max410011
4dda0672ba
add nas_test_config
2023-06-26 17:15:31 +00:00
410011max
1e6a2eee39
Add pretrained args & fix weight seperate bug
2023-06-20 02:44:21 +08:00
max410011
9e28e47f31
Fix seperate bug
2023-06-19 17:26:30 +00:00
Max
0ed02778c7
Merge branch 'main' into weight-twined-by-M
2023-06-20 01:08:12 +08:00
max410011
c7577aab4d
Add seperate_config
2023-06-19 16:58:45 +00:00
brian1009
1868bd2aca
[fix, NFC] fix evaluation bug when running in non-nas mode. Check if nas is enable when running related command
2023-06-17 12:09:16 +08:00
brian1009
43d74ab8b8
[Refactor, Feature Distillation] refactor models, clean distillation token and add feature distillation
2023-06-17 02:51:32 +08:00
max410011
a172d027f3
Add KD
2023-06-16 17:09:58 +00:00
410011max
2ba43bbca1
update main & test config
2023-06-16 21:49:10 +08:00
410011max
8beda79f83
update training config & test sample config
2023-06-16 21:45:22 +08:00
ningchihuang
4049bd790c
Update main.py
...
Adding set_nas_config after loading pre-trained weights
Modifying DistributedDataParallel(..., find_unused_parameters=True)
2023-06-12 12:31:31 +08:00
max410011
d38229f3fb
update main.py
2023-05-08 12:31:59 +00:00
max410011
39232d1e02
update main.py
2023-05-08 08:33:14 +00:00
brian1009
afadc46e64
[NAS] Modify the infrasturcture for nas training
2023-03-12 17:52:14 +08:00
brian1009
5080409627
rename the sparsity related entry code to main.py and move original one to original_main.py
2023-02-23 15:15:27 +08:00
brian1009
ce08e408dd
Add the basic implementation of the sparsity factory
2023-02-23 15:12:28 +08:00
Byeongho Heo
012a1007cc
Add eval-crop-ratio to args
2022-09-22 11:27:03 +09:00
Hugo Touvron
d64e7e927b
Update main.py
2022-07-29 08:17:08 +02:00
Zhaokai Wang
d48dde3a4d
Fix img_size for DeiT-III
2022-06-24 01:59:42 +08:00
Hugo Touvron
b9a8c27970
fix scaling lr
2022-06-14 10:27:37 +02:00
Hugo Touvron
4da66916c7
Add files via upload
2022-05-08 20:06:44 +02:00
Hugo Touvron
5d5fbbd753
Update main.py
2022-01-29 11:57:22 +01:00
Hugo Touvron
f512394620
Merge pull request #118 from developer0hye/patch-1
...
save best checkpoint
2021-11-21 15:24:12 +01:00
Yonghye Kwon
fdafaf0b8c
save best checkpoint
2021-10-01 17:12:25 +09:00
Maxwell Aladago
2f76ec64fd
BUG Fix: ensure the right loss function is selected when mixtup or cutmix is enabeled
2021-05-02 10:27:25 -04:00
Maxwell Aladago
686507a6a5
BUG Fix: ensure the right loss function is selected when mixtup or cutmix is enabeled
2021-05-02 10:09:58 -04:00
Francisco Massa
ab5715372d
Add deit_base_distilled_patch16_384 ( #55 )
2021-01-18 12:19:47 +01:00
Francisco Massa
1f961b060a
Fix no-weight-decay in optimizer ( #52 )
2021-01-16 11:53:29 +01:00
Francisco Massa
adc7f1e849
Add loss_scaler to checkpoints ( #49 )
...
Ensure bit-wise reproducibility when rescheduling jobs
2021-01-15 10:52:41 +01:00
Francisco Massa
a8e90967a3
Add option to finetune on larger resolution ( #43 )
...
* Add option for finetuning a model
* Fixes
* Keep model in eval mode during finetuning
* Only skip head weights if size mismatch
* Remove finetune-epochs
Might not be needed
* Raise error if distillation + finetune are enabled
2021-01-15 10:13:52 +01:00
Francisco Massa
8eae3269da
Add Knowledge-Distillation ( #42 )
...
* Add knowledge distillation
* Bugfix
* Bugfix
* Make names more readable and use single torch.cat call
* Remove criterion.train() in engine
The teacher should stay in eval mode
* Change default argument for teacher-model
* Return the average of classifiers during inference
* Cleanup unused code
* Add docstring for DistillationLoss
* Remove warnings from newer PyTorch
Also uses more stable variant, instead of using softmax + log, use directly log_softmax
2021-01-13 14:19:23 +01:00
Changlin Li
b06fcba6bf
Support parallelized evaluation ( #24 )
...
* support parallelized evaluation
* remove shuffle arg of loader val, add sampler val in non-dist branch
* replace timm eval sampler with torch sampler
* add logger synchronizing to support parallelized evaluation
* add command line argument dist-eval and warning
2021-01-08 11:05:39 +01:00
Francisco Massa
0c4b8f60bd
Change LICENSE to Apache 2.0
2021-01-08 10:51:58 +01:00
Francisco Massa
dcd888df20
Update default data-path ( #25 )
...
Points to the new valid location
2021-01-07 22:18:54 +01:00
Zhiyuan Chen
0282d2a175
Remove drop block args ( #23 )
...
timm's Vision Transformer does not support drop block
2021-01-07 17:28:41 +01:00
Francisco Massa
1d38fa4c37
Initial commit
2020-12-23 10:47:58 -08:00
