Trying to add CNN to an MLP Siamese - tensorflow

Question

I'm getting an incompatible shape error when trying trying to add a CNN to a ready siamese code that I got from github : here is the link :
https://github.com/ywpkwon/siamese_tf_mnist
here is the code for running the session:
""" Siamese implementation using Tensorflow with MNIST example.
This siamese network embeds a 28x28 image (a point in 784D)
into a point in 2D.
By Youngwook Paul Kwon (young at berkeley.edu)
"""
from __future__ import absolute_import
from __future__ import division
from __future__ import print_function
#import system things
from tensorflow.examples.tutorials.mnist import input_data # for data
import tensorflow as tf
import numpy as np
import os
#import helpers
import inference
import visualize
# prepare data and tf.session
mnist = input_data.read_data_sets('MNIST_data', one_hot=False)
sess = tf.InteractiveSession()
# setup siamese network
siamese = inference.siamese();
train_step = tf.train.GradientDescentOptimizer(0.01).minimize(siamese.loss)
saver = tf.train.Saver()
tf.initialize_all_variables().run()
# start training
if new:
for step in range(1000):
batch_x1, batch_y1 = mnist.train.next_batch(128)
batch_x2, batch_y2 = mnist.train.next_batch(128)
batch_y = (batch_y1 == batch_y2).astype('float')
_, loss_v = sess.run([train_step, siamese.loss], feed_dict={
siamese.x1: batch_x1,
siamese.x2: batch_x2,
siamese.y_: batch_y})
if step % 10 == 0:
print ('step %d: loss' % (step))
print (loss_v)
here is the code for creating the Siamese model.
import tensorflow as tf
class siamese:
# Create model
def __init__(self):
self.x1 = tf.placeholder(tf.float32, [None, 784])
self.x2 = tf.placeholder(tf.float32, [None, 784])
with tf.variable_scope("siamese") as scope:
self.o1 = self.network(self.x1)
scope.reuse_variables()
self.o2 = self.network(self.x2)
# Create loss
self.y_ = tf.placeholder(tf.float32, [None])
self.loss = self.loss_with_step()
def network(self, x):
weights = []
fc1 = self.fc_layer(x, 1024, "fc1" , [5, 5, 1, 32])
return fc1
def fc_layer(self, bottom, n_weight, name,kernel_shape ): #[5, 5, 1, 32]
assert len(bottom.get_shape()) == 2
#n_prev_weight = bottom.get_shape()[1]
initer = tf.truncated_normal_initializer(stddev=0.01)
weights_for_convolution = tf.get_variable(name+"weights_for_convolution", kernel_shape,
initializer=tf.random_normal_initializer())
bias_shape = kernel_shape[-1]
biases_for_convolution = tf.get_variable(name+"biases_for_convolution", [bias_shape],
initializer=tf.constant_initializer(0.1))
biases_for_connected_layer = tf.get_variable(name+"biases_for_connected_layer", [1024],
initializer=tf.constant_initializer(0.1))
weights_for_connected_layer = tf.get_variable(name+"weights_for_connected_layer", [7*7*64,1024],
initializer=tf.random_normal_initializer())
W = tf.get_variable(name+'W', dtype=tf.float32, shape=[1024,2], initializer=initer)
b = tf.get_variable(name+'b', dtype=tf.float32, initializer=tf.constant(0.01, shape=[2], dtype=tf.float32))
#weights_for_readout_layer = tf.get_variable("weights_for_readout_layer", [1024,2],
#initializer=tf.random_normal_initializer())
#biases_for_readout_layer = tf.get_variable("biases_for_readout_layer", [2],
#initializer=tf.constant_initializer(0.1))
bottom1 = tf.reshape(bottom,[-1,28,28,1]) ##
c2 = tf.nn.conv2d(bottom1, weights_for_convolution, strides=[1, 1, 1, 1], padding='SAME')
conv = tf.nn.bias_add(c2, biases_for_convolution)
relu = tf.nn.relu(conv)
out = tf.nn.max_pool(relu, ksize=[1, 2, 2, 1],
strides=[1, 2, 2, 1], padding='SAME')
#print tf.shape(out)
h_out_flat = tf.reshape(out ,[-1,7*7*64])
h_fc1 = tf.nn.relu(tf.matmul(h_out_flat, weights_for_connected_layer) + biases_for_connected_layer)
#compute model output
final_output = tf.matmul(h_fc1,W) + b
#fc = tf.nn.bias_add(tf.matmul(bottom, W), b)
return final_output
def loss_with_spring(self):
margin = 5.0
labels_t = self.y_
labels_f = tf.subtract(1.0, self.y_, name="1-yi") # labels_ = !labels;
eucd2 = tf.pow(tf.subtract(self.o1, self.o2), 2)
print tf.shape(eucd2)
eucd2 = tf.reduce_sum(eucd2, 1)
eucd = tf.sqrt(eucd2+1e-6, name="eucd")
C = tf.constant(margin, name="C")
