Tensorfree is an image classification library that provides quick and easy access to some of the latest SOTA models. Simply install, define the location of your photos and let it do everything for you.

Installation

Use the package manager pip to install foobar.

pip install tensorfree

Usage

from tensorfree import Tensorfree

# Here we create a new InceptionResNetV2 model
model = Tensorfree.build('InceptionResNetV2')
model.get_photos('photos/')
model.save_photos('labeled_photos/')
model.label()

Current Models Available

NASNetLarge : Learning Transferable Architectures for Scalable Image Recognition

DenseNet : Densely Connected Convolutional Networks

MobileNetV2 : MobileNetV2: Inverted Residuals and Linear Bottlenecks

InceptionResNetV2 : Inception-v4, Inception-ResNet and the Impact of Residual Connections on Learning

VGG19 : Very Deep Convolutional Networks for Large-Scale Image Recognition

Contributing

Contributions are welcome, and they are greatly appreciated! Every little bit helps, and credit will always be given. Please check CONTRIBUTING.rst for more info.

License

MIT