smorettini / cnns-on-chb-mit Goto Github PK
View Code? Open in Web Editor NEWThe project is about applying CNNs to EEG data from CHB-MIT to predict seizure
License: GNU General Public License v3.0
The project is about applying CNNs to EEG data from CHB-MIT to predict seizure
License: GNU General Public License v3.0
CNNs-on-CHB-MIT/DataserToSpectogram.py
Line 143 in b85441c
why,there
return (data.shape[1]-t*_SIZE_WINDOW_SPECTOGRAM)*-1
not
return (data.shape[1]-(t * movement+_SIZE_WINDOW_SPECTOGRAM))*-1
Actually I have some questions about your code:
1- In the training why did you choose that it be be for each patient apart I mean why didn't you collect the spectrograms for all patients and use it as input for CNN. .
2- How could I know the number of the training data used?
in DataserToSpectogram.py line 205
if (signalsBlock.shape[0] == 50):
saveSignalsOnDisk(signalsBlock, nSpectogram)
What does 50 mean, is it 50 times of 30 seconds sampling, or is it something else that I don't understand, please forgive me for being a beginner. Thank you very much for your reply
as for the result of codes, is it normal about chb05:sens=77,FPR=2.8;CHB19:sens=79,fpr=4?The result I got was not good,FPR is very far from zero.May I know your final results?thanks!!
while running this code in google colab I am getting this error.
InvalidArgumentError Traceback (most recent call last)
in ()
311
312 if name == 'main':
--> 313 main()
314
3 frames
/usr/local/lib/python3.7/dist-packages/tensorflow/python/eager/execute.py in quick_execute(op_name, num_outputs, inputs, attrs, ctx, name)
53 ctx.ensure_initialized()
54 tensors = pywrap_tfe.TFE_Py_Execute(ctx._handle, device_name, op_name,
---> 55 inputs, attrs, num_outputs)
56 except core._NotOkStatusException as e:
57 if name is not None:
InvalidArgumentError: Graph execution error:
![Capture](https://user-images.git
The full error is attached in the text file below. Please help me to understand this issue.
CNN_training_Error.txt
hubusercontent.com/100077429/169679398-ea893a4a-f382-43a0-a50c-5bd18c4573fa.PNG)
It takes me very long, >20 minutes for one epoch on GPU, is that normal?
Thanks,
Nicole
训练19号病人损失为nan,前边的没问题,不知道是什么问题
What does the "real preictal" mean? I didn't find anything about it in the paper.When you train the CNN,what data will be used? preictal data or real preictal data ?I am really confused. Thank you
Can you please explain why you subtract (30 + 3) minutes at the referenced line? I thought that with SOP = 30 min and SPH = 3 min, we only subtract 3 minutes from the start time of the seizure onset?
https://github.com/MesSem/CNNs-on-CHB-MIT/blob/e1e7a19ded971d521054fd3a063a7943f9c53336/DataserToSpectogram.py#L288
hi
Why don't consider all 13 patients?
and
what are the threshold?
Hello @ritwikmishra ,
Thank you very much for providing such excellent code, I have a question to ask you .
I check the spectrogram generated in the first part of the code and get ”shape: (50, 21, 59, 114)“, what should I do to make the shape generate three-dimensional ?I would be grateful if you could provide some suggestions and look forward to receiving your reply .
Unable to download chb - mit annotation files. Please help me out
threhold 中的 secondsInterictalInTest 的数值是怎么得到的
Question is same as title, what is the meaning of S variable at the referenced line?
https://github.com/MesSem/CNNs-on-CHB-MIT/blob/e1e7a19ded971d521054fd3a063a7943f9c53336/DataserToSpectogram.py#L372
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.