The COCO validation dataset is used in the Faster R-CNN quick start scripts. The scripts require that the dataset has been converted to the TensorFlow* records format. See the COCO dataset for instructions on downloading and preprocessing the COCO validation dataset.
DATASET_DIR to point to this directory when running Faster R-CNN .
Quick Start Scripts
|int8_inference||Runs batch and online inference using the raw coco dataset|
|int8_accuracy||Runs inference and evaluates the model's accuracy with coco dataset in
To run on bare metal, the following prerequisites must be installed in your environment:
- Python* 3
- GNU Wget
- Protobuf Compilation
- Intel® Optimization for TensorFlow* 1.15.2
- Pillow 7.1.0
Clone the TensorFlow* Model Garden repository using the specified tag, and save the path to the
TF_MODELS_DIR environment variable.
# Clone the TF models repo git clone https://github.com/tensorflow/models.git pushd models git checkout tags/v1.12.0 export TF_MODELS_DIR=$(pwd) popd
After installing the prerequisites, download and extract the model package, which includes the pretrained model and scripts needed to run inference. Set environment variables for the path to your
DATASET_DIR (where the coco TensorFlow* records file is located) and an
OUTPUT_DIR where log files will be written, then run a quick start script.
wget https://storage.googleapis.com/intel-optimized-tensorflow/models/v2_3_0/faster-rcnn-int8-inference.tar.gz tar -xzf faster_rcnn-int8-inference.tar.gz cd faster_rcnn-int8-inference export DATASET_DIR=<path to the coco dataset> export OUTPUT_DIR=<directory where log files will be written> 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.