Giter Club home page Giter Club logo

Comments (3)

swz30 avatar swz30 commented on August 31, 2024

Hi @ivaxsirc

Here are the instructions to perform testing for defocus deblurring: https://github.com/swz30/MIRNetv2/tree/main/Defocus_Deblurring#evaluation

from mirnetv2.

ivaxsirc avatar ivaxsirc commented on August 31, 2024

Thanks for the quick answer

I've tried with two images one of your dataset and other an own image, when i used the script in results only appears your dataset image.

I put the two images in test/DPDD in the four folders inputC inputL inputR target

the anaconda prompt says:

(pytorch111) D:\restauracio\MIRNetv2\Defocus_Deblurring>python test_dual_pixel_defocus_deblur.py --save_images
Setting up [LPIPS] perceptual loss: trunk [alex], v[0.1], spatial [off]
Loading model from: C:\ProgramData\Anaconda3\envs\pytorch111\lib\site-packages\lpips\weights\v0.1\alex.pth
===>Testing using weights: ./pretrained_models/dual_pixel_defocus_deblurring.pth
100%|████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████| 1/1 [00:09<00:00, 9.37s/it]
Traceback (most recent call last):
File "test_dual_pixel_defocus_deblur.py", line 100, in
psnr_indoor, mae_indoor, ssim_indoor, pips_indoor = psnr[indoor_labels-1], mae[indoor_labels-1], ssim[indoor_labels-1], pips[indoor_labels-1]
IndexError: index 8 is out of bounds for axis 0 with size 1

Any idea? Thanks in advance

from mirnetv2.

KKKLeouee avatar KKKLeouee commented on August 31, 2024

感谢你及时的答复

我已经尝试使用两个图像,一个是您的数据集,另一个是自己的图像,当我在结果中使用脚本时,只会出现您的数据集图像。

我把两张图片放在 test/DPDD 的四个文件夹 inputC inputL inputR target

蟒蛇提示说:

(pytorch111) D:\restauracio\MIRNetv2\Defocus_Deblurring>python test_dual_pixel_defocus_deblur.py --save_images 设置 [LPIPS] 感知损失:trunk [alex], v[0.1], spatial [off] 从:C:\ProgramData\ 加载模型Anaconda3\envs\pytorch111\lib\site-packages\lpips\weights\v0.1\alex.pth ===>使用权重进行测试:./pretrained_models/dual_pixel_defocus_deblurring.pth 100%|█████████ ███████████████████████████████████████████████████ ███████████████████████████████████████████████████ ████████████████████████████| 1/1 [00:09<00:00, 9.37s/it] Traceback(最近一次调用最后): 文件“test_dual_pixel_defocus_deblur.py”,第 100 行,在 psnr_indoor, mae_indoor, ssim_indoor, pips_indoor = psnr[indoor_labels-1], mae[indoor_labels-1], ssim[indoor_labels-1], pips[indoor_labels-1] IndexError: index 8 is out of bounds for axis 0 with size 1

任何想法?提前致谢

Hello, I have encountered similar problems, and I would like to ask you how to solve them,thank you

from mirnetv2.

Related Issues (20)

Recommend Projects

  • React photo React

    A declarative, efficient, and flexible JavaScript library for building user interfaces.

  • Vue.js photo Vue.js

    🖖 Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.

  • Typescript photo Typescript

    TypeScript is a superset of JavaScript that compiles to clean JavaScript output.

  • TensorFlow photo TensorFlow

    An Open Source Machine Learning Framework for Everyone

  • Django photo Django

    The Web framework for perfectionists with deadlines.

  • D3 photo 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.

  • Game

    Some thing interesting about game, make everyone happy.

Recommend Org

  • Facebook photo Facebook

    We are working to build community through open source technology. NB: members must have two-factor auth.

  • Microsoft photo Microsoft

    Open source projects and samples from Microsoft.

  • Google photo Google

    Google ❤️ Open Source for everyone.

  • D3 photo D3

    Data-Driven Documents codes.