Giters

sunny2109 / SAFMN

[ICCV 2023] Spatially-Adaptive Feature Modulation for Efficient Image Super-Resolution; runner-up method for the model complexity track in NTIRE2023 Efficient SR challenge

Geek Repo:Geek Repo

Github PK Tool:Github PK Tool

OpenXLab model details

Feynman1999 opened this issue · comments

commented

whhich model do you upload to OpenXlab? can you share the training details?

commented

Hi, thank you for your interest.
We provide x2 and x4 pre-trained models for the OpenXlab demo.

For the training detail, we adopt a multi-stage strategy, which uses different loss functions and learning rate in each stage.
The main used loss functions include L1 Loss, FFT Loss, Perceptual Loss, LDL, and Cosine Similarity Loss.

commented

Hi, thank you for your interest. We provide x2 and x4 pre-trained models for the OpenXlab demo.

For the training detail, we adopt a multi-stage strategy, which uses different loss functions and learning rate in each stage. The main used loss functions include L1 Loss, FFT Loss, Perceptual Loss, LDL, and Cosine Similarity Loss.

thanks, the training config is not in the repo, right?

commented

Hi, thank you for your interest. We provide x2 and x4 pre-trained models for the OpenXlab demo.
For the training detail, we adopt a multi-stage strategy, which uses different loss functions and learning rate in each stage. The main used loss functions include L1 Loss, FFT Loss, Perceptual Loss, LDL, and Cosine Similarity Loss.

thanks, the training config is not in the repo, right?

Yeah, the whole training procedure is similar to the Real-ESRGAN and you can refer to it for implementation.

commented

Hi, thank you for your interest. We provide x2 and x4 pre-trained models for the OpenXlab demo.
For the training detail, we adopt a multi-stage strategy, which uses different loss functions and learning rate in each stage. The main used loss functions include L1 Loss, FFT Loss, Perceptual Loss, LDL, and Cosine Similarity Loss.

thanks, the training config is not in the repo, right?

Yeah, the whole training procedure is similar to the Real-ESRGAN and you can refer to it for implementation.

ok， you use the same config (e.g. kernel，resize, blur probability) as Real-ESRGAN? I want to retrain by myself

commented

Hi, Could you provide the training confs for the SAFMN_Real_x4.pth model ? I would like to train the model on real world data.