: configs/ann/ann_r101-d8_512x512_160k_ade20k.py
233233
Weights: https://download.openmmlab.com/mmsegmentation/v0.5/ann/ann_r101-d8_512x512_160k_ade20k/ann_r101-d8_512x512_160k_ade20k_20200615_231733-955eb1ec.pth
234234
- Name: ann_r50-d8_512x512_20k_voc12aug
235-
In Collection: ann
235+
In Collection: ANN
236236
Metadata:
237237
backbone: R-50-D8
238238
crop size: (512,512)
@@ -254,7 +254,7 @@ Models:
254254
Config: configs/ann/ann_r50-d8_512x512_20k_voc12aug.py
255255
Weights: https://download.openmmlab.com/mmsegmentation/v0.5/ann/ann_r50-d8_512x512_20k_voc12aug/ann_r50-d8_512x512_20k_voc12aug_20200617_222246-dfcb1c62.pth
256256
- Name: ann_r101-d8_512x512_20k_voc12aug
257-
In Collection: ann
257+
In Collection: ANN
258258
Metadata:
259259
backbone: R-101-D8
260260
crop size: (512,512)
@@ -276,7 +276,7 @@ Models:
276276
Config: configs/ann/ann_r101-d8_512x512_20k_voc12aug.py
277277
Weights: https://download.openmmlab.com/mmsegmentation/v0.5/ann/ann_r101-d8_512x512_20k_voc12aug/ann_r101-d8_512x512_20k_voc12aug_20200617_222246-2fad0042.pth
278278
- Name: ann_r50-d8_512x512_40k_voc12aug
279-
In Collection: ann
279+
In Collection: ANN
280280
Metadata:
281281
backbone: R-50-D8
282282
crop size: (512,512)
@@ -290,7 +290,7 @@ Models:
290290
Config: configs/ann/ann_r50-d8_512x512_40k_voc12aug.py
291291
Weights: https://download.openmmlab.com/mmsegmentation/v0.5/ann/ann_r50-d8_512x512_40k_voc12aug/ann_r50-d8_512x512_40k_voc12aug_20200613_231314-b5dac322.pth
292292
- Name: ann_r101-d8_512x512_40k_voc12aug
293-
In Collection: ann
293+
In Collection: ANN
294294
Metadata:
295295
backbone: R-101-D8
296296
crop size: (512,512)

