Keras implementation of Google's inception v4 model with ported weights!
As described in: Inception-v4, Inception-ResNet and the Impact of Residual Connections on Learning (Christian Szegedy, Sergey Ioffe, Vincent Vanhoucke, Alex Alemi)
Note this Keras implementation tries to follow the tf.slim definition as closely as possible.
Pre-Trained weights for this Keras model can be found here (ported from the tf.slim ckpt): https://github.com/kentsommer/keras-inceptionV4/releases
You can evaluate a sample image by performing the following (weights are downloaded automatically):
$ python evaluate_image.py
Loaded Model Weights!
Class is: African elephant, Loxodonta africana
Certainty is: 0.8684985/23/2017:
Error rate on non-blacklisted subset of ILSVRC2012 Validation Dataset (Single Crop):
These error rates are actually slightly lower than the listed error rates in the paper: