Freeze All layers except Output layers

[Asif6511]

Hi,

I am finetuning a COCO pretrained model with VOC dataset. I am using the config file : e2e_mask_rcnn_R-50-FPN_1x.yaml

I found a key to freeze the backbone of model with TRAIN.FREEZE_CONV_BODY: True But this only freezes the Convolutional layers. How do I freeze the Fast RCNN and MRCNN layers so I can update the output layers alone by fine tuning ?