forked from open-mmlab/mmpretrain
-
Notifications
You must be signed in to change notification settings - Fork 0
/
metafile.yml
367 lines (366 loc) · 12.7 KB
/
metafile.yml
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
330
331
332
333
334
335
336
337
338
339
340
341
342
343
344
345
346
347
348
349
350
351
352
353
354
355
356
357
358
359
360
361
362
363
364
365
366
367
Collections:
- Name: MAE
Metadata:
Training Data: ImageNet-1k
Training Techniques:
- AdamW
Training Resources: 8x A100-80G GPUs
Architecture:
- ViT
Paper:
Title: Masked Autoencoders Are Scalable Vision Learners
URL: https://arxiv.org/abs/2111.06377
README: configs/mae/README.md
Models:
- Name: mae_vit-base-p16_8xb512-amp-coslr-300e_in1k
Metadata:
Epochs: 300
Batch Size: 4096
FLOPs: 17581972224
Parameters: 111907840
Training Data: ImageNet-1k
In Collection: MAE
Results: null
Weights: https://download.openmmlab.com/mmselfsup/1.x/mae/mae_vit-base-p16_8xb512-fp16-coslr-300e_in1k/mae_vit-base-p16_8xb512-coslr-300e-fp16_in1k_20220829-c2cf66ba.pth
Config: configs/mae/mae_vit-base-p16_8xb512-amp-coslr-300e_in1k.py
Downstream:
- vit-base-p16_mae-300e-pre_8xb2048-linear-coslr-90e_in1k
- vit-base-p16_mae-300e-pre_8xb128-coslr-100e_in1k
- Name: mae_vit-base-p16_8xb512-amp-coslr-400e_in1k
Metadata:
Epochs: 400
Batch Size: 4096
FLOPs: 17581972224
Parameters: 111907840
Training Data: ImageNet-1k
In Collection: MAE
Results: null
Weights: https://download.openmmlab.com/mmselfsup/1.x/mae/mae_vit-base-p16_8xb512-fp16-coslr-400e_in1k/mae_vit-base-p16_8xb512-coslr-400e-fp16_in1k_20220825-bc79e40b.pth
Config: configs/mae/mae_vit-base-p16_8xb512-amp-coslr-400e_in1k.py
Downstream:
- vit-base-p16_mae-400e-pre_8xb2048-linear-coslr-90e_in1k
- vit-base-p16_mae-400e-pre_8xb128-coslr-100e_in1k
- Name: mae_vit-base-p16_8xb512-amp-coslr-800e_in1k
Metadata:
Epochs: 800
Batch Size: 4096
FLOPs: 17581972224
Parameters: 111907840
Training Data: ImageNet-1k
In Collection: MAE
Results: null
Weights: https://download.openmmlab.com/mmselfsup/1.x/mae/mae_vit-base-p16_8xb512-fp16-coslr-800e_in1k/mae_vit-base-p16_8xb512-coslr-800e-fp16_in1k_20220825-5d81fbc4.pth
Config: configs/mae/mae_vit-base-p16_8xb512-amp-coslr-800e_in1k.py
Downstream:
- vit-base-p16_mae-800e-pre_8xb2048-linear-coslr-90e_in1k
- vit-base-p16_mae-800e-pre_8xb128-coslr-100e_in1k
- Name: mae_vit-base-p16_8xb512-amp-coslr-1600e_in1k
Metadata:
Epochs: 1600
Batch Size: 4096
FLOPs: 17581972224
Parameters: 111907840
Training Data: ImageNet-1k
In Collection: MAE
Results: null
Weights: https://download.openmmlab.com/mmselfsup/1.x/mae/mae_vit-base-p16_8xb512-fp16-coslr-1600e_in1k/mae_vit-base-p16_8xb512-fp16-coslr-1600e_in1k_20220825-f7569ca2.pth
Config: configs/mae/mae_vit-base-p16_8xb512-amp-coslr-1600e_in1k.py
Downstream:
- vit-base-p16_mae-1600e-pre_8xb2048-linear-coslr-90e_in1k
- vit-base-p16_mae-1600e-pre_8xb128-coslr-100e_in1k
