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
..
__pycache__	official release of our isnet and dis5k	2022-07-16 22:56:37 -07:00
models	Update isnet.py	2022-11-17 20:57:13 -08:00
basics.py	official release of our isnet and dis5k	2022-07-16 22:56:37 -07:00
data_loader_cache.py	update data_loader_cache.py	2022-07-27 23:54:20 +04:00
environment_cu118.yaml	Update environment from CUDA10.2 to CUDA 11.8	2023-11-20 11:42:31 +08:00
hce_metric_main.py	official release of our isnet and dis5k	2022-07-16 22:56:37 -07:00
Inference.py	Modify inference.py	2023-01-26 12:10:39 +04:00
pytorch18.yml	official release of our isnet and dis5k	2022-07-16 22:56:37 -07:00
requirements_cu118.txt	Update environment from CUDA10.2 to CUDA 11.8	2023-11-20 11:42:31 +08:00
requirements.txt	official release of our isnet and dis5k	2022-07-16 22:56:37 -07:00
train_valid_inference_main.py	correct the error that F1 always equal to 0.	2022-11-04 12:10:53 +04:00