lzz11834
commented
2 years ago Thanks for your letter! Test_img is utilized for the assessment of simulated data. If you want to perform the model on real data, just make test_img the same as noisy_img. The results will not be affected.
------------------ 原始邮件 ------------------ 发件人: "lzz11834/SGIDN" @.>; 发送时间: 2022年6月8日(星期三) 下午5:04 @.>; @.***>; 主题: [lzz11834/SGIDN] how to test for only one noisy image without corresponding clean image? (Issue #1)
Thanks a lot for sharing the denoising codes. When I run the "python test.py" to denoising my HSI dataset using SGIDN, just using this fuction "def test(self, test_img, noisy_img, ckpt_dir):", I only have the noisy_img, but without the test_img, how can I denoising my dataset in this situation? I just want to using your checkpoint to denoising my HSI without training from the begining. Thanks again!
— Reply to this email directly, view it on GitHub, or unsubscribe. You are receiving this because you are subscribed to this thread.Message ID: @.***>
Thanks a lot for sharing the denoising codes. When I run the "python test.py" to denoising my HSI dataset using SGIDN, just using this fuction "def test(self, test_img, noisy_img, ckpt_dir):", I only have the noisy_img, but without the test_img, how can I denoising my dataset in this situation? I just want to using your checkpoint to denoising my HSI without training from the begining. Thanks again!