-
Notifications
You must be signed in to change notification settings - Fork 946
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
object detection, add save() and load() #405
Conversation
Job PR-405-1 is done. |
@@ -10,7 +10,7 @@ def _get_network(meta_arch, name, transfer_classes, ctx=mx.cpu()): | |||
net = gcv.model_zoo.get_model(net_name, | |||
classes=transfer_classes, | |||
pretrained_base=False, | |||
transfer='coco') | |||
transfer=None) |
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
why change to None
this time?
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
It doesn't matter here since we will load our trained model later and all weights will be updated. I just change it to None to make it consistent with faster-rcnn part
https://github.com/chongruo/autogluon/blob/d9cb58c2762fbcd496d3fec7ade57416fe2707bf/autogluon/task/object_detection/nets.py#L29
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
Thanks for implementing it. Could you also add this method to the tutorial (also for image classification tutorial)?
have added them to the tutorial |
Job PR-405-2 is done. |
Job PR-405-3 is done. |
Add save() and load() for object detection