Commit Graph

22 Commits

Author SHA1 Message Date
August
efc389018e
Update environment from CUDA10.2 to CUDA 11.8
Hello author, I have been using the A100 to train the ISNet model. However, I encountered a problem with CUDA incompatibility. To resolve this issue, I spent some time upgrading the CUDA-related packages and conducting compatibility checks. Now, ISNet can run on newer architecture GPUs like the A100/4090. I have exported the upgraded environment configuration to share with you, hoping to help more people avoid the pain of environment upgrading. 
The two environment configuration files I am providing are compatible with CUDA 11.8. Using this environment, ISNet can run on GPUs with Ampere architecture and earlier, such as the 30 series cards, 40 series cards, A100, A10, etc. Except for the H100, which requires a CUDA 12+ environment, CUDA 11.8 currently supports the vast majority of Nvidia graphics cards.
2023-11-20 11:42:31 +08:00
PiggyJerry
f3837183a3 Modify inference.py 2023-01-26 12:10:39 +04:00
Xuebin Qin
996c9495d4
Update isnet.py 2022-11-17 20:57:13 -08:00
PiggyJerry
10657f42e5 correct the error that F1 always equal to 0. 2022-11-04 12:10:53 +04:00
Xuebin Qin
e7c38f4902
Update isnet.py 2022-08-27 22:03:13 -07:00
Xuebin Qin
fdb5f91ad1
Update Inference.py 2022-08-21 12:37:16 -07:00
Xuebin Qin
1646044b43
Update Inference.py 2022-08-21 11:49:39 -07:00
PiggyJerry
3e90a9109d Inference.py modified 2022-08-21 22:33:38 +04:00
PiggyJerry
9a37251d6b Inference.py modified 2022-08-20 19:10:44 +04:00
PiggyJerry
ff195223e5 Inference.py 2022-08-16 14:10:30 +04:00
Xuebin Qin
bdf1a300d4
Merge pull request #9 from PINTO0309/pinto0309work
Avoiding "local variable'i_val' referenced before assignment"
2022-07-30 09:27:58 -07:00
Xuebin Qin
7bf8a3be2d
Merge pull request #6 from deshwalmahesh/main
gt.cuda() creating error for CPU. Change to .to(device)
2022-07-30 09:27:04 -07:00
PiggyJerry
db68ff3480 update data_loader_cache.py 2022-07-27 23:54:20 +04:00
PiggyJerry
6e807f8d10 update data_loader_cache.py 2022-07-27 23:42:02 +04:00
Xuebin Qin
362f4e9699
Update data_loader_cache.py
temporarily solution for training bugs
2022-07-26 19:55:35 -07:00
pinto0309
b365cafded Avoiding "local variable'i_val' referenced before assignment" 2022-07-19 11:34:51 +09:00
Xuebin Qin
85a9a1be60 dis v2 2022-07-17 16:19:20 -07:00
Xuebin Qin
b9e31bdc26 dis v2 2022-07-17 16:14:28 -07:00
Xuebin Qin
7c61e1876d dataloader for inference w/o gt 2022-07-17 13:17:27 -07:00
Xuebin Qin
c1480958ac compute_loss 2022-07-17 11:00:12 -07:00
Mahesh Deshwal
8836d5b4f4 gt.cuda() creating error for CPU. Change to .to(device) 2022-07-17 14:52:08 +05:30
Xuebin Qin
e6455bae38 official release of our isnet and dis5k 2022-07-16 22:56:37 -07:00