Freezing layers when using Tensorflow Object Detection API?

[tft-robert]

Is it possible to freeze specific layers when using Tensorflow Object Detection API?

For example, I am using EfficientDet downloaded from the Tensorflow 2 Model Zoo. The model is (as you might know) already trained on objects that I am interested to detect (cars and boats in this case), but I want to train it more on my specific use case. At the same time I do not want it to “forget” what it has already learned. Hence, I need to freeze some of the layers.
So, is this possible?
I have found that I might can use the freeze_variables parameter in the pipeline.config file?

[tft-robert]

This is set in the pipeline.config based on what you want:

   1. "classification": Restores only the classification backbone part of
        the feature extractor. This option is typically used when you want
        to train a detection model starting from a pre-trained image
        classification model, e.g. a ResNet model pre-trained on ImageNet.
   2. "detection": Restores the entire feature extractor. The only parts
        of the full detection model that are not restored are the box and
        class prediction heads. This option is typically used when you want
        to use a pre-trained detection model and train on a new dataset or
        task which requires different box and class prediction heads.
   3. "full": Restores the entire detection model, including the
        feature extractor, its classification backbone, and the prediction
        heads. This option should only be used when the pre-training and
        fine-tuning tasks are the same. Otherwise, the model's parameters
        may have incompatible shapes, which will cause errors when
        attempting to restore the checkpoint.

[google-ml-butler]

Are you satisfied with the resolution of your issue?
Yes
No