371ffe8f69e9f76978dd4254534285129f0f3d6c,examples/common.py,,distribution_accuracy,#Any#Any#,68

Before Change

    tiled_a = tf.tile(tiled_a, [1, int(tiled_a.get_shape()[0]), 1])

    tiled_b = b
    tiled_b = tf.reshape(tiled_b, [1, int(tiled_b.get_shape()[0]), int(tiled_b.get_shape()[1])])
    tiled_b = tf.tile(tiled_b, [int(tiled_b.get_shape()[0]), 1, 1])

    difference = tf.abs(tiled_a-tiled_b)
    difference = tf.reduce_min(difference, axis=1)
    difference = tf.reduce_sum(difference, axis=1)
    return tf.reduce_sum(difference, axis=0) 

def batch_accuracy(a, b):

After Change

    This works best on a large batch of small inputs.

    shape = a.shape
    tiled_a = a.view(shape[0], 1, shape[1]).repeat(1, shape[0], 1)
    tiled_b = b.view(1, shape[0], shape[1]).repeat(shape[0], 1, 1)

    difference = torch.abs(tiled_a-tiled_b)
    difference = torch.min(difference, dim=1)[0]
    difference = torch.sum(difference, dim=1)
    return torch.sum(difference, dim=0)

def batch_accuracy(a, b):

Instances