‎configs/apcnet/apcnet.yml‎

Lines changed: 13 additions & 13 deletions
Original file line numberDiff line numberDiff line change
@@ -1,5 +1,5 @@
11
Collections:
2-
- Name: apcnet
2+
- Name: APCNet
33
Metadata:
44
Training Data:
55
- Cityscapes
@@ -15,7 +15,7 @@ Collections:
1515
Code: https://github.com/Junjun2016/APCNet
1616
Models:
1717
- Name: apcnet_r50-d8_512x1024_40k_cityscapes
18-
In Collection: apcnet
18+
In Collection: APCNet
1919
Metadata:
2020
backbone: R-50-D8
2121
crop size: (512,1024)
@@ -37,7 +37,7 @@ Models:
3737
Config: configs/apcnet/apcnet_r50-d8_512x1024_40k_cityscapes.py
3838
Weights: https://download.openmmlab.com/mmsegmentation/v0.5/apcnet/apcnet_r50-d8_512x1024_40k_cityscapes/apcnet_r50-d8_512x1024_40k_cityscapes_20201214_115717-5e88fa33.pth
3939
- Name: apcnet_r101-d8_512x1024_40k_cityscapes
40-
In Collection: apcnet
40+
In Collection: APCNet
4141
Metadata:
4242
backbone: R-101-D8
4343
crop size: (512,1024)
@@ -59,7 +59,7 @@ Models:
5959
Config: configs/apcnet/apcnet_r101-d8_512x1024_40k_cityscapes.py
6060
Weights: https://download.openmmlab.com/mmsegmentation/v0.5/apcnet/apcnet_r101-d8_512x1024_40k_cityscapes/apcnet_r101-d8_512x1024_40k_cityscapes_20201214_115716-abc9d111.pth
6161
- Name: apcnet_r50-d8_769x769_40k_cityscapes
62-
In Collection: apcnet
62+
In Collection: APCNet
6363
Metadata:
6464
backbone: R-50-D8
6565
crop size: (769,769)
@@ -81,7 +81,7 @@ Models:
8181
Config: configs/apcnet/apcnet_r50-d8_769x769_40k_cityscapes.py
8282
Weights: https://download.openmmlab.com/mmsegmentation/v0.5/apcnet/apcnet_r50-d8_769x769_40k_cityscapes/apcnet_r50-d8_769x769_40k_cityscapes_20201214_115717-2a2628d7.pth
8383
- Name: apcnet_r101-d8_769x769_40k_cityscapes
84-
In Collection: apcnet
84+
In Collection: APCNet
8585
Metadata:
8686
backbone: R-101-D8
8787
crop size: (769,769)
@@ -103,7 +103,7 @@ Models:
103103
Config: configs/apcnet/apcnet_r101-d8_769x769_40k_cityscapes.py
104104
Weights: https://download.openmmlab.com/mmsegmentation/v0.5/apcnet/apcnet_r101-d8_769x769_40k_cityscapes/apcnet_r101-d8_769x769_40k_cityscapes_20201214_115718-b650de90.pth
105105
- Name: apcnet_r50-d8_512x1024_80k_cityscapes
106-
In Collection: apcnet
106+
In Collection: APCNet
107107
Metadata:
108108
backbone: R-50-D8
109109
crop size: (512,1024)
@@ -117,7 +117,7 @@ Models:
117117
Config: configs/apcnet/apcnet_r50-d8_512x1024_80k_cityscapes.py
118118
Weights: https://download.openmmlab.com/mmsegmentation/v0.5/apcnet/apcnet_r50-d8_512x1024_80k_cityscapes/apcnet_r50-d8_512x1024_80k_cityscapes_20201214_115716-987f51e3.pth
119119
- Name: apcnet_r101-d8_512x1024_80k_cityscapes
120-
In Collection: apcnet
120+
In Collection: APCNet
121121
Metadata:
122122
backbone: R-101-D8
