siamese.py

from keras.layers import Input, Conv2D, Lambda, merge, Dense, Flatten, MaxPooling2D
from keras.models import Model, Sequential
from keras.regularizers import l2
from keras import backend as K
from keras.optimizers import SGD, Adam
from keras.losses import binary_crossentropy
import numpy.random as rng
import numpy as np
import os
import matplotlib.pyplot as plt
from sklearn.utils import shuffle

def W_init(shape,name=None):
    """Initialize weights randomly"""
    values = rng.normal(loc=0, scale=1e-2, size=shape)
    return K.variable(values,name=name)

def b_init(shape,name=None):
    """Initialize random"""
    values=rng.normal(loc=0.5,scale=1e-2,size=shape)
    return K.variable(values,name=name)

input_shape = (105, 105, 1)
left_input = Input(input_shape)
right_input = Input(input_shape)

# left and right leg
convnet = Sequential()
convnet.add(Conv2D(64,(10,10),activation='relu',input_shape=input_shape,
                   kernel_initializer=W_init,kernel_regularizer=l2(2e-4)))
convnet.add(MaxPooling2D())
convnet.add(Conv2D(128,(7,7),activation='relu',
                   kernel_regularizer=l2(2e-4),kernel_initializer=W_init,bias_initializer=b_init))
convnet.add(MaxPooling2D())
convnet.add(Conv2D(128,(4,4),activation='relu',kernel_initializer=W_init,kernel_regularizer=l2(2e-4),bias_initializer=b_init))
convnet.add(MaxPooling2D())
convnet.add(Conv2D(256,(4,4),activation='relu',kernel_initializer=W_init,kernel_regularizer=l2(2e-4),bias_initializer=b_init))
convnet.add(Flatten())
convnet.add(Dense(4096,activation="sigmoid",kernel_regularizer=l2(1e-3),kernel_initializer=W_init,bias_initializer=b_init))
#encode each of the two inputs into a vector with the convnet
encoded_l = convnet(left_input)
encoded_r = convnet(right_input)
#merge two encoded inputs with the l1 distance between them
L1_distance = lambda x: K.abs(x[0]-x[1])

both = merge([encoded_l, encoded_r], mode = L1_distance, output_shape=lambda x: x[0])
prediction = Dense(1, activation='sigmoid',bias_initializer=b_init)(both)
siamese_net = Model(input=[left_input,right_input],output=prediction)

optimizer = Adam(0.00006)

siamese_net.compile(loss="binary_crossentropy",optimizer=optimizer)

siamese_net.count_params()