Spatial Transformer Network
The Spatial Transformer Network  allows the spatial manipulation of data within the network.
A Spatial Transformer Network implemented in Tensorflow 0.7 and based on .
How to use
transformer(U, theta, out_size)
U : float The output of a convolutional net should have the shape [num_batch, height, width, num_channels]. theta: float The output of the localisation network should be [num_batch, 6]. out_size: tuple of two ints The size of the output of the network
To initialize the network to the identity transform init
theta to :
identity = np.array([[1., 0., 0.], [0., 1., 0.]]) identity = identity.flatten() theta = tf.Variable(initial_value=identity)
We used cluttered MNIST. Left column are the input images, right are the attended parts of the image by an STN.
All experiments were run in Tensorflow 0.7.
 Jaderberg, Max, et al. "Spatial Transformer Networks." arXiv preprint arXiv:1506.02025 (2015)