123123
crop size: (512,1024)
@@ -131,7 +131,7 @@ Models:
131131
Config: configs/apcnet/apcnet_r101-d8_512x1024_80k_cityscapes.py
132132
Weights: https://download.openmmlab.com/mmsegmentation/v0.5/apcnet/apcnet_r101-d8_512x1024_80k_cityscapes/apcnet_r101-d8_512x1024_80k_cityscapes_20201214_115705-b1ff208a.pth
133133
- Name: apcnet_r50-d8_769x769_80k_cityscapes
134-
In Collection: apcnet
134+
In Collection: APCNet
135135
Metadata:
136136
backbone: R-50-D8
137137
crop size: (769,769)
@@ -145,7 +145,7 @@ Models:
145145
Config: configs/apcnet/apcnet_r50-d8_769x769_80k_cityscapes.py
146146
Weights: https://download.openmmlab.com/mmsegmentation/v0.5/apcnet/apcnet_r50-d8_769x769_80k_cityscapes/apcnet_r50-d8_769x769_80k_cityscapes_20201214_115718-7ea9fa12.pth
147147
- Name: apcnet_r101-d8_769x769_80k_cityscapes
148-
In Collection: apcnet
148+
In Collection: APCNet
149149
Metadata:
150150
backbone: R-101-D8
151151
crop size: (769,769)
@@ -159,7 +159,7 @@ Models:
159159
Config: configs/apcnet/apcnet_r101-d8_769x769_80k_cityscapes.py
160160
Weights: https://download.openmmlab.com/mmsegmentation/v0.5/apcnet/apcnet_r101-d8_769x769_80k_cityscapes/apcnet_r101-d8_769x769_80k_cityscapes_20201214_115716-a7fbc2ab.pth
161161
- Name: apcnet_r50-d8_512x512_80k_ade20k
162-
In Collection: apcnet
162+
In Collection: APCNet
163163
Metadata:
164164
backbone: R-50-D8
165165
crop size: (512,512)
@@ -181,7 +181,7 @@ Models:
181181
Config: configs/apcnet/apcnet_r50-d8_512x512_80k_ade20k.py
182182
Weights: https://download.openmmlab.com/mmsegmentation/v0.5/apcnet/apcnet_r50-d8_512x512_80k_ade20k/apcnet_r50-d8_512x512_80k_ade20k_20201214_115705-a8626293.pth
183183
- Name: apcnet_r101-d8_512x512_80k_ade20k
184-
In Collection: apcnet
184+
In Collection: APCNet
185185
Metadata:
186186
backbone: R-101-D8
187187
crop size: (512,512)
@@ -203,7 +203,7 @@ Models:
203203
Config: configs/apcnet/apcnet_r101-d8_512x512_80k_ade20k.py
204204
Weights: https://download.openmmlab.com/mmsegmentation/v0.5/apcnet/apcnet_r101-d8_512x512_80k_ade20k/apcnet_r101-d8_512x512_80k_ade20k_20201214_115704-c656c3fb.pth
205205
- Name: apcnet_r50-d8_512x512_160k_ade20k
206-
In Collection: apcnet
206+
In Collection: APCNet
207207
Metadata:
208208
backbone: R-50-D8
209209
crop size: (512,512)
@@ -217,7 +217,7 @@ Models:
217217
Config: configs/apcnet/apcnet_r50-d8_512x512_160k_ade20k.py
218218
Weights: https://download.openmmlab.com/mmsegmentation/v0.5/apcnet/apcnet_r50-d8_512x512_160k_ade20k/apcnet_r50-d8_512x512_160k_ade20k_20201214_115706-25fb92c2.pth
219219
- Name: apcnet_r101-d8_512x512_160k_ade20k
220-
In Collection: apcnet
220+
In Collection: APCNet
221221
Metadata:
222222
backbone: R-101-D8
223223
crop size: (512,512)

