-
Notifications
You must be signed in to change notification settings - Fork 848
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
yolox person detection result can not reproduce #387
Comments
know the learning rate I use is very low, but use same learning rate e-3 suggested in paper for yolox detection, model will overfit in first epoch. |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Hi, thanks for the work:
for MOT20 detection model, I try same dataset (train: crowdhuman+MOT20 train, test: MOT20 test), but the yolox detection model person detection result on MOT is much lower than your model: my one only around 60%mAP compare to you release yolox model 82% mAP in person detection,
could help take a look the parameter that I use which might go wrong, thanks
parameters that I use:
class Exp(BaseExp):
def init(self):
super().init()
The text was updated successfully, but these errors were encountered: