zero-dce_extension's Issues
about learning rate decay strategy
Hi,thank you for your excellent work, but I have a question that why there is no learning rate decay strategy in trianing process? Do you think it will help to improve enhancement?
测试文件运行失败
作者您好!运行测试文件出现_pickle.UnpicklingError: A load persistent id instruction was encountered,but no persistent_load function was specified.不过运行环境按照您推荐的搭建的,请问这个是什么问题?
Why the Wtv is so big?
x
测试结果问题
Why scale factor is 12 in testing but 1 in training?
Hello, authors. Thanks for your excellent work.
I notice that line 20 of lowlight_test.py defines the scale factor as 12, whereas line 105 of lowlight_train.py assumes that the default scale factor is 1.
I would like to know (1) the reason for this inconsistency (2) which one I should adopt for training the model.
Thanks!
x_r总是负值,算法只能做亮度增强,无法使过曝区域变暗
x_r总是负值,根据model.py中增强代码,算法只能做亮度增强,无法使过曝区域变暗,这样看来论文中exp损失没有起到作用,是这样吗,且实验过程中发现图像增强后有些图像会变模糊请问是什么原因,
[Question] abnormal results
Code of MindSpore version of ZeroDCE++
The original link of MindSpore version of ZeroDCE++ is invalid, could you please share it again? Thank you very much!
请问这个需要重新训练吗?
unzip error
report:unzip error..
Images are saturated for adobe5k
Hi,
I trained ZDCE++ in adobe5k for 100 epochs. I had kept 4000 images for training, 500 for validation and 500 for testing. I used the original folder for training. I found the results to be saturated.
One more question is on why we are not checking for validation loss. If we monitor validation loss, can this be improved.
Any help will be appreciated.
Thank you
License
Hey,
could you elaborate on the license? It says research only, but under MIT (which permits commercial use). Thanks for your great work!
[Question] Can curve-based enhancing method handle over-exposure images correction?
Convert PTH model to onnx
Hi,
Could you provide a script to Convert PTH model to onnx?
Thanks!
-Scott
train problems
When training, if it doesn't work, it's just that the terminal inputs Python lowerlight_ After train.py, it ended directly without any errors, but there was no training information. If the answer is provided, we would greatly appreciate it
Where to download DICM dataset?
Hello, when I evaluate the code, there is no file containing the dataset DICM、LIME、MEF infered in paper "Learning to Enhance Low-Light Image via Zero-Reference Deep Curve Estimation", can I ask for a help?
Error while loading the model in macos cpu
After installing all the module in requirements, I get the following error when loading the model
_pickle.UnpicklingError: A load persistent id instruction was encountered
but no persistent_load function was specified.
I checked the forums for this error
https://blog.csdn.net/wavehaha/article/details/114900600
which suggests inconsistency pytorch version
But i am using pytorch=1.0.0 only
Has anybody encountered it? How to load the model on cpu ?
请教
非常感谢开源,对这方面很感兴趣,请问下你这边有做过高曝光的研究吗,想请教下是不是通用的
[nan loss occur]
Hi, nan loss occured when training on some images. How to solve this?
SSIM值相比较Zero-DEC低了
对比了六张图片,SSIM值相比于Zero-DEC都低。
Hello, why did the 512 * 512 image become 504 * 504 after testing? How to use PSNR evaluation in MATLAB when two images have different sizes? I really hope to receive your answer. Thank you
exposure question
I have a question. Is the training data used by the author the same as the one released? I trained my own model, but it has overexposure issues, for example: areas that were originally bright in the image become very bright. However, the official model doesn't have this problem. I'd like to ask how to solve it?
测试以及训练自己的数据集,发现成像偏红
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.