tensorboard_tools.py

'''
Created on 14 Sep 2017

@author: pingshiyu
'''

from math import sqrt
import tensorflow as tf

def put_kernels_on_grid(kernel, pad = 1):

    '''
    Visualize conv. filters as an image (mostly for the 1st layer).
    Arranges filters into a grid, with some paddings between adjacent filters.
    
    Args:
      kernel:            tensor of shape [Y, X, NumChannels, NumKernels]
      pad:               number of black pixels around each filter (between them)
    
    Return:
      Tensor of shape [1, (Y+2*pad)*grid_Y, (X+2*pad)*grid_X, NumChannels].
    '''
    # get shape of the grid. NumKernels == grid_Y * grid_X
    def factorization(n):
        for i in range(int(sqrt(float(n))), 0, -1):
            if n % i == 0:
                if i == 1: print('Who would enter a prime number of filters')
                return (i, int(n / i))
    (grid_Y, grid_X) = factorization (kernel.get_shape()[3].value)
    print ('grid: %d = (%d, %d)' % (kernel.get_shape()[3].value, grid_Y, grid_X))
    
    x_min = tf.reduce_min(kernel)
    x_max = tf.reduce_max(kernel)
    kernel = (kernel - x_min) / (x_max - x_min)
    
    # pad X and Y
    x = tf.pad(kernel, tf.constant( [[pad,pad],[pad, pad],[0,0],[0,0]] ), mode = 'CONSTANT')
    
    # X and Y dimensions, w.r.t. padding
    Y = kernel.get_shape()[0] + 2 * pad
    X = kernel.get_shape()[1] + 2 * pad
    
    channels = kernel.get_shape()[2]
    
    # put NumKernels to the 1st dimension
    x = tf.transpose(x, (3, 0, 1, 2))
    # organize grid on Y axis
    x = tf.reshape(x, tf.stack([grid_X, Y * grid_Y, X, channels]))
    
    # switch X and Y axes
    x = tf.transpose(x, (0, 2, 1, 3))
    # organize grid on X axis
    x = tf.reshape(x, tf.stack([1, X * grid_X, Y * grid_Y, channels]))
    
    # back to normal order (not combining with the next step for clarity)
    x = tf.transpose(x, (2, 1, 3, 0))
    
    # to tf.image_summary order [batch_size, height, width, channels],
    #   where in this case batch_size == 1
    x = tf.transpose(x, (3, 0, 1, 2))
    
    # scaling to [0, 255] is not necessary for tensorboard
    return x

def variable_summaries(var):
    '''
    Attach a lot of summaries to a Tensor (for TensorBoard visualization).
    '''
    with tf.name_scope('summaries'):
        mean = tf.reduce_mean(var)
        tf.summary.scalar('mean', mean)
        with tf.name_scope('stddev'):
            stddev = tf.sqrt(tf.reduce_mean(tf.square(var - mean)))
        tf.summary.scalar('stddev', stddev)
        tf.summary.scalar('max', tf.reduce_max(var))
        tf.summary.scalar('min', tf.reduce_min(var))
        tf.summary.histogram('histogram', var)