hitzhangyu / flw-net Goto Github PK
View Code? Open in Web Editor NEWSimplifying Low-Light Image Enhancement Networks with Relative Loss Functions
Simplifying Low-Light Image Enhancement Networks with Relative Loss Functions
How can I solve the problem of different two-dimensional tensors after enhancing images and highlighting images?
如题
请问一下作者,为什么我用LOL_v1的数据集训练出来的模型,在对v2的测试集做测试的时候,得到的PSNR的值会比测v1的高出三个多点呢,请问训练v1数据集的时候,数据集是怎么划分的呢
今天测试了一下,发现在服务器上运行时,数据加载是正常的,但是经过模型之后,enhanced_image和ill_image图片基本上是纯色,没有内容,但是retouch_image确实正常的灰白亮度图。我服务器上的虚拟环境和本地的是一样的也不行。请问作者,这是什么原因呢
我今天测试了一下,发现在模型函数中,enhance_image = F.softplus(self.e_conv7(x6)),在经过softplus()之前,self.e_conv7(x6)的输出图像是有图像信息的,不是纯色,但是经过softplus()之后,enhance_image 就变成了之前的那个样子,基本上为纯色,没有任何信息,导致网络训练不起来。但是这种问题在我自己的电脑上就没有
Hello.
Do you have plan to offer pre-trained weight?
I found some methods online for calculating the NIQE metric, and I used them to test the enhancement results, but the results I got were inconsistent with the ones provided in your paper. If possible, could you please share the code you used to calculate the NIQE?
Dear author
I would appreciate it if you could publish the entire code and write a note about the code needing a torch version, etc
请问一下作者,为什么我用您给的代码给LOL_v2数据集训练时,PSNR和SSIM的值会从一开始就越来越低直到为负值呢
关于上一个issue里面,使模型应对过饱和/过曝光的调整,请问张老师有打算把更改过的损失函数更新嘛?或者张老师有打算出一篇新论文,在里面启用新的损失函数吗?我尝试删除SSIM和L1进行训练,仍旧是越来越亮。感谢!
filePath = 'F:/FlW-Net/low'
filePath_high = 'F:/FlW-Net/high'
想请教一下,是只修改这个路径成自己的就可以运行了吗,Traceback (most recent call last):
File "F:\FLW-Net\lowlight_test.py", line 132, in
runtime,Loss_psnr,Loss_ssim = lowlight(image_name,image_high_name,expect_mean[i])
File "F:\FLW-Net\lowlight_test.py", line 31, in lowlight
data_lowlight = Image.open(image_path)
File "F:\ANACONDA3\envs\yolov7\lib\site-packages\PIL\Image.py", line 3218, in open
fp = builtins.open(filename, "rb")
FileNotFoundError: [Errno 2] No such file or directory: 'F:/FlW-Net/low337.png',,,为什么运行test.py会报错呢?
A declarative, efficient, and flexible JavaScript library for building user interfaces.
🖖 Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.
TypeScript is a superset of JavaScript that compiles to clean JavaScript output.
An Open Source Machine Learning Framework for Everyone
The Web framework for perfectionists with deadlines.
A PHP framework for web artisans
Bring data to life with SVG, Canvas and HTML. 📊📈🎉
JavaScript (JS) is a lightweight interpreted programming language with first-class functions.
Some thing interesting about web. New door for the world.
A server is a program made to process requests and deliver data to clients.
Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.
Some thing interesting about visualization, use data art
Some thing interesting about game, make everyone happy.
We are working to build community through open source technology. NB: members must have two-factor auth.
Open source projects and samples from Microsoft.
Google ❤️ Open Source for everyone.
Alibaba Open Source for everyone
Data-Driven Documents codes.
China tencent open source team.