‎configs/bisenetv1/README.md‎

Lines changed: 1 addition & 1 deletion
Original file line numberDiff line numberDiff line change
@@ -53,7 +53,7 @@ Semantic segmentation requires both rich spatial information and sizeable recept
5353
| BiSeNetV1| R-18-D32 | 512x512 | 160000 | 6.33 | 74.24 | 28.55 | 29.26 | [config](https://github.com/open-mmlab/mmsegmentation/blob/master/configs/bisenetv1/bisenetv1_r18-d32_in1k-pre_lr5e-3_4x4_512x512_160k_coco-stuff164k.py) | [model](https://download.openmmlab.com/mmsegmentation/v0.5/bisenetv1/bisenetv1_r18-d32_in1k-pre_lr5e-3_4x4_512x512_160k_coco-stuff164k/bisenetv1_r18-d32_in1k-pre_lr5e-3_4x4_512x512_160k_coco-stuff164k_20211023_013100-f700dbf7.pth) &#124; [log](https://download.openmmlab.com/mmsegmentation/v0.5/bisenetv1/bisenetv1_r18-d32_in1k-pre_lr5e-3_4x4_512x512_160k_coco-stuff164k/bisenetv1_r18-d32_in1k-pre_lr5e-3_4x4_512x512_160k_coco-stuff164k_20211023_013100.log.json) |
5454
| BiSeNetV1 (No Pretrain) | R-50-D32 | 512x512 | 160000 | - | - | 29.82 | 30.33 | [config](https://github.com/open-mmlab/mmsegmentation/blob/master/configs/bisenetv1/bisenetv1_r50-d32_lr5e-3_4x4_512x512_160k_coco-stuff164k.py) | [model](https://download.openmmlab.com/mmsegmentation/v0.5/bisenetv1/bisenetv1_r50-d32_lr5e-3_4x4_512x512_160k_coco-stuff164k/bisenetv1_r50-d32_lr5e-3_4x4_512x512_160k_coco-stuff164k_20211101_040616-d2bb0df4.pth) &#124; [log](https://download.openmmlab.com/mmsegmentation/v0.5/bisenetv1/bisenetv1_r50-d32_lr5e-3_4x4_512x512_160k_coco-stuff164k/bisenetv1_r50-d32_lr5e-3_4x4_512x512_160k_coco-stuff164k_20211101_040616.log.json) |
5555
| BiSeNetV1 | R-50-D32 | 512x512 | 160000 | 9.28 | 32.60 | 34.88 | 35.37 | [config](https://github.com/open-mmlab/mmsegmentation/blob/master/configs/bisenetv1/bisenetv1_r50-d32_in1k-pre_lr5e-3_4x4_512x512_160k_coco-stuff164k.py) | [model](https://download.openmmlab.com/mmsegmentation/v0.5/bisenetv1/bisenetv1_r50-d32_in1k-pre_lr5e-3_4x4_512x512_160k_coco-stuff164k/bisenetv1_r50-d32_in1k-pre_lr5e-3_4x4_512x512_160k_coco-stuff164k_20211101_181932-66747911.pth) &#124; [log](https://download.openmmlab.com/mmsegmentation/v0.5/bisenetv1/bisenetv1_r50-d32_in1k-pre_lr5e-3_4x4_512x512_160k_coco-stuff164k/bisenetv1_r50-d32_in1k-pre_lr5e-3_4x4_512x512_160k_coco-stuff164k_20211101_181932.log.json) |
56-
| BiSeNetV1(No Pretrain) | R-101-D32 | 512x512 | 160000 | - | - | 31.14 | 31.76 | [config](https://github.com/open-mmlab/mmsegmentation/blob/master/configs/bisenetv1/bisenetv1_r101-d32_lr5e-3_4x4_512x512_160k_coco-stuff164k.py) | [model](https://download.openmmlab.com/mmsegmentation/v0.5/bisenetv1/bisenetv1_r101-d32_lr5e-3_4x4_512x512_160k_coco-stuff164k/bisenetv1_r101-d32_lr5e-3_4x4_512x512_160k_coco-stuff164k_20211102_164147-c6b32c3b.pth) &#124; [log](https://download.openmmlab.com/mmsegmentation/v0.5/bisenetv1/bisenetv1_r101-d32_lr5e-3_4x4_512x512_160k_coco-stuff164k/bisenetv1_r101-d32_lr5e-3_4x4_512x512_160k_coco-stuff164k_20211102_164147.log.json) |
56+
| BiSeNetV1 (No Pretrain) | R-101-D32 | 512x512 | 160000 | - | - | 31.14 | 31.76 | [config](https://github.com/open-mmlab/mmsegmentation/blob/master/configs/bisenetv1/bisenetv1_r101-d32_lr5e-3_4x4_512x512_160k_coco-stuff164k.py) | [model](https://download.openmmlab.com/mmsegmentation/v0.5/bisenetv1/bisenetv1_r101-d32_lr5e-3_4x4_512x512_160k_coco-stuff164k/bisenetv1_r101-d32_lr5e-3_4x4_512x512_160k_coco-stuff164k_20211102_164147-c6b32c3b.pth) &#124; [log](https://download.openmmlab.com/mmsegmentation/v0.5/bisenetv1/bisenetv1_r101-d32_lr5e-3_4x4_512x512_160k_coco-stuff164k/bisenetv1_r101-d32_lr5e-3_4x4_512x512_160k_coco-stuff164k_20211102_164147.log.json) |
5757
| BiSeNetV1 | R-101-D32 | 512x512 | 160000 | 10.36 | 25.25 | 37.38 | 37.99 | [config](https://github.com/open-mmlab/mmsegmentation/blob/master/configs/bisenetv1/bisenetv1_r101-d32_in1k-pre_lr5e-3_4x4_512x512_160k_coco-stuff164k.py) | [model](https://download.openmmlab.com/mmsegmentation/v0.5/bisenetv1/bisenetv1_r101-d32_in1k-pre_lr5e-3_4x4_512x512_160k_coco-stuff164k/bisenetv1_r101-d32_in1k-pre_lr5e-3_4x4_512x512_160k_coco-stuff164k_20211101_225220-28c8f092.pth) &#124; [log](https://download.openmmlab.com/mmsegmentation/v0.5/bisenetv1/bisenetv1_r101-d32_in1k-pre_lr5e-3_4x4_512x512_160k_coco-stuff164k/bisenetv1_r101-d32_in1k-pre_lr5e-3_4x4_512x512_160k_coco-stuff164k_20211101_225220.log.json) |
5858

5959
Note:

0 commit comments

Comments
 (0)