Download the MovieLens 1M dataset
wget http://files.grouplens.org/datasets/movielens/ml-1m.zip unzip ml-1m.zip
DATASET_DIR to point to this directory when running NCF.
Quick Start Scripts
||Runs online inference (batch_size=1).|
||Runs batch inference (batch_size=256).|
||Measures the model accuracy (batch_size=256).|
To run on bare metal, the following prerequisites must be installed in your environment:
- Python* 3
- Intel® Optimization for TensorFlow*
- Google* API Python* client 1.6.7
- Google Cloud* enterprise services BigQuery* 0.31.0
- Kaggle* 1.3.9
- NumPy 1.16.1
- Oauth2client 4.1.2
- pandas psutil 5.4.3
- Py-cpuinfo 3.3.0
- TensorFlow* models: Clone the official repository with the tag v1.11.
git clone https://github.com/tensorflow/models.git tf_models cd tf_models git checkout v1.11
After installing the prerequisites, download and untar the model package. Set environment variables for the path to your
DATASET_DIR and an
OUTPUT_DIR where log files will be written, then run a quick start script.
DATASET_DIR=<path to the dataset> OUTPUT_DIR=<directory where log files will be written> TF_MODELS_DIR=<path to the TensorFlow models directory tf_models> wget https://storage.googleapis.com/intel-optimized-tensorflow/models/v2_3_0/ncf-fp32-inference.tar.gz tar -xzf ncf-fp32-inference.tar.gz cd ncf-fp32-inference quickstart/<script name>.sh
Documentation and Sources
LEGAL NOTICE: By accessing, downloading or using this software and any required dependent software (the “Software Package”), you agree to the terms and conditions of the software license agreements for the Software Package, which may also include notices, disclaimers, or license terms for third party software included with the Software Package. Please refer to the license file for additional details.
Related Containers and Solutions
Product and Performance Information
Performance varies by use, configuration and other factors. Learn more at www.Intel.com/PerformanceIndex.