How to Install TensorFlow Lite
Contents
Building TensorFlow Lite from Source
Tested Operating Systems
This instructions have been tested on:
- Ubuntu Xenial 16.04
- Ubuntu Bionic 18.04
- Elementary Hera 5.1
TensorFlow Lite dependencies
sudo apt install git wget unzip python3 curl build-essential zlib1g-dev python3-numpy python3-six
# Some TF tools assume python is pointing to python3
# This uses the update-alternative util to do so. Caution,
# verify you don't have an alternative already configured
# by running "update-alternatives --config python"
#
sudo update-alternatives --install /usr/bin/python python /usr/bin/python3 1
Configuration Variables
TF_VERSION=v2.0.1
TensorFlow Lite Build Steps
git clone https://github.com/tensorflow/tensorflow.git
cd tensorflow
# Move to a stable version
git checkout $TF_VERSION
# Important - download a valid bazel version
BAZEL=`awk -F"'" '/_TF_MAX_BAZEL_VERSION = /{print $2}' configure.py`
mkdir bazel
cd bazel
wget -c https://github.com/bazelbuild/bazel/releases/download/${BAZEL}/bazel-${BAZEL}-installer-linux-x86_64.sh
chmod +x bazel-${BAZEL}-installer-linux-x86_64.sh
sudo ./bazel-${BAZEL}-installer-linux-x86_64.sh
cd ..
# Configure tensorflow - I usually accept all defaults
./configure
# Build the library
cd tensorflow/lite/tools/make
./download_dependencies.sh
./build_lib.sh
cd ../../../..
# The library will be built here
realpath tensorflow/lite/tools/make/gen/linux_x86_64/lib/libtensorflow-lite.a
Benchmarking a TensorFlow Lite Model
Make sure you've run the previous steps already.
# Configure tensorflow (if you havent already)- I usually accept all defaults
./configure
# Finally build the benchmarking tool
bazel build -c opt tensorflow/lite/tools/benchmark:benchmark_model
# Run the benchmarking
bazel-bin/tensorflow/lite/tools/benchmark/benchmark_model \
--graph=mobilenet_quant_v1_224.tflite \
--num_threads=4
|
RidgeRun Resources | |||||||||||||||||||||||||||||||||||||||||||||||||||||||
| |||||||||||||||||||||||||||||||||||||||||||||||||||||||
|
|||||||||||||||||||||||||||||||||||||||||||||||||||||||
| Visit our Main Website for the RidgeRun Products and Online Store. RidgeRun Engineering informations are available in RidgeRun Professional Services, RidgeRun Subscription Model and Client Engagement Process wiki pages. Please email to support@ridgerun.com for technical questions and contactus@ridgerun.com for other queries. Contact details for sponsoring the RidgeRun GStreamer projects are available in Sponsor Projects page. |  
|
