Comments (4)
Symbadian
commented on August 18, 2024
Hey Li,
I solved it pal, change the following in your code it is causing some issues on the 3dcnn.py file in the model section! I am running spyder 5.0.0 whilst researching I found the solution here at the very bottom: https://stackoverflow.com/questions/49079115/valueerror-negative-dimension-size-caused-by-subtracting-2-from-1-for-max-pool
Change the max pooling to this and edit all of the section in the model with the padding to padding='same':
""" model.add(MaxPooling3D(pool_size=(3, 3, 3), padding='same'))''''
apparently, the images are gradually getting smaller making it challenging for the convolution processing to occur! let me know when you made the amendments I will select the start ratings!
from 3dcnn-with-keras.
paolo626
commented on August 18, 2024
Hey MatParr,
I am sorry that this project is not fully understood by me because it fixes from another project. In this period, I am ready for a recruit. When it finished after this month, I will work with you on this project.
from 3dcnn-with-keras.
Symbadian
commented on August 18, 2024
No worries mate, I solve it the padding was causing the issues check the errors I posted to the forum, it can save someone else some time!
I am not sure the padding method you deployed is still in effect or was upgraded! That’s the thing, when the model is functional and packages upgrade they cause all
Sorts of issues!
I am observing the metrics from this model today! Thanx once more!
Cheers!
From: liupeng678 ***@***.***>
Date: Friday, 16 April 2021 at 06:49
To: liupeng678/3DCNN-with-keras ***@***.***>
Cc: MatParr ***@***.***>, Author ***@***.***>
Subject: Re: [liupeng678/3DCNN-with-keras] Errors With The Model 2dcnn and 3dcnn (#3)
Hey MatParr,
I am sorry that this project is not fully understood by me because it fixes from another project. In this period, I am ready for a recruit. When it finished after this month, I will work with you on this project.
—
You are receiving this because you authored the thread.
Reply to this email directly, view it on GitHub<#3 (comment)>, or unsubscribe<https://github.com/notifications/unsubscribe-auth/AL7WSHK46ULHJV66CSXABJ3TI7FWBANCNFSM427CVUOQ>.
from 3dcnn-with-keras.
Symbadian
commented on August 18, 2024
Ohh by the way I do come across more stuff I will let you know okay!
I will be experimenting today and breaking stuff and fixing stuff to test is functionality! I see you didn’t implement stratify nor scaling for normalisations via the testing, any reason? Is it that the more is computationally heavy or you are unaware of it? I am trying to understand your pattern of though here!
Also is there any specific reason for you choosing the hold out method “train test split” and not kfold for higher accuracy’s?
Cheer to positive perspectives!
Matt.
…________________________________
From: mm gp ***@***.***>
Sent: Friday, April 16, 2021 7:03:07 AM
To: liupeng678/3DCNN-with-keras ***@***.***>; liupeng678/3DCNN-with-keras ***@***.***>
Cc: Author ***@***.***>
Subject: Re: [liupeng678/3DCNN-with-keras] Errors With The Model 2dcnn and 3dcnn (#3)
No worries mate, I solve it the padding was causing the issues check the errors I posted to the forum, it can save someone else some time!
I am not sure the padding method you deployed is still in effect or was upgraded! That’s the thing, when the model is functional and packages upgrade they cause all
Sorts of issues!
I am observing the metrics from this model today! Thanx once more!
Cheers!
From: liupeng678 ***@***.***>
Date: Friday, 16 April 2021 at 06:49
To: liupeng678/3DCNN-with-keras ***@***.***>
Cc: MatParr ***@***.***>, Author ***@***.***>
Subject: Re: [liupeng678/3DCNN-with-keras] Errors With The Model 2dcnn and 3dcnn (#3)
Hey MatParr,
I am sorry that this project is not fully understood by me because it fixes from another project. In this period, I am ready for a recruit. When it finished after this month, I will work with you on this project.
—
You are receiving this because you authored the thread.
Reply to this email directly, view it on GitHub<#3 (comment)>, or unsubscribe<https://github.com/notifications/unsubscribe-auth/AL7WSHK46ULHJV66CSXABJ3TI7FWBANCNFSM427CVUOQ>.
from 3dcnn-with-keras.
Related Issues (5)
- 请问怎么测试模型 HOT 2
- pritning the output results HOT 7
- UCF101 问题？
- No Metrics For Model HOT 7
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.
from 3dcnn-with-keras.