- Name: mae_vit-large-p16_8xb512-amp-coslr-400e_in1k
Metadata:
Epochs: 400
Batch Size: 4096
FLOPs: 61603111936
Parameters: 329541888
Training Data: ImageNet-1k
In Collection: MAE
Results: null
Weights: https://download.openmmlab.com/mmselfsup/1.x/mae/mae_vit-large-p16_8xb512-fp16-coslr-400e_in1k/mae_vit-large-p16_8xb512-fp16-coslr-400e_in1k_20220825-b11d0425.pth
Config: configs/mae/mae_vit-large-p16_8xb512-amp-coslr-400e_in1k.py
Downstream:
- vit-large-p16_mae-400e-pre_8xb2048-linear-coslr-90e_in1k
- vit-large-p16_mae-400e-pre_8xb128-coslr-50e_in1k
- Name: mae_vit-large-p16_8xb512-amp-coslr-800e_in1k
Metadata:
Epochs: 800
Batch Size: 4096
FLOPs: 61603111936
Parameters: 329541888
Training Data: ImageNet-1k
In Collection: MAE
Results: null
Weights: https://download.openmmlab.com/mmselfsup/1.x/mae/mae_vit-large-p16_8xb512-fp16-coslr-800e_in1k/mae_vit-large-p16_8xb512-fp16-coslr-800e_in1k_20220825-df72726a.pth
Config: configs/mae/mae_vit-large-p16_8xb512-amp-coslr-800e_in1k.py
Downstream:
- vit-large-p16_mae-800e-pre_8xb2048-linear-coslr-90e_in1k
- vit-large-p16_mae-800e-pre_8xb128-coslr-50e_in1k
- Name: mae_vit-large-p16_8xb512-amp-coslr-1600e_in1k
Metadata:
Epochs: 1600
Batch Size: 4096
FLOPs: 61603111936
Parameters: 329541888
Training Data: ImageNet-1k
In Collection: MAE
Results: null
Weights: https://download.openmmlab.com/mmselfsup/1.x/mae/mae_vit-large-p16_8xb512-fp16-coslr-1600e_in1k/mae_vit-large-p16_8xb512-fp16-coslr-1600e_in1k_20220825-cc7e98c9.pth
Config: configs/mae/mae_vit-large-p16_8xb512-amp-coslr-1600e_in1k.py
Downstream:
- vit-large-p16_mae-1600e-pre_8xb2048-linear-coslr-90e_in1k
- vit-large-p16_mae-1600e-pre_8xb128-coslr-50e_in1k
- Name: mae_vit-huge-p16_8xb512-amp-coslr-1600e_in1k
Metadata:
Epochs: 1600
Batch Size: 4096
FLOPs: 167400741120
Parameters: 657074508
Training Data: ImageNet-1k
In Collection: MAE
Results: null
Weights: https://download.openmmlab.com/mmselfsup/1.x/mae/mae_vit-huge-p16_8xb512-fp16-coslr-1600e_in1k/mae_vit-huge-p16_8xb512-fp16-coslr-1600e_in1k_20220916-ff848775.pth
Config: configs/mae/mae_vit-huge-p14_8xb512-amp-coslr-1600e_in1k.py
Downstream:
- vit-huge-p14_mae-1600e-pre_8xb128-coslr-50e_in1k
- vit-huge-p14_mae-1600e-pre_32xb8-coslr-50e_in1k-448px
- Name: vit-base-p16_mae-300e-pre_8xb128-coslr-100e_in1k
Metadata:
Epochs: 100
Batch Size: 1024
FLOPs: 17581215744
Parameters: 86566120
Training Data: ImageNet-1k
In Collection: MAE
Results:
- Task: Image Classification
Dataset: ImageNet-1k
Metrics:
Top 1 Accuracy: 83.1
Weights: null
Config: configs/mae/benchmarks/vit-base-p16_8xb128-coslr-100e_in1k.py
- Name: vit-base-p16_mae-400e-pre_8xb128-coslr-100e_in1k
Metadata:
Epochs: 100
Batch Size: 1024
FLOPs: 17581215744
Parameters: 86566120
Training Data: ImageNet-1k
In Collection: MAE
Results:
- Task: Image Classification
Dataset: ImageNet-1k
Metrics:
Top 1 Accuracy: 83.3
Weights: null
