Converting a TensorFlow Neural Collaborative Filtering Model

This tutorial explains how to convert Neural Collaborative Filtering (NCF) model to the OpenVINO Intermediate Representation.

Public TensorFlow NCF model does not contain pre-trained weights. To convert this model to the IR:

  1. Use the instructions from this repository to train the model.

  2. Freeze the inference graph you get in the previous step in model_dir, following the instructions from the Freezing Custom Models in Python section of the Converting a TensorFlow Model guide. Run the following commands:

    import tensorflow as tf
    from tensorflow.python.framework import graph_io
    sess = tf.compat.v1.Session()
    saver = tf.compat.v1.train.import_meta_graph("/path/to/model/model.meta")
    saver.restore(sess, tf.train.latest_checkpoint('/path/to/model/'))
    frozen = tf.compat.v1.graph_util.convert_variables_to_constants(sess, sess.graph_def, \
    graph_io.write_graph(frozen, './', 'inference_graph.pb', as_text=False)

    where rating/BiasAdd is an output node.

  3. Convert the model to the OpenVINO format. If you look at your frozen model, you can see that it has one input that is split into four ResourceGather layers. (Click image to zoom in.)

NCF model beginning

However, as the Model Optimizer does not support such data feeding, you should skip it. Cut the edges incoming in ResourceGather port 1:

 mo --input_model inference_graph.pb                    \
--input 1:embedding/embedding_lookup,1:embedding_1/embedding_lookup, \
1:embedding_2/embedding_lookup,1:embedding_3/embedding_lookup        \
--input_shape [256],[256],[256],[256]                                \
--output_dir <OUTPUT_MODEL_DIR>

In the input_shape parameter, 256 specifies the batch_size for your model.

Alternatively, you can do steps 2 and 3 in one command line:

 mo --input_meta_graph /path/to/model/model.meta        \
--input 1:embedding/embedding_lookup,1:embedding_1/embedding_lookup, \
1:embedding_2/embedding_lookup,1:embedding_3/embedding_lookup        \
--input_shape [256],[256],[256],[256] --output rating/BiasAdd        \
--output_dir <OUTPUT_MODEL_DIR>