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

Update Readme and added ipynb file #7

Merged
merged 5 commits into from
Nov 5, 2020
Merged

Update Readme and added ipynb file #7

merged 5 commits into from
Nov 5, 2020

Conversation

Preetesh21
Copy link
Contributor

@Preetesh21 Preetesh21 commented Nov 5, 2020

Fixes #5

Update Readme and added ipynb file for the issue #5

Copy link
Owner

@Chintan2108 Chintan2108 left a comment

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

@Preetesh21 Great work!
Good inferences on the epoch vs error graphs.

Copy link
Owner

@Chintan2108 Chintan2108 left a comment

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Could you add a comparison of the previous model and this model?
Plot graphs for epoch vs PSNR, epoch vs PC and epoch vs SSIM for both the methods together, so that we can visually analyze it?

@Preetesh21
Copy link
Contributor Author

Sure.

@Preetesh21
Copy link
Contributor Author

Added the Graphs for the Parameters.

@Chintan2108
Copy link
Owner

Hi @Preetesh21
Good work on the graphs. We need to compare the performance of the two models.
Please have only these three graphs in the readme:

  1. PSNR vs Epoch (single graph)
    a. One curve for validation of earlier model
    b. One curve for validation of skewed-data model

  2. PC vs Epoch (single graph)
    a. One curve for validation of earlier model
    b. One curve for validation of skewed-data model

  3. SSIM vs Epoch (single graph)
    a. One curve for validation of earlier model
    b. One curve for validation of skewed-data model

This way we can compare the performance of both models for each of the parameters. Since we want to compare their predictive capabilities, we don't need to have the training curve, only the validation curve is required.

@Preetesh21
Copy link
Contributor Author

ok sure.

@Preetesh21
Copy link
Contributor Author

Done the requested changes.

Copy link
Owner

@Chintan2108 Chintan2108 left a comment

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Great work @Preetesh21

@Chintan2108 Chintan2108 merged commit 700da29 into Chintan2108:master Nov 5, 2020
@Chintan2108
Copy link
Owner

give @Preetesh21 25 points

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
None yet
Projects
None yet
Development

Successfully merging this pull request may close these issues.

Train the model using new data created in issue #4
2 participants