-
Notifications
You must be signed in to change notification settings - Fork 524
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
what should be the ideal mAP0.95 should be? #276
Comments
What do you mean by Negative Samples ? |
Negative sample means images not having the object of interest. |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Hi,
I am training yolor_csp with a single class of ~1500 images, where 400 images are negative images. train test split is of the ratio 80:20. While training with fine-tune hyper parameters for 1280 size for 5000 epochs, best_overall is being generated around epoch #900. after than mAP values are going down.
The best mAP0.5:0.95 is coming around 0.85.
My query is , is that value too high ? or is it expected? Am I overfitting the data ? Shall I continue training beyond 5000 epochs?
Kindly give your valuable feedback.
The text was updated successfully, but these errors were encountered: