tensorflow - Is it possible to bias the training of an object detection model towards classification in tensorflow ModelMaker?

Question

I'm using Tensorflow 2 Model Maker to perform transfer training of EfficientDet-Lite (ultimately to run on a Coral EdgeTPU) and I care much more about the classification output and much less about the precision of the bounding boxes. Is there a way to modify some training parameters to improve the accuracy of the classes at the expense of the accuracy of the bounding boxes? Or does this not make sense?

Answer 1

不幸的是，TensorFlow 2 Model Maker 目前不支持这种定制。

如果你想这样做，你可以绕过 Model Maker 直接使用AutoML repo。技术细节是通过添加功能来调整不同损失的权重loss_weights。compile()