Config: configs/mae/benchmarks/vit-base-p16_8xb128-coslr-100e_in1k.py
- Name: vit-base-p16_mae-800e-pre_8xb128-coslr-100e_in1k
Metadata:
Epochs: 100
Batch Size: 1024
FLOPs: 17581215744
Parameters: 86566120
Training Data: ImageNet-1k
In Collection: MAE
Results:
- Task: Image Classification
Dataset: ImageNet-1k
Metrics:
Top 1 Accuracy: 83.3
Weights: null
Config: configs/mae/benchmarks/vit-base-p16_8xb128-coslr-100e_in1k.py
- Name: vit-base-p16_mae-1600e-pre_8xb128-coslr-100e_in1k
Metadata:
Epochs: 100
Batch Size: 1024
FLOPs: 17581215744
Parameters: 86566120
Training Data: ImageNet-1k
In Collection: MAE
Results:
- Task: Image Classification
Dataset: ImageNet-1k
Metrics:
Top 1 Accuracy: 83.5
Weights: https://download.openmmlab.com/mmselfsup/1.x/mae/mae_vit-base-p16_8xb512-fp16-coslr-1600e_in1k/vit-base-p16_ft-8xb128-coslr-100e_in1k/vit-base-p16_ft-8xb128-coslr-100e_in1k_20220825-cf70aa21.pth
Config: configs/mae/benchmarks/vit-base-p16_8xb128-coslr-100e_in1k.py
- Name: vit-base-p16_mae-300e-pre_8xb2048-linear-coslr-90e_in1k
Metadata:
Epochs: 90
Batch Size: 16384
FLOPs: 17581972992
Parameters: 86567656
Training Data: ImageNet-1k
In Collection: MAE
Results:
- Task: Image Classification
Dataset: ImageNet-1k
Metrics:
Top 1 Accuracy: 60.8
Weights: null
Config: configs/mae/benchmarks/vit-base-p16_8xb2048-linear-coslr-90e_in1k.py
- Name: vit-base-p16_mae-400e-pre_8xb2048-linear-coslr-90e_in1k
Metadata:
Epochs: 90
Batch Size: 16384
FLOPs: 17581972992
Parameters: 86567656
Training Data: ImageNet-1k
In Collection: MAE
Results:
- Task: Image Classification
Dataset: ImageNet-1k
Metrics:
Top 1 Accuracy: 62.5
Weights: null
Config: configs/mae/benchmarks/vit-base-p16_8xb2048-linear-coslr-90e_in1k.py
- Name: vit-base-p16_mae-800e-pre_8xb2048-linear-coslr-90e_in1k
Metadata:
Epochs: 90
Batch Size: 16384
FLOPs: 17581972992
Parameters: 86567656
Training Data: ImageNet-1k
In Collection: MAE
Results:
- Task: Image Classification
Dataset: ImageNet-1k
Metrics:
Top 1 Accuracy: 65.1
Weights: null
Config: configs/mae/benchmarks/vit-base-p16_8xb2048-linear-coslr-90e_in1k.py
- Name: vit-base-p16_mae-1600e-pre_8xb2048-linear-coslr-90e_in1k
Metadata:
Epochs: 90
Batch Size: 16384
FLOPs: 17581972992
Parameters: 86567656
Training Data: ImageNet-1k
In Collection: MAE
Results:
- Task: Image Classification
Dataset: ImageNet-1k
Metrics:
Top 1 Accuracy: 67.1
Weights: null
Config: configs/mae/benchmarks/vit-base-p16_8xb2048-linear-coslr-90e_in1k.py
- Name: vit-large-p16_mae-400e-pre_8xb128-coslr-50e_in1k
Metadata:
Epochs: 50
Batch Size: 1024
FLOPs: 61602103296
Parameters: 304324584
Training Data: ImageNet-1k
In Collection: MAE
Results:
- Task: Image Classification
Dataset: ImageNet-1k
Metrics:
Top 1 Accuracy: 85.2
Weights: null
Config: configs/mae/benchmarks/vit-large-p16_8xb128-coslr-50e_in1k.py
- Name: vit-large-p16_mae-800e-pre_8xb128-coslr-50e_in1k
