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

Unable to replicate results of convLSTM #741

Closed
mulvey-g opened this issue Dec 14, 2021 · 2 comments
Closed

Unable to replicate results of convLSTM #741

mulvey-g opened this issue Dec 14, 2021 · 2 comments

Comments

@mulvey-g
Copy link

My predicted output results of the moving MNIST are not as good as what is visible on the website. The first predicted image appears to be the most accurate, and after that, the images get very blurry very quickly. I believe there is someone else who is having a similar difficulty.

I am using NVIDIA GeForce RTX 2080 with Max-Q design, TensorFlow 2.5.0 and cudNN 8.2.1.
After 20 epochs, these are some of the results I got. I did not make any alterations to the code

Results I got

convLSTM_20_epochs_27_10_2021 2
convLSTM_20_epochs_exact_code_27_10_2021

Results produced on the Keras website after 20 epochs.
keras example of frame prediction

@pcoet pcoet self-assigned this Aug 22, 2023
@pcoet pcoet removed their assignment Sep 28, 2023
@sachinprasadhs
Copy link
Collaborator

Duplicate of: #732

@sachinprasadhs sachinprasadhs closed this as not planned Won't fix, can't repro, duplicate, stale Jul 23, 2024
Copy link

Are you satisfied with the resolution of your issue?
Yes
No

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

No branches or pull requests

3 participants