Handling mask RCNN

[anshkumar]

I was wondering if for the detection of mask RCNN do we have to make following changes:

output_names = [BOXES_NAME, CLASSES_NAME, SCORES_NAME, NUM_DETECTIONS_NAME, MASKS_NAME]

in the file "Step1_Object_detection_Colab_TensorRT.ipynb" ? Or I missing something else ?

Also, why are you overriding some of the config parameters for ssd and faster RCNN ?

    if config.model.HasField('ssd'):
        config.model.ssd.feature_extractor.override_base_feature_extractor_hyperparams = True
        if score_threshold is not None:
            config.model.ssd.post_processing.batch_non_max_suppression.score_threshold = score_threshold
        if iou_threshold is not None:
            config.model.ssd.post_processing.batch_non_max_suppression.iou_threshold = iou_threshold
        if input_shape is not None:
            config.model.ssd.image_resizer.fixed_shape_resizer.height = input_shape[0]
            config.model.ssd.image_resizer.fixed_shape_resizer.width = input_shape[1]
    elif config.model.HasField('faster_rcnn'):
        if score_threshold is not None:
            config.model.faster_rcnn.second_stage_post_processing.score_threshold = score_threshold
        if input_shape is not None:
            config.model.faster_rcnn.image_resizer.fixed_shape_resizer.height = input_shape[0]
            config.model.faster_rcnn.image_resizer.fixed_shape_resizer.width = input_shape[1]

Do we have to make such changes for mask RCNN also ?