7d9f4dcb59
change Tensor.numpy()[0] to float(Tensor) for 0-D tensor case
2022-11-01 14:37:11 +08:00
3be87e0d91
fix ConsinFixmatch bug
2022-10-25 12:04:22 +08:00
944763d7a5
add fixmatch
2022-10-25 12:04:22 +08:00
30cbb18321
update learning_rate.py
2022-10-17 15:51:48 +08:00
2cfd8dd828
add xbm
2022-10-17 15:45:45 +08:00
db80bfb5ab
change return type from float to Constant when self.learning_rate is an float number
2022-09-27 19:46:20 +08:00
6125fa941b
change Constant to ConstLR
2022-09-20 14:45:02 +08:00
cc12db099c
fix Constant learning rate bug
2022-09-20 12:01:52 +08:00
27101d3d88
fix bug for warmup_steps setting
2022-09-19 14:37:15 +08:00
0776f1c700
fix small bugs
2022-09-16 14:40:51 +08:00
57dcf7adb5
fix small bugs
2022-09-16 14:24:34 +08:00
7e072087a5
refactor learningrate.py
2022-09-16 13:59:11 +08:00
7b50ce6585
merge CAE
2022-09-08 08:11:25 +00:00
43410aa852
update config, add amp eval for retrieval
2022-06-21 23:03:56 +08:00
790815f430
refine code and docs
2022-05-05 22:14:07 +08:00
16f910b451
add m1 and baseline config
2022-05-05 19:55:08 +08:00
0b1481402b
merge devevelop
2022-05-05 14:42:06 +08:00
bb13f3c4f5
fix single card dist ( #1889 )
...
* fix single card logit
* fix distillation yaml files
2022-05-05 09:48:56 +08:00
6149e719b3
refine code
2022-04-25 14:14:20 +08:00
674447f63e
refine code
2022-04-25 11:25:44 +08:00
bc6e7f5cf5
update code
2022-04-22 15:26:05 +08:00
9dde9376fb
update code
2022-04-22 15:25:11 +08:00
74b4574367
Support for multiple components when build optimizer
2022-04-22 13:15:49 +08:00
17fd1bc2c0
refine code
2022-04-22 12:00:03 +08:00
0146af28b0
fix code bug
2022-04-21 17:11:07 +08:00
aa26a8c1d8
fix bug for static graph
2022-04-21 16:31:28 +08:00
dfd7749828
refine hard code
2022-04-21 14:37:00 +08:00
41e1a86caf
add center loss
2022-04-21 00:17:54 +08:00
15242df170
refine optimizer/__init__.py
2022-04-20 13:10:31 +08:00
80b8ca3f23
fix optimizer/init.py
2022-04-20 12:16:40 +08:00
3f117428da
fix code
2022-04-20 11:08:42 +08:00
3a1276d315
train_loss_func only used in train mode
2022-04-19 19:54:48 +08:00
24abea151a
support for multi optimizer case
2022-04-19 14:26:42 +08:00
af90cd7c59
update center loss config and related code
2022-04-12 13:07:53 +08:00
509f4d77e3
modify the cifar10 dataset format
2022-02-28 11:47:42 +00:00
cef3cb25d9
update optimizer and some comment
2022-02-28 08:02:51 +00:00
2507be1a51
add deephash configs and dch algorithm
2022-02-23 11:50:39 +00:00
558f03d684
refine code
2021-12-21 06:30:13 +00:00
28061f537c
refine optimizer init logice
2021-12-21 06:28:13 +00:00
b54ee04491
Accelerate dynamic graph amp training
2021-12-20 06:36:56 +00:00
7dcb2d4fd0
fix: raise exception
...
raise exception about using no_weight_decay of AdamW in static graph
2021-09-30 10:48:36 +00:00
c7aeec28e2
fix: support static graph
2021-09-30 06:57:17 +00:00
f91bc7ba0b
perf: add parameter validation ( #1249 )
...
When using warm up, the total epoch num must be greater than warm up epoch num. Otherwise,
there will be raising warning and warm up epoch num will be set to total epoch num.
2021-09-22 14:35:37 +08:00
ba9b708acb
Merge pull request #1174 from TingquanGao/dev/add_adamw
...
feat: add AdamW
2021-09-17 18:53:18 +08:00
94433634c0
fix: fix Linear & support warmup start lr & support Cosine eta_min
...
Support setting warmup start lr and eta_min in Cosine.
Fix bug that Linear can not decay to end_lr when setting warmup.
2021-09-17 18:41:55 +08:00
079434dc5f
feat: add AdamW
2021-09-01 08:07:48 +00:00
0bc5b54d19
fix opt ( #1048 )
2021-07-15 15:19:41 +08:00
9d9cd3719e
add static training ( #1037 )
...
* add static training
* fix typo
* add se fp16
* rm note
* fix loader
* fix cfg
2021-07-15 10:30:07 +08:00
2e6dfa4433
fix logger ( #840 )
...
* fix logger
* fix trainer for int64 on windows
2021-06-15 14:11:50 +08:00
452f532121
add CompCars train and fix bugs
2021-06-03 11:00:47 +08:00
HydrogenSulfate
dongshuilong
zengshao0622
littletomatodonkey
lubin
zhangbo9674
gaotingquan
cuicheng01
littletomatodonkey