-
-
Notifications
You must be signed in to change notification settings - Fork 3.4k
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
hyperparameters #497
Comments
@berad1ar its impossible to say. Start with the default hyps to establish a benchmark, then use hyperparameter evolution to automate the process. Evolution command for coco_16img dataset for example: while true
do
python3 train.py --data data/coco_16img.data --img-size 320 --batch-size 16 --accumulate 1 --cache --evolve
done See hyperparameter evolution: #392 |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
thanks for your work.I have a question need your help.
my dataset has 2000 images for training, and their objects are small.
I need to change hyperparameters to increase P and mAP. In your opinion, which hyperparameters should be changed and approximately how much should I increase or decrease them?
The text was updated successfully, but these errors were encountered: