I deployed a Convolutional Neural Network(ALL-CNN) for Object recognition. It obtains state of the art performance at object recognition on the CIFAR 10 image dataset in 2015.
The CNN used was built using Keras(a high level Neural Network), application programming interface that supports theano and tensorflow backends.
I used one-hot vector for categorical labels, added layers to the keras model, loaded pre-trained weights and made predicitions using this model.
The dataset used was the CIFAR 10 which consists of 60,000 32 by 32 color images in 10 classes.