This document has instructions for running BERT FP32 inference using Intel® Optimization for TensorFlow*.
Download and unzip the BERT-Large uncased (whole word masking) model from the Google* BERT repository. Then, download the Stanford Question Answering Dataset (SQuAD) dataset file
dev-v1.1.json into the
wwm_uncased_L-24_H-1024_A-16 directory that was just unzipped.
wget https://storage.googleapis.com/bert_models/2019_05_30/wwm_uncased_L-24_H-1024_A-16.zip unzip wwm_uncased_L-24_H-1024_A-16.zip wget https://rajpurkar.github.io/SQuAD-explorer/dataset/dev-v1.1.json -P wwm_uncased_L-24_H-1024_A-16
DATASET_DIR to point to that directory when running BERT-Large inference using the SQuAD data.
Quick Start Scripts
||This script runs BERT-Large fp32 inference.|
||This script runs fp32 inference in profile mode.|
||This script runs BERT-Large fp32 inference in accuracy mode.|
To run on bare metal, the following prerequisites must be installed in your enviornment:
- Python* 3
- Intel Optimization for TensorFlow
Once the above dependencies have been installed, download and untar the model package, set environment variables, and then run a quick start script. See the datasets and list of quick start scripts for more details on the different options.
The snippet below shows how to run a quick start script:
wget https://storage.googleapis.com/intel-optimized-tensorflow/models/v2_3_0/bert-large-fp32-inference.tar.gz tar -xvf bert-large-fp32-inference.tar.gz cd bert-large-fp32-inference DATASET_DIR=<path to the dataset being used> OUTPUT_DIR=<directory where log files will be saved> # Run a script for your desired usage bash ./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
BERT-Large FP32 Inference TensorFlow* Container
Product and Performance Information
Performance varies by use, configuration and other factors. Learn more at www.Intel.com/PerformanceIndex.