Agfdhyk

I'm trying to implement unpool in tensorflow with tf.scatter_add, but I meet a strange bug, here is my code:

import tensorflow as tf

import numpy as np

import random



tf.reset_default_graph()



mat = list(range(64))

random.shuffle(mat)

mat = np.array(mat)

mat = np.reshape(mat, [1,8,8,1])

M = tf.constant(mat, dtype=tf.float32)

pool1, argmax1 = tf.nn.max_pool_with_argmax(M, ksize=[1,2,2,1], strides=[1,2,2,1], padding='SAME')

pool2, argmax2 = tf.nn.max_pool_with_argmax(pool1, ksize=[1,2,2,1], strides=[1,2,2,1], padding='SAME')

pool3, argmax3 = tf.nn.max_pool_with_argmax(pool2, ksize=[1,2,2,1], strides=[1,2,2,1], padding='SAME')





def unpool(x, argmax, strides, unpool_shape=None, batch_size=None, name='unpool'):

    x_shape = x.get_shape().as_list()

    argmax_shape = argmax.get_shape().as_list()

    assert not(x_shape[0] is None and batch_size is None), "must input batch_size if number of batch is alterable"

    if x_shape[0] is None:

        x_shape[0] = batch_size

    if argmax_shape[0] is None:

        argmax_shape[0] = x_shape[0]

    if unpool_shape is None:

        unpool_shape = [x_shape[i] * strides[i] for i in range(4)]

    x_unpool = tf.get_variable(name=name, shape=[np.prod(unpool_shape)], initializer=tf.zeros_initializer(), trainable=False)

    argmax = tf.cast(argmax, tf.int32)

    argmax = tf.reshape(argmax, [np.prod(argmax_shape)])

    x = tf.reshape(x, [np.prod(argmax.get_shape().as_list())])

    x_unpool = tf.scatter_add(x_unpool , argmax, x)

    x_unpool = tf.reshape(x_unpool , unpool_shape)

    return x_unpool 





unpool2 = unpool(pool3, argmax3, strides=[1,2,2,1], name='unpool3')

unpool1 = unpool(unpool2, argmax2, strides=[1,2,2,1], name='unpool2')

unpool0 = unpool(unpool1, argmax1, strides=[1,2,2,1], name='unpool1')





with tf.Session() as sess:

    sess.run(tf.global_variables_initializer())

    mat_out = mat[:,:,:,0]

    pool1_out = sess.run(pool1)[0,:,:,0]

    pool2_out = sess.run(pool2)[0,:,:,0]

    pool3_out = sess.run(pool3)[0,:,:,0]

    argmax1_out = sess.run(argmax1)[0,:,:,0]

    argmax2_out = sess.run(argmax2)[0,:,:,0]

    argmax3_out = sess.run(argmax3)[0,:,:,0]

    unpool2_out = sess.run(unpool2)[0,:,:,0]

    unpool1_out = sess.run(unpool1)[0,:,:,0]

    unpool0_out = sess.run(unpool0)[0,:,:,0]

    print(unpool2_out)

    print(unpool1_out)

    print(unpool0_out)

output:

[[ 0.  0.]

 [ 0. 63.]]

[[  0.   0.   0.   0.]

 [  0.   0.   0.   0.]

 [  0.   0. 126.   0.]

 [  0.   0.   0.   0.]]

[[  0.   0.   0.   0.   0.   0.   0.   0.]

 [  0.   0.   0.   0.   0.   0.   0.   0.]

 [  0.   0.   0.   0.   0.   0.   0.   0.]

 [  0.   0.   0.   0.   0.   0.   0.   0.]

 [  0.   0.   0.   0.   0.   0.   0.   0.]

 [  0.   0.   0.   0. 315.   0.   0.   0.]

 [  0.   0.   0.   0.   0.   0.   0.   0.]

 [  0.   0.   0.   0.   0.   0.   0.   0.]]

The location is right, but the value is wrong. unpool2 is right, unpool1 is double of expected value, and unpool2 is quintuple of expected value. I don't what't wrong, can anyone tell me how to fix this bug?

Great thanks in advance.

Use tf.scatter_update will avoid this bug, but I still want to konw what's the reason for this bug.

import tensorflow as tf

import numpy as np

import random



tf.reset_default_graph()



mat = list(range(64))

random.shuffle(mat)

mat = np.array(mat)

mat = np.reshape(mat, [1,8,8,1])

M = tf.constant(mat, dtype=tf.float32)

pool1, argmax1 = tf.nn.max_pool_with_argmax(M, ksize=[1,2,2,1], strides=[1,2,2,1], padding='SAME')

pool2, argmax2 = tf.nn.max_pool_with_argmax(pool1, ksize=[1,2,2,1], strides=[1,2,2,1], padding='SAME')

pool3, argmax3 = tf.nn.max_pool_with_argmax(pool2, ksize=[1,2,2,1], strides=[1,2,2,1], padding='SAME')





def unpool(x, argmax, strides, unpool_shape=None, batch_size=None, name='unpool'):

    x_shape = x.get_shape().as_list()

    argmax_shape = argmax.get_shape().as_list()

    assert not(x_shape[0] is None and batch_size is None), "must input batch_size if number of batch is alterable"

