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

How long does it take to train the models? #3

Closed
gaopeng-eugene opened this issue Mar 4, 2019 · 6 comments
Closed

How long does it take to train the models? #3

gaopeng-eugene opened this issue Mar 4, 2019 · 6 comments
Assignees
Labels
enhancement New feature or request

Comments

@gaopeng-eugene
Copy link

No description provided.

@Cadene
Copy link
Owner

Cadene commented Mar 4, 2019

For the complete murel model with the pairwise module and three steps, it can take 1 day on two gpus.

@gaopeng-eugene
Copy link
Author

Hi

Will you be able to share the training log for TDIUC and VQACP2?

@Cadene Cadene self-assigned this Mar 5, 2019
@Cadene Cadene added the enhancement New feature or request label Mar 5, 2019
@gaopeng-eugene
Copy link
Author

Hi, I can train TDIUC and VQA2 with your code but not for VQACP2. Could you share VQACP2 log first, if possible. I will share the TDIUC log file after finished training.

@Cadene
Copy link
Owner

Cadene commented Mar 23, 2019

@gaopeng-eugene Did you solve your issue?

What was the issue with VQACP2?

@Cadene Cadene closed this as completed Apr 11, 2019
@Zzmonica
Copy link

For the complete murel model with the pairwise module and three steps, it can take 1 day on two gpus.

I use the same configuration, it takes almost 4.5 hours per epoch, and you know here is 25 epoches in total for training procedure,and I use 4 GeForce GTX 1080 GPU for training.
Is that normal?

@Einstone-rose
Copy link

For the complete murel model with the pairwise module and three steps, it can take 1 day on two gpus.

I use the same configuration, it takes almost 4.5 hours per epoch, and you know here is 25 epoches in total for training procedure,and I use 4 GeForce GTX 1080 GPU for training.
Is that normal?

Hi, i have some questions. When training based on its default parameters ( dropout_input: 0.1, dropout_pre_lin: 0.0, dropout_output: 0.0), Isn't that overfitting? when I training the model , the val score is only 0.24.

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

No branches or pull requests

4 participants