Public pre-trained FaceNet models contain both training and inference part of graph. Switch between this two states is manageable with placeholder value. Intermediate Representation (IR) models are intended for inference, which means that train part is redundant.
There are two inputs in this network: boolean
phase_train which manages state of the graph (train/infer) and
batch_size which is a part of batch joining pattern.
To generate FaceNet IR provide TensorFlow FaceNet model to Model Optimizer with parameters:
Batch joining pattern transforms to placeholder with model default shape if
-b was not provided. Otherwise, placeholder shape has custom parameters.
--freeze_placeholder_with_value "phase_train->False" to switch graph to inference mode
-b is applicable to override original network batch
--input_shape is applicable with or without