A pre-trained model for object detection using the basic google image library.
DenseNet model. Fantastic for identifying similar shapes in new formats as would be encountered in data imports.
See our example here:
****
This model is available for both the Theano and TensorFlow backend, and can be built both with 'channels_first'data format (channels, height, width) or 'channels_last' data format (height, width, channels).
https://keras.io/applications/#densenet