# yi*||CNN(p1i)-CNN(p2i)||^2 + (1-yi)*max(0, C-||CNN(p1i)-CNN(p2i)||^2)
pos = tf.multiply(labels_t, eucd2, name="yi_x_eucd2")
# neg = tf.multiply(labels_f, tf.subtract(0.0,eucd2), name="yi_x_eucd2")
# neg = tf.multiply(labels_f, tf.maximum(0.0, tf.subtract(C,eucd2)), name="Nyi_x_C-eucd_xx_2")
neg = tf.multiply(labels_f, tf.pow(tf.maximum(tf.subtract(C, eucd), 0), 2), name="Nyi_x_C-eucd_xx_2")
losses = tf.add(pos, neg, name="losses")
loss = tf.reduce_mean(losses, name="loss")
return loss
def loss_with_step(self):
margin = 5.0
labels_t = self.y_ #128
labels_f = tf.subtract(1.0, self.y_, name="1-yi") # labels_ = !labels;
eucd2 = tf.pow(tf.subtract(self.o1, self.o2), 2)
eucd2 = tf.reduce_sum(eucd2, 1)
eucd = tf.sqrt(eucd2+1e-6, name="eucd")
C = tf.constant(margin, name="C")
pos = tf.multiply(labels_t, eucd, name="y_x_eucd")
neg = tf.multiply(labels_f, tf.maximum(0.0, tf.subtract(C, eucd)), name="Ny_C-eucd")
losses = tf.add(pos, neg, name="losses")
loss = tf.reduce_mean(losses, name="loss")
return loss
Actually as the batch size is 128 label-t is 128,
the problem here is that the euclidean distance in the loss_with_step function,
as well as in the loss_with_spring function is of size 256 and not 128 I don't really know why!
here is the error I get.
Traceback (most recent call last):
File "run1.py", line 56, in <module>
siamese.y_: batch_y})
File "/home/sudonuma/anaconda2/envs/tensorflow/lib/python2.7/site- packages/tensorflow/python/client/session.py", line 789, in run
run_metadata_ptr)
File "/home/sudonuma/anaconda2/envs/tensorflow/lib/python2.7/site- packages/tensorflow/python/client/session.py", line 997, in _run
feed_dict_string, options, run_metadata)
File "/home/sudonuma/anaconda2/envs/tensorflow/lib/python2.7/site- packages/tensorflow/python/client/session.py", line 1132, in _do_run
target_list, options, run_metadata)
File "/home/sudonuma/anaconda2/envs/tensorflow/lib/python2.7/site- packages/tensorflow/python/client/session.py", line 1152, in _do_call
raise type(e)(node_def, op, message)
tensorflow.python.framework.errors_impl.InvalidArgumentError: Incompatible shapes: [128] vs. [256]
[[Node: y_x_eucd = Mul[T=DT_FLOAT, _device="/job:localhost/ replica:0/task:0/cpu:0"](_arg_Placeholder_2_0_2, eucd)]]
Caused by op u'y_x_eucd', defined at:
File "run1.py", line 28, in <module>
siamese = inference1.siamese();
File "/home/sudonuma/Documents/siamese for mnist/siamese_tf_mnist-master /inference1.py", line 18, in __init__
self.loss = self.loss_with_step()
File "/home/sudonuma/Documents/siamese for mnist/siamese_tf_mnist-master /inference1.py", line 110, in loss_with_step
pos = tf.multiply(labels_t, eucd, name="y_x_eucd")
File "/home/sudonuma/anaconda2/envs/tensorflow/lib/python2.7/site- packages/tensorflow/python/ops/math_ops.py", line 286, in multiply
return gen_math_ops._mul(x, y, name)
File "/home/sudonuma/anaconda2/envs/tensorflow/lib/python2.7/site- packages/tensorflow/python/ops/gen_math_ops.py", line 1377, in _mul
result = _op_def_lib.apply_op("Mul", x=x, y=y, name=name)
File "/home/sudonuma/anaconda2/envs/tensorflow/lib/python2.7/site- packages/tensorflow/python/framework/op_def_library.py", line 767, in apply
_op
op_def=op_def)
File "/home/sudonuma/anaconda2/envs/tensorflow/lib/python2.7/site- packages/tensorflow/python/framework/ops.py", line 2506, in create_op
original_op=self._default_original_op, op_def=op_def)
File "/home/sudonuma/anaconda2/envs/tensorflow/lib/python2.7/site- packages/tensorflow/python/framework/ops.py", line 1269, in __init__
self._traceback = _extract_stack()
InvalidArgumentError (see above for traceback): Incompatible shapes: [128] vs. [256]
[[Node: y_x_eucd = Mul[T=DT_FLOAT, _device="/job:localhost /replica:0/task:0/cpu:0"](_arg_Placeholder_2_0_2, eucd)]]
can anyone help?

Answer 1

Looks like your reshaping after the convolution is wrong. The output of the convolution layer would be 14x14x32 for a 28x28x1 input passed through conv(stride=1)-maxpool(stride 2). So you need to change the flatten layer to :
h_out_flat = tf.reshape(out ,[-1,14*14*32])
and also the weights_for_connected_layer appropriately.