Eager Few Shot Object Detection Colab for CenterNet

Question

I am using Tensorflow Object Detection API. Recently it was updated to Tensorflow2. And with it authors put out a great Colab https://github.com/tensorflow/models/blob/master/research/object_detection/colab_tutorials/eager_few_shot_od_training_tf2_colab.ipynb. They fine-tune RetinaNet on new dataset, however I don't understand how can I use this to fine-tune CenterNet (and EfficientDet).

They have the following code for initialising RetinaNet model:

tf.keras.backend.clear_session()

print('Building model and restoring weights for fine-tuning...', flush=True)
num_classes = 1
pipeline_config = 'models/research/object_detection/configs/tf2/ssd_resnet50_v1_fpn_640x640_coco17_tpu-8.config'
checkpoint_path = 'models/research/object_detection/test_data/checkpoint/ckpt-0'

# Load pipeline config and build a detection model.
#
# Since we are working off of a COCO architecture which predicts 90
# class slots by default, we override the `num_classes` field here to be just
# one (for our new rubber ducky class).
configs = config_util.get_configs_from_pipeline_file(pipeline_config)
model_config = configs['model']
model_config.ssd.num_classes = num_classes
model_config.ssd.freeze_batchnorm = True
detection_model = model_builder.build(
      model_config=model_config, is_training=True)

# Set up object-based checkpoint restore --- RetinaNet has two prediction
# `heads` --- one for classification, the other for box regression.  We will
# restore the box regression head but initialize the classification head
# from scratch (we show the omission below by commenting out the line that
# we would add if we wanted to restore both heads)
fake_box_predictor = tf.compat.v2.train.Checkpoint(
    _base_tower_layers_for_heads=detection_model._box_predictor._base_tower_layers_for_heads,
    # _prediction_heads=detection_model._box_predictor._prediction_heads,
    #    (i.e., the classification head that we *will not* restore)
    _box_prediction_head=detection_model._box_predictor._box_prediction_head,
    )
fake_model = tf.compat.v2.train.Checkpoint(
          _feature_extractor=detection_model._feature_extractor,
          _box_predictor=fake_box_predictor)
ckpt = tf.compat.v2.train.Checkpoint(model=fake_model)
ckpt.restore(checkpoint_path).expect_partial()

# Run model through a dummy image so that variables are created
image, shapes = detection_model.preprocess(tf.zeros([1, 640, 640, 3]))
prediction_dict = detection_model.predict(image, shapes)
_ = detection_model.postprocess(prediction_dict, shapes)
print('Weights restored!')

I tried to do similar thing with CenterNet model (it is used for inferencing in this Colab tutorial https://github.com/tensorflow/models/blob/master/research/object_detection/colab_tutorials/inference_tf2_colab.ipynb):

pipeline_config =  'models/research/object_detection/configs/tf2/centernet_hourglass104_512x512_coco17_tpu-8.config'
model_dir = 'models/research/object_detection/test_data/checkpoint/'
num_classes = 1
# Load pipeline config and build a detection model
configs = config_util.get_configs_from_pipeline_file(pipeline_config)
model_config = configs['model']

model_config.center_net.num_classes = num_classes
detection_model = model_builder.build(
      model_config=model_config, is_training=True)

# Restore checkpoint
ckpt = tf.compat.v2.train.Checkpoint(
      model=detection_model)
ckpt.restore(os.path.join(model_dir, 'ckpt-0')).expect_partial()

However, an exception is thrown because shapes are not compatible (because I changed number of classes). In the example with RetinaNet this trick was used (as I understand) to make tensors of right shapes:

fake_box_predictor = tf.compat.v2.train.Checkpoint(
    _base_tower_layers_for_heads=detection_model._box_predictor._base_tower_layers_for_heads,
    # _prediction_heads=detection_model._box_predictor._prediction_heads,
    #    (i.e., the classification head that we *will not* restore)
    _box_prediction_head=detection_model._box_predictor._box_prediction_head,
    )
fake_model = tf.compat.v2.train.Checkpoint(
          _feature_extractor=detection_model._feature_extractor,
          _box_predictor=fake_box_predictor)

But how can I discover what should I write inside checkpoint function? (for example, _base_tower_layers_for_heads=detection_model._box_predictor._base_tower_layers_for_heads or _box_prediction_head=detection_model._box_predictor._box_prediction_head)