ai-med / relaynet Goto Github PK
View Code? Open in Web Editor NEWRetinal Layers and Fluid Segmentation in Macular OCT scans (code + Pre-trained Model)
License: MIT License
Retinal Layers and Fluid Segmentation in Macular OCT scans (code + Pre-trained Model)
License: MIT License
I would like to ask, does this code only support GPU?
Can't I train under the CPU? What changes do I need to make if it can?
Thanks.
Dear Dr. ROY,
I have a few questions about the details of your paper and code:
According to the Dataset Section of your paper, you are using the Duke SD-OCT data set and the image size is 512 × 740, but I downloaded the data set and found the size of images are 496x768,.
Have you done some kind of preprocessing?
The parameters in Experimental Settings Section are not the same as in your matlab code, such as batch size, momentum and the change of learning rate is from 10^-1 to 10^-3, then 1-^-4, not by an order of magnitude. Which one should I use to reproduce the result in your paper?
Thanks,
Donghuan Lu
Hi, I am trying to deploy EnsembleTest
but it is unable to run due to the missing Loss_TVReg
function which should be in the dagnn wrappers folder, I think. Thank you!
please give me a url link,thank you!
Error using vl_nnconv
operator(): operator(): getWorkspace [out of memory error]
How many memory for the OS and GPU I need to run the prediction?
Thank you very much.
Dear Dr. Roy,
Thanks for your code. I try to reproduce your paper using your code but failed. I have one question that really confused me : in this MATLAB code, the function drawConfusionMatrix didn't calculate the dice coefficient. When I run your code,the value on the diagonal line is basically consistent with the dice coefficient in the paper. But,if I am right, the value on the diagonal line is TP/(TP+FP). Could you please provide more details about the result of dice coefficient in your paper?
Thanks,
Wen Liu
May I know what version of MatConvNet you used?
I am using MatConvNet 1.0-beta25,
When I tried to run EnsembleTest
I got error on this block
net = load('../TrainedModels/NetFold1.mat'),
fnet1 = dagnn.DagNN.loadobj(net);
saying
net =
struct with fields:
net: [1×1 struct]
stats: [1×1 struct]
Error using assert
Invalid model.
Error in dagnn.DagNN.loadobj (line 17)
assert(isfield(s, 'layers'), 'Invalid model.');
Error in EnsembleTest (line 19)
fnet1 = dagnn.DagNN.loadobj(net);
Thank you very much
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.