Customize Object Detection Model Maker

General Discussion
, , ,
#1

Hello, community!

Is there a way to customize the model from object detection model_maker? e.g., get the loss and do some early stopping with the validation loss, save and load it. If it is not possible, is there a way to load the model as a tf/keras model to customize the training? Or maybe print the model summary to try to reproduce on tf/keras…

I followed the tutorial with efficiendet, Object Detection with TensorFlow Lite Model Maker, and it worked fine, besides the fact that the training is being done on CPU.

Best Regards,

#3

@khanhlvg may have some advice.

But AFAIK model maker is really limited in terms of customizability.

1 Like
#5

@Yuqi_Li for in-depth advices.

1 Like
#7

If you’d like to customize the model, I would suggest you directly use efficientdet repo. Model Maker is based on this repo which limit the customization part.

1 Like