experiments
/
STT-tensorflow
1
0
Fork 0
Code Issues Pull Requests Projects Releases Wiki Activity

Fix formatting of lite/tools/pip_package/REDAME.md 

PiperOrigin-RevId: 301934203
Change-Id: I9146b9d9afca2f95576edbb2588dff8d8759e79e
This commit is contained in:
Terry Heo 2020-03-19 18:02:53 -07:00 committed by TensorFlower Gardener
parent 2260719374
commit 08ab10f127
1 changed files with 14 additions and 7 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

21
tensorflow/lite/tools/pip_package/README.md
View File

@ -6,44 +6,51 @@ Python without requiring the rest of TensorFlow.
## Steps ## Steps
To build a binary wheel run this script: To build a binary wheel run this script:
```
```sh
sudo apt install swig libjpeg-dev zlib1g-dev python3-dev python3-numpy sudo apt install swig libjpeg-dev zlib1g-dev python3-dev python3-numpy
sh tensorflow/lite/tools/pip_package/build_pip_package.sh sh tensorflow/lite/tools/pip_package/build_pip_package.sh
``` ```
That will print out some output and a .whl file. You can then install that That will print out some output and a .whl file. You can then install that
```
```sh
pip install --upgrade <wheel> pip install --upgrade <wheel>
``` ```
You can also build a wheel inside docker container using make tool. For example You can also build a wheel inside docker container using make tool. For example
the following command will cross-compile tflite-runtime package for python2.7 the following command will cross-compile tflite-runtime package for python2.7
and python3.7 (from Debian Buster) on Raspberry Pi: and python3.7 (from Debian Buster) on Raspberry Pi:
```
```sh
make BASE_IMAGE=debian:buster PYTHON=python TENSORFLOW_TARGET=rpi docker-build make BASE_IMAGE=debian:buster PYTHON=python TENSORFLOW_TARGET=rpi docker-build
make BASE_IMAGE=debian:buster PYTHON=python3 TENSORFLOW_TARGET=rpi docker-build make BASE_IMAGE=debian:buster PYTHON=python3 TENSORFLOW_TARGET=rpi docker-build
``` ```
Another option is to cross-compile for python3.5 (from Debian Stretch) on ARM64 Another option is to cross-compile for python3.5 (from Debian Stretch) on ARM64
board: board:
```
```sh
make BASE_IMAGE=debian:stretch PYTHON=python3 TENSORFLOW_TARGET=aarch64 docker-build make BASE_IMAGE=debian:stretch PYTHON=python3 TENSORFLOW_TARGET=aarch64 docker-build
``` ```
To build for python3.6 (from Ubuntu 18.04) on x86_64 (native to the docker To build for python3.6 (from Ubuntu 18.04) on x86_64 (native to the docker
image) run: image) run:
```
```sh
make BASE_IMAGE=ubuntu:18.04 PYTHON=python3 TENSORFLOW_TARGET=native docker-build make BASE_IMAGE=ubuntu:18.04 PYTHON=python3 TENSORFLOW_TARGET=native docker-build
``` ```
In addition to the wheel there is a way to build Debian package by adding In addition to the wheel there is a way to build Debian package by adding
BUILD_DEB=y to the make command (only for python3): BUILD_DEB=y to the make command (only for python3):
```
```sh
make BASE_IMAGE=debian:buster PYTHON=python3 TENSORFLOW_TARGET=rpi BUILD_DEB=y docker-build make BASE_IMAGE=debian:buster PYTHON=python3 TENSORFLOW_TARGET=rpi BUILD_DEB=y docker-build
``` ```
Note, unlike tensorflow this will be installed to a tflite_runtime namespace. Note, unlike tensorflow this will be installed to a tflite_runtime namespace.
You can then use the Tensorflow Lite interpreter as. You can then use the Tensorflow Lite interpreter as.
```
```python
from tflite_runtime.interpreter import Interpreter from tflite_runtime.interpreter import Interpreter
interpreter = Interpreter(model_path="foo.tflite") interpreter = Interpreter(model_path="foo.tflite")
``` ```