lobe

Python toolset for working with Lobe models

Showing:

Popularity

Downloads/wk

0

GitHub Stars

111

Maintenance

Last Commit

2mos ago

Contributors

9

Package

Dependencies

6

License

MIT

Categories

Readme

Lobe Python API

Code to run exported Lobe models in Python using the TensorFlow, TensorFlow Lite, or ONNX options.

Works with Python 3.6, 3.7, and 3.8 untested for other versions.

Install

Backend options with pip

You can install each of the backends on an individual basis, or all together through pip like so:

# For all of the supported backends (TensorFlow, TensorFlow Lite, ONNX)
pip install lobe[all]

# For TensorFlow only
pip install lobe[tf]

# For TensorFlow Lite only -- this requires two steps for the runtime and for lobe (note for Raspberry Pi see our setup script in scripts/lobe-rpi-install.sh)
pip install --index-url https://google-coral.github.io/py-repo/ tflite_runtime 
pip install lobe

# For ONNX only
pip install lobe[onnx]

Installing lobe-python without any options (pip install lobe) will only install the base requirements, no backends will be installed. If you try to load a model with a backend that hasn't been installed, an error message will show you the instructions to install the correct backend.

Linux

Before running these commands, make sure that you have git installed.

# Install Python3
sudo apt update
sudo apt install -y python3-dev python3-pip

# Install Pillow dependencies
sudo apt update
sudo apt install -y libatlas-base-dev libopenjp2-7 libtiff5 libjpeg62-dev

# Install lobe-python
pip3 install setuptools
# Swap out the 'all' option here for your desired backend from 'backend options with pip' above.
pip3 install lobe[all]

For Raspberry Pi OS (Raspian) run:

cd ~
wget https://raw.githubusercontent.com/lobe/lobe-python/master/scripts/lobe-rpi-install.sh
chmod 755 lobe-rpi-install.sh
sudo ./lobe-rpi-install.sh

Mac/Windows

We recommend using a virtual environment:

python3 -m venv .venv

# Mac:
source .venv/bin/activate

# Windows:
.venv\Scripts\activate

Install the library

# Make sure pip is up to date
python -m pip install --upgrade pip
# Swap out the 'all' option here for your desired backend from 'backend options with pip' above.
pip install lobe[all]

Usage

from lobe import ImageModel

model = ImageModel.load('path/to/exported/model/folder')

# OPTION 1: Predict from an image file
result = model.predict_from_file('path/to/file.jpg')

# OPTION 2: Predict from an image url
result = model.predict_from_url('http://url/to/file.jpg')

# OPTION 3: Predict from Pillow image
from PIL import Image
img = Image.open('path/to/file.jpg')
result = model.predict(img)

# Print top prediction
print(result.prediction)

# Print all classes
for label, confidence in result.labels:
    print(f"{label}: {confidence*100}%")

Note: model predict functions should be thread-safe. If you find bugs please file an issue.

Resources

See the Raspberry Pi Trash Classifier example, and its Adafruit Tutorial.

Rate & Review

Great Documentation0
Easy to Use0
Performant0
Highly Customizable0
Bleeding Edge0
Responsive Maintainers0
Poor Documentation0
Hard to Use0
Slow0
Buggy0
Abandoned0
Unwelcoming Community0
100