Open Guaishou74851 opened 4 months ago
In this repo, I release an enhanced checkpoint trained for a long time. This enhanced version obtains better visual results but the CLIPIQA and MUSIQ metrics decrease slightly. After the ECCV deadline, I will upload the checkpoint to reproduce the results in our paper.
Hello @zsyOAOA,
I recently conducted tests using the ResShift model on the ImageNet-Test dataset you provided here. I am pleased to share that the results closely align with the reported values, reinforcing the model's reliability. Below are the specific metrics I obtained:
PSNR: Calculated on the Y channel of the YCbCr space using the calculate_psnr
function in utils/util_image.py
.
SSIM: Evaluated on the Y channel of the YCbCr space using the calculate_ssim
function in utils/util_image.py
.
LPIPS: Evaluated in the RGB formate using the IQA-PyTorch library.
CLIPIQA: Evaluated in the RGB formate using the IQA-PyTorch library.
MUSIQ: Evaluated in the RGB formate using the IQA-PyTorch library.
The results for the ImageNet-Test dataset are satisfactory and align well with the reported figures, which is commendable.
In response to your previous communication, I am eager and optimistic about running the code with the newly uploaded checkpoint to replicate the results documented in your paper. Your efforts in maintaining transparency and reproducibility are much appreciated.
Best regards, Bin Chen
Hi @zsyOAOA,
I am experiencing inconsistencies in the evaluation metrics while testing ResShift with the RealSR65 dataset. Below is a detailed description of my process and the issues encountered:
Data Verification and Command Execution:
./testdata/RealSet65
.Evaluation Metrics Assessment:
Issue and Inquiry:
--seed
option, the scores did not align with the reported values.Questions:
I am keen to understand and rectify these discrepancies and would greatly appreciate your insights.
Thank you for your assistance.