How to convert Keras* H5 model to an Intermediate Representation (IR) format?

Unable to determine steps to convert Keras* H5 model to an IR format.

Step 1: Convert Keras H5 model to SavedModel Format

1. Install dependencies:
   cd <INSTALL_DIR>\deployment_tools\model_optimizer\install_prerequisites
   install_prerequisites_tf2.bat
2. Load the model using TensorFlow* 2 and serialize it in the SavedModel format.
   import tensorflow as tf
   model = tf.keras.models.load_model('model.h5')
   tf.saved_model.save(model,'model')
3. Optional: Model with a custom layer CustomLayer from custom_layer.py:
   import tensorflow as tf
   from custom_layer import CustomLayer
   model = tf.keras.models.load_model('model.h5', custom_objects={'CustomLayer': CustomLayer})
   tf.saved_model.save(model,'model')

Step 2: Convert SavedModel Format to Intermediate Representation

1. Change directory to <INSTALL_DIR>/deployment_tools/model_optimizer
2. Run the mo_tf.py script with a path to the SavedModel directory and a writable output directory:
   python mo_tf.py --saved_model_dir <SAVED_MODEL_DIRECTORY> --output_dir <OUTPUT_MODEL_DIR> --input_shape

Convert TensorFlow 2 Models in Converting a TensorFlow Model.

General Conversion Parameter and When to Specify Input Shapes in Converting a Model to Intermediate Representation.