-
Notifications
You must be signed in to change notification settings - Fork 1.2k
This issue was moved to a discussion.
You can continue the conversation there. Go to discussion →
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
In a new open dataset,the performance of the tsm is poor.Which lead to this? #628
Comments
config Can you help me? |
try i3d? |
And use pre-trained model on k400 |
Oh,I forget to use pre-trained model on k400. |
@innerlee When I do as you said ,the top1 acc of last model is higher than past. tsm log with k400 pre-train Is the dataset problem leading to low top1 acc? |
The dataset is very tiny.
|
|
It's overfitting. For small datasets, fewer epochs (i.e. 20) are enough. |
This issue was moved to a discussion.
You can continue the conversation there. Go to discussion →
I train the tsm on the fight dataset.
And the best top1 acc is 0.53.
When I use other small open dataset,the top1 acc is nearly to 1.0.
Is the fight dataset problem lead to the problem?
The text was updated successfully, but these errors were encountered: