Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Upgrade the CNN for better results 🖼️ #3

Open
BlueBlaze6335 opened this issue Oct 1, 2021 · 8 comments
Open

Upgrade the CNN for better results 🖼️ #3

BlueBlaze6335 opened this issue Oct 1, 2021 · 8 comments
Assignees
Labels
documentation Improvements or additions to documentation enhancement New feature or request hacktoberfest Issue is under Hacktoberfest

Comments

@BlueBlaze6335
Copy link
Collaborator

BlueBlaze6335 commented Oct 1, 2021

🖼️ Update the CNN by adding layers !!

You can add Convolution layers and edit the CNN to generate better results !!

The accuracy is very poor. You can add layers and make changes and tweak the model to generate better results. You can create a new model named "Net-X" , where X is the network number and also plot the training and validation accuracy of your model !! And when you are done update the readme with the results and also the model architecture.

Additional
You can add Validation loss vs. training loss graph and confusion matrix.

@BlueBlaze6335 BlueBlaze6335 added documentation Improvements or additions to documentation enhancement New feature or request labels Oct 1, 2021
@Tanmoydey21
Copy link
Contributor

Tanmoydey21 commented Oct 2, 2021

🖼️ Update the CNN by adding layers !!

You can add Convolution layers and edit the CNN to generate better results !!

The accuracy is very poor. You can add layers and make changes and tweak the model to generate better results. You can create a new model named "Net-X" , where X is the network number and also plot the training and validation accuracy of your model !! And when you are done update the readme with the results and also the model architecture.

Additional You can add Validation loss vs. training loss graph and confusion matrix.

Please assign me this issue so that I can update the CNN.
Thank you.
Dada, My name is Tanmoy dey, from Electronics and communication engineering department, Jalpaiguri government engineering college.

@niloysikdar niloysikdar added the hacktoberfest Issue is under Hacktoberfest label Oct 2, 2021
@BlueBlaze6335
Copy link
Collaborator Author

@Tanmoydey21 I have assigned you this issue !! If you need any help , i guess you know how to reach me. Otherwise you can ask questions in the GDSC JGEC Discord server - Link to text channel

@sebaspv
Copy link
Contributor

sebaspv commented Oct 6, 2021

🖼️ Update the CNN by adding layers !!

You can add Convolution layers and edit the CNN to generate better results !!

The accuracy is very poor. You can add layers and make changes and tweak the model to generate better results. You can create a new model named "Net-X" , where X is the network number and also plot the training and validation accuracy of your model !! And when you are done update the readme with the results and also the model architecture.

Additional You can add Validation loss vs. training loss graph and confusion matrix.

Hi! Can I try this issue? I'd love to try more implementations of CNNs in order to increase the accuracy. Thanks!

@BlueBlaze6335
Copy link
Collaborator Author

@sebaspv I am assigning you !! Happy contributing !!

@BlueBlaze6335
Copy link
Collaborator Author

BlueBlaze6335 commented Oct 9, 2021

Everyone please check the discussion section !!

https://github.com/gdscjgec/ML-Gallery/discussions

@Yasas4D
Copy link

Yasas4D commented Oct 11, 2021

Hi @BlueBlaze6335 Can you please assign me?

@BlueBlaze6335
Copy link
Collaborator Author

@Yasas4D ✌🏻

@Yasas4D
Copy link

Yasas4D commented Oct 12, 2021

Thank you

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
documentation Improvements or additions to documentation enhancement New feature or request hacktoberfest Issue is under Hacktoberfest
Projects
None yet
Development

No branches or pull requests

5 participants