Comments (6)
2倍mod2, 3倍mod3, 4倍mod4
from hat.
我刚刚按照您给的方法进行了新的测试,使用Set5数据集测试了HAT_SRx2.pth、HAT_SRx3.pth、HAT_SRx4.pth,结果如下:
2023-03-01 19:09:39,193 INFO: Loading HAT model from ./experiments/pretrained_models/HAT_SRx2.pth, with param key: [params_ema]. 2023-03-01 19:09:39,283 INFO: Model [HATModel] is created. 2023-03-01 19:09:39,283 INFO: Testing Set5... 2023-03-01 19:09:42,956 INFO: Validation Set5 # psnr: 38.6039 Best: 38.6039 @ HAT_SRx2 iter # ssim: 0.9629 Best: 0.9629 @ HAT_SRx2 iter
2023-03-01 19:12:24,515 INFO: Loading HAT model from ./experiments/pretrained_models/HAT_SRx3.pth, with param key: [params_ema]. 2023-03-01 19:12:24,607 INFO: Model [HATModel] is created. 2023-03-01 19:12:24,607 INFO: Testing Set5... 2023-03-01 19:12:26,698 INFO: Validation Set5 # psnr: 35.0567 Best: 35.0567 @ HAT_SRx3 iter # ssim: 0.9328 Best: 0.9328 @ HAT_SRx3 iter
2023-03-01 19:12:56,934 INFO: Loading HAT model from ./experiments/pretrained_models/HAT_SRx4.pth, with param key: [params_ema]. 2023-03-01 19:12:57,023 INFO: Model [HATModel] is created. 2023-03-01 19:12:57,023 INFO: Testing Set5... 2023-03-01 19:12:59,043 INFO: Validation Set5 # psnr: 33.0383 Best: 33.0383 @ HAT_SRx4 iter # ssim: 0.9055 Best: 0.9055 @ HAT_SRx4 iter
- x2的测试结果为PSNR=38.60,SSIM=0.9629,PSNR比论文少0.03,SSIM比论文少0.0001。
- x3的测试结果为PSNR=35.06,SSIM=0.9328,PSNR与论文一致,SSIM比论文少0.0001。
- x4的测试结果为PSNR=33.04,SSIM=0.9055,PSNR与论文一致,SSIM比论文少0.0001。
请问结果有差别可能的原因是什么?测试的结果在可接受的范围之内吗?您认为测试结果在±多少范围内可接受?期待您的回答!
from hat.
目前这个测试结果应该可接受的。不过有0.03的差异确实还是挺奇怪的。我这边测试是没问题的,可能数据来源不完全一样,有一些细微差别。你可以先用release的结果验证一下计算函数是不是有区别。
from hat.
我同意您的观点,可能是数据来源的问题或是计算函数的问题,但我更认同前者。
我上次测试使用的是RCAN下载的数据集,他们的数据集是使用matlab生成的GTmod2/3/4/8,见该链接
请问您在准备测试集的时候使用的方法和RCAN一致吗?如果方便的话可以分享一下程序吗?
期待您的回复!
from hat.
https://github.com/XPixelGroup/BasicSR/blob/master/scripts/matlab_scripts/generate_bicubic_img.m
from hat.
感谢您的回复,我使用BasicSR的原图,使用matlab生成GT与Bicubic,分别在Set5、Set14、BSD100、Urban100、Manga109上测试x2x3x4,发现结果均与您的结果一致,再次感谢你们精彩的工作!
from hat.
Related Issues (20)
- fine tuning Real_HAT_mse model with paired dataset HOT 2
- Scale by 2 or 8?
- 单通道训练问题 HOT 3
- RuntimeError: NCCL invalid usage HOT 1
- Having problem while Training on low resolution images
- How to use the package in Mac with M1/M2 chip
- How you calculate macs and params?
- Inquiry on HAT Application for Same-Size Super Resolution HOT 5
- How to modify basicsr code and apply to HAT model? HOT 2
- Can't Reproduce the Results of SRx3
- How can I calculate PSNR&SSIM with only LR images in HAT_SRX4_ImageNet-LR.yml?Thank you!
- Does the Real-HAT have a small version like HAT-S? HOT 6
- Half precision (fp16) Training and Inference of the HAT models HOT 3
- TypeError: calculate_psnr() missing 1 required positional argument: 'img2' HOT 2
- Tại bài hát mới
- Question about the forward method HOT 3
- 1x模型权重
- How to limit the range of the super-resolved image HOT 2
- LAM可视化
- Value of RPI in hat_arch.py value
Recommend Projects
-
React
A declarative, efficient, and flexible JavaScript library for building user interfaces.
-
Vue.js
🖖 Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.
-
Typescript
TypeScript is a superset of JavaScript that compiles to clean JavaScript output.
-
TensorFlow
An Open Source Machine Learning Framework for Everyone
-
Django
The Web framework for perfectionists with deadlines.
-
Laravel
A PHP framework for web artisans
-
D3
Bring data to life with SVG, Canvas and HTML. 📊📈🎉
-
Recommend Topics
-
javascript
JavaScript (JS) is a lightweight interpreted programming language with first-class functions.
-
web
Some thing interesting about web. New door for the world.
-
server
A server is a program made to process requests and deliver data to clients.
-
Machine learning
Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.
-
Visualization
Some thing interesting about visualization, use data art
-
Game
Some thing interesting about game, make everyone happy.
Recommend Org
-
Facebook
We are working to build community through open source technology. NB: members must have two-factor auth.
-
Microsoft
Open source projects and samples from Microsoft.
-
Google
Google ❤️ Open Source for everyone.
-
Alibaba
Alibaba Open Source for everyone
-
D3
Data-Driven Documents codes.
-
Tencent
China tencent open source team.
from hat.