Metadata:
Epochs: 50
Batch Size: 1024
FLOPs: 61602103296
Parameters: 304324584
Training Data: ImageNet-1k
In Collection: MAE
Results:
- Task: Image Classification
Dataset: ImageNet-1k
Metrics:
Top 1 Accuracy: 85.4
Weights: null
Config: configs/mae/benchmarks/vit-large-p16_8xb128-coslr-50e_in1k.py
- Name: vit-large-p16_mae-1600e-pre_8xb128-coslr-50e_in1k
Metadata:
Epochs: 50
Batch Size: 1024
FLOPs: 61602103296
Parameters: 304324584
Training Data: ImageNet-1k
In Collection: MAE
Results:
- Task: Image Classification
Dataset: ImageNet-1k
Metrics:
Top 1 Accuracy: 85.7
Weights: null
Config: configs/mae/benchmarks/vit-large-p16_8xb128-coslr-50e_in1k.py
- Name: vit-large-p16_mae-400e-pre_8xb2048-linear-coslr-90e_in1k
Metadata:
Epochs: 90
Batch Size: 16384
FLOPs: 61603112960
Parameters: 304326632
Training Data: ImageNet-1k
In Collection: MAE
Results:
- Task: Image Classification
Dataset: ImageNet-1k
Metrics:
Top 1 Accuracy: 70.7
Weights: null
Config: configs/mae/benchmarks/vit-large-p16_8xb2048-linear-coslr-90e_in1k.py
- Name: vit-large-p16_mae-800e-pre_8xb2048-linear-coslr-90e_in1k
Metadata:
Epochs: 90
Batch Size: 16384
FLOPs: 61603112960
Parameters: 304326632
Training Data: ImageNet-1k
In Collection: MAE
Results:
- Task: Image Classification
Dataset: ImageNet-1k
Metrics:
Top 1 Accuracy: 73.7
Weights: null
Config: configs/mae/benchmarks/vit-large-p16_8xb2048-linear-coslr-90e_in1k.py
- Name: vit-large-p16_mae-1600e-pre_8xb2048-linear-coslr-90e_in1k
Metadata:
Epochs: 90
Batch Size: 16384
FLOPs: 61603112960
Parameters: 304326632
Training Data: ImageNet-1k
In Collection: MAE
Results:
- Task: Image Classification
Dataset: ImageNet-1k
Metrics:
Top 1 Accuracy: 75.5
Weights: null
Config: configs/mae/benchmarks/vit-large-p16_8xb2048-linear-coslr-90e_in1k.py
- Name: vit-huge-p14_mae-1600e-pre_8xb128-coslr-50e_in1k
Metadata:
Epochs: 50
Batch Size: 1024
FLOPs: 167399096320
Parameters: 632043240
Training Data: ImageNet-1k
In Collection: MAE
Results:
- Task: Image Classification
Dataset: ImageNet-1k
Metrics:
Top 1 Accuracy: 86.9
Weights: https://download.openmmlab.com/mmselfsup/1.x/mae/mae_vit-huge-p16_8xb512-fp16-coslr-1600e_in1k/vit-huge-p16_ft-8xb128-coslr-50e_in1k/vit-huge-p16_ft-8xb128-coslr-50e_in1k_20220916-0bfc9bfd.pth
Config: configs/mae/benchmarks/vit-huge-p14_8xb128-coslr-50e_in1k.py
- Name: vit-huge-p14_mae-1600e-pre_32xb8-coslr-50e_in1k-448px
Metadata:
Epochs: 50
Batch Size: 256
FLOPs: 732131983360
Parameters: 633026280
Training Data: ImageNet-1k
In Collection: MAE
Results:
- Task: Image Classification
Dataset: ImageNet-1k
Metrics:
Top 1 Accuracy: 87.3
Weights: https://download.openmmlab.com/mmselfsup/1.x/mae/mae_vit-huge-p16_8xb512-fp16-coslr-1600e_in1k/vit-huge-p16_ft-32xb8-coslr-50e_in1k-448/vit-huge-p16_ft-32xb8-coslr-50e_in1k-448_20220916-95b6a0ce.pth
Config: configs/mae/benchmarks/vit-huge-p14_32xb8-coslr-50e_in1k-448px.py