def model_fc(self,
z,
layer=[2 * 2 * 256, 2 * 2 * 128, 2 * 2 * 64, 2 * 2 * 16, 10]):
output = z
layer_num = 0
with tf.name_scope('reshape'):
reshape_size = 2 * 2 * 256
output = tf.reshape(output, [-1, reshape_size])
for i in range(3):
layer_num += 1
with tf.variable_scope('fc' + str(layer_num)):
output = NNutils.create_layer('fc',
output,
layer[layer_num],
var_list=self.train_list,
dropout=self.dropout_normal)
layer_num += 1
with tf.variable_scope('fc' + str(layer_num)):
output = NNutils.create_layer('fc',
output,
layer[layer_num],
var_list=self.train_list,
activation='none')
y = output
return y
def model_fc(self, z, layer=[7 * 7, 6 * 6, 5 * 5, 10]):
output = z
layer_num = 0
for i in range(2):
layer_num += 1
with tf.variable_scope('fc' + str(layer_num)):
output = NNutils.create_layer('fc',
output,
layer[layer_num],
var_list=self.train_list)
# output = tf.nn.dropout(output, self.dropout_conv)
layer_num += 1
with tf.variable_scope('fc' + str(layer_num)):
output = NNutils.create_layer('fc',
output,
layer[layer_num],
var_list=self.train_list,
activation='none')
y = output
return y
def model(self, x, layer):
image_width = 32
output = x
#first image
layer_num = 0
output1 = output
with tf.variable_scope('1conv' + str(layer_num)):
output1 = NNutils.create_layer('conv', output1, layer[layer_num])
output1 = tf.nn.max_pool(output1, ksize=[1, 2, 2, 1], strides=[1, 2, 2, 1], padding='SAME')
layer_num += 1
with tf.variable_scope('1conv' + str(layer_num)):
output1 = NNutils.create_layer('conv', output1, layer[layer_num])
output1 = tf.nn.max_pool(output1, ksize=[1, 2, 2, 1], strides=[1, 2, 2, 1], padding='SAME')
layer_num += 1
with tf.variable_scope('1conv' + str(layer_num)):
output1 = NNutils.create_layer('conv', output1, layer[layer_num])
output1 = tf.nn.max_pool(output1, ksize=[1, 2, 2, 1], strides=[1, 2, 2, 1], padding='SAME')
layer_num += 1
with tf.variable_scope('1conv' + str(layer_num)):
output1 = NNutils.create_layer('conv', output1, layer[layer_num])
output1 = tf.nn.max_pool(output1, ksize=[1, 2, 2, 1], strides=[1, 2, 2, 1], padding='SAME')
layer_num += 1
with tf.name_scope('reshape'):
output1 = tf.reshape(output1, [-1, image_width * image_width * layer[3]])
#second image
layer_num = 0
output2 = output
with tf.variable_scope('2conv' + str(layer_num)):
output2 = NNutils.create_layer('conv', output2, layer[layer_num])
output2 = tf.nn.max_pool(output2, ksize=[1, 2, 2, 1], strides=[1, 2, 2, 1], padding='SAME')
layer_num += 1
with tf.variable_scope('2conv' + str(layer_num)):
output2 = NNutils.create_layer('conv', output2, layer[layer_num])
output2 = tf.nn.max_pool(output2, ksize=[1, 2, 2, 1], strides=[1, 2, 2, 1], padding='SAME')
layer_num += 1
with tf.variable_scope('2conv' + str(layer_num)):
output2 = NNutils.create_layer('conv', output2, layer[layer_num])
output2 = tf.nn.max_pool(output2, ksize=[1, 2, 2, 1], strides=[1, 2, 2, 1], padding='SAME')
layer_num += 1
with tf.variable_scope('2conv' + str(layer_num)):
output2 = NNutils.create_layer('conv', output2, layer[layer_num])
output2 = tf.nn.max_pool(output2, ksize=[1, 2, 2, 1], strides=[1, 2, 2, 1], padding='SAME')
layer_num += 1
with tf.name_scope('reshape'):
output2 = tf.reshape(output2, [-1, image_width * image_width * layer[3]])
#summation layer
with tf.name_scope('concat'):
output = tf.concat([output1, output2], 0)
with tf.variable_scope('normal' + str(layer_num)):
output = NNutils.create_layer('normal', output, layer[layer_num])
layer_num += 1
with tf.variable_scope('normal' + str(layer_num)):
output = NNutils.create_layer('normal', output, layer[layer_num], activation='none')
layer_num += 1
y = output
return y