Using the given model，PSNR-u is lower than the cvpr repoerted

[LiuzhuForFun]

def range_compressor_tensor(x): const_1 = torch.from_numpy(np.array(1.0)).cuda() const_5000 = torch.from_numpy(np.array(5000.0)).cuda() return (torch.log(const_1 + const_5000 * x)) / torch.log(const_1 + const_5000) Is this fuction not correct? Thanks

[wensongc]

大佬，我用这里的pt文件，复现的结果比论文低，请问你复现出来论文的结果了吗？

[LiuzhuForFun]

可以

---Original--- From: @.> Date: Sun, Apr 24, 2022 11:13 AM To: @.>; Cc: @.>;"State @.>; Subject: Re: [qingsenyangit/AHDRNet] Using the given model，PSNR-u is lower than the cvpr repoerted (Issue #14)

大佬，我用这里的pt文件，复现的结果比论文低，请问你复现出来论文的结果了吗？

— Reply to this email directly, view it on GitHub, or unsubscribe. You are receiving this because you modified the open/close state.Message ID: @.***>

[wensongc]

谢谢大佬回复，是需要继续训练还是直接用这里面的pt文件就可以呀？

[LiuzhuForFun]

重新训练一下吧

[LiuzhuForFun]

通过调学习率能收敛

[wensongc]

明白了，感谢大佬！