    if x_shape[0] is None:

        x_shape[0] = batch_size

    if argmax_shape[0] is None:

        argmax_shape[0] = x_shape[0]

    if unpool_shape is None:

        unpool_shape = [x_shape[i] * strides[i] for i in range(4)]

    unpool = tf.get_variable(name=name, shape=[np.prod(unpool_shape)], initializer=tf.zeros_initializer(), trainable=False)

    argmax = tf.cast(argmax, tf.int32)

    argmax = tf.reshape(argmax, [np.prod(argmax_shape)])

    x = tf.reshape(x, [np.prod(argmax.get_shape().as_list())])

    unpool = tf.scatter_update(unpool, argmax, x)

    unpool = tf.reshape(unpool, unpool_shape)

    return unpool





unpool2 = unpool(pool3, argmax3, strides=[1,2,2,1], name='unpool3')

unpool1 = unpool(unpool2, argmax2, strides=[1,2,2,1], name='unpool2')

unpool0 = unpool(unpool1, argmax1, strides=[1,2,2,1], name='unpool1')





with tf.Session() as sess:

    sess.run(tf.global_variables_initializer())

    mat_out = mat[:,:,:,0]

    pool1_out = sess.run(pool1)[0,:,:,0]

    pool2_out = sess.run(pool2)[0,:,:,0]

    pool3_out = sess.run(pool3)[0,:,:,0]

    argmax1_out = sess.run(argmax1)[0,:,:,0]

    argmax2_out = sess.run(argmax2)[0,:,:,0]

    argmax3_out = sess.run(argmax3)[0,:,:,0]

    unpool2_out = sess.run(unpool2)[0,:,:,0]

    unpool1_out = sess.run(unpool1)[0,:,:,0]

    unpool0_out = sess.run(unpool0)[0,:,:,0]

    print(unpool2_out)

    print(unpool1_out)

    print(unpool0_out)

output:

[[ 0.  0.]

 [ 0. 63.]]

[[ 0.  0.  0.  0.]

 [ 0.  0.  0.  0.]

 [ 0.  0.  0. 63.]

 [ 0.  0.  0.  0.]]

[[ 0.  0.  0.  0.  0.  0.  0.  0.]

 [ 0.  0.  0.  0.  0.  0.  0.  0.]

 [ 0.  0.  0.  0.  0.  0.  0.  0.]

 [ 0.  0.  0.  0.  0.  0.  0.  0.]

 [ 0.  0.  0.  0.  0.  0.  0.  0.]

 [ 0.  0.  0.  0.  0.  0.  0. 63.]

 [ 0.  0.  0.  0.  0.  0.  0.  0.]

 [ 0.  0.  0.  0.  0.  0.  0.  0.]]

In fact, the answer is simple. For convenience, I rename some variables, look this code:

def unpool(x, argmax, strides, unpool_shape=None, batch_size=None, name='unpool'):

    x_shape = x.get_shape().as_list()

    argmax_shape = argmax.get_shape().as_list()

    assert not(x_shape[0] is None and batch_size is None), "must input batch_size if number of batch is alterable"

    if x_shape[0] is None:

        x_shape[0] = batch_size

    if argmax_shape[0] is None:

        argmax_shape[0] = x_shape[0]

    if unpool_shape is None:

        unpool_shape = [x_shape[i] * strides[i] for i in range(4)]

    x_unpool = tf.get_variable(name=name, shape=[np.prod(unpool_shape)], initializer=tf.zeros_initializer(), trainable=False)

    argmax = tf.cast(argmax, tf.int32)

    argmax = tf.reshape(argmax, [np.prod(argmax_shape)])

    x = tf.reshape(x, [np.prod(argmax.get_shape().as_list())])

    x_unpool_add = tf.scatter_add(x_unpool , argmax, x)

    x_unpool_reshape = tf.reshape(x_unpool_add , unpool_shape)

    return x_unpool_reshape 

x_unpool_add is a op of tf.scatter_add, everytime we compute x_unpool_reshape, x_unpool_add will be called. So x_unpool will add x twice if we compute unpool2 twice. In my origin code, I compute unpool0, unpool1, unpool2 in order, x_unpool_add of unpool1 is called firstly, then when we compute unpool2, because of we need compute unpool1, x_unpool_add will be called again, so it's equal to call x_unpool_add twice, the value is wrong. If we compute unpool2 directly, we will get right result. So replacling tf.scatter_add with tf.scatter_update can avoid this bug.

This code can reproducible this intuitively:

import tensorflow as tf



t1 = tf.get_variable(name='t1', shape=[1], dtype=tf.float32, initializer=tf.zeros_initializer())

t2 = tf.get_variable(name='t2', shape=[1], dtype=tf.float32, initializer=tf.zeros_initializer())

d = tf.scatter_add(t1, [0], [1])

e = tf.scatter_add(t2, [0], d)



with tf.Session() as sess:

    sess.run(tf.global_variables_initializer())

    d_out1 = sess.run(d)

    d_out2 = sess.run(d)

    e_out = sess.run(e)

    print(d_out1)

    print(d_out2)

    print(e_out)

output:

[1.]

[2.]

[3.]