updated_resnet_1.py

import numpy as np
from keras import layers
from keras.layers import Input, Add, Dense, Activation, ZeroPadding2D, BatchNormalization, Flatten, Conv2D, AveragePooling2D, MaxPooling2D, GlobalMaxPooling2D
from keras.models import Model, load_model
from keras.preprocessing import image
# from keras.utils import layer_utils
# from keras.utils.data_utils import get_file
from keras.applications.imagenet_utils import preprocess_input
# from IPython.display import SVG
# from keras.utils.vis_utils import model_to_dot
from keras.utils import plot_model

import scipy.misc
from matplotlib.pyplot import imshow

from keras.layers import Input, Add, Dense, Activation, ZeroPadding2D, BatchNormalization, Flatten, Conv2D, AveragePooling2D, MaxPooling2D, GlobalMaxPooling2D


# x is input, y=F(x)
# identity block simply means input should be equal to output.
#  y = x + F(x)   the layers in a traditional network are learning the true output H(x)
# F(x) = y - x   the layers in a residual network are learning the residual F(x)
# Hence, the name: Residual Block.



def identity_block(X, f, filters, stage, block):
    """

    Arguments:
    X -- input of shape (m, height, width, channel)
    f -- shape of the middle CONV's window for the main path
    filters -- python list of integers, defining the number of filters in the CONV layers of the main path
    stage -- integer, used to name the layers, depending on their position in the network
    block -- string/character, used to name the layers, depending on their position in the network

    Returns:
    X -- output of the identity block, tensor of shape (n_H, n_W, n_C)
    """

    # defining name basis
    conv_name_base = 'res' + str(stage) + block + '_branch'
    bn_name_base = 'bn' + str(stage) + block + '_branch'

    # Retrieve Filters
    F1, F2, F3 = filters

    # Saving the input value.we need this later to add to the output.
    X_shortcut = X

    # First component of main path
    X = Conv2D(filters = F1, kernel_size = (1, 1), strides = (1,1), padding = 'valid', name = conv_name_base + '2a')(X)
    X = BatchNormalization(axis = 3, name = bn_name_base + '2a')(X)
    X = Activation('relu')(X)


    # Second component of main path (≈3 lines)
    X = Conv2D(filters = F2, kernel_size = (f, f), strides = (1,1), padding = 'same', name = conv_name_base + '2b')(X)
    X = BatchNormalization(axis = 3, name = bn_name_base + '2b')(X)
    X = Activation('relu')(X)

    # Third component of main path (≈2 lines)
    X = Conv2D(filters = F3, kernel_size = (1, 1), strides = (1,1), padding = 'valid', name = conv_name_base + '2c')(X)
    X = BatchNormalization(axis = 3, name = bn_name_base + '2c')(X)

    # Final step: Add shortcut value to main path, and pass it through a RELU activation
    X = Add()([X, X_shortcut])
    X = Activation('relu')(X)


    return X


def convolutional_block(X, f, filters, stage, block, s = 2):

    # defining name basis
    conv_name_base = 'res' + str(stage) + block + '_branch'
    bn_name_base = 'bn' + str(stage) + block + '_branch'

    # Retrieve Filters
    F1, F2, F3 = filters

    # Save the input value
    X_shortcut = X


    # First layer
    X = Conv2D(F1, (1, 1), strides = (s,s), name = conv_name_base + '2a')(X) # 1,1 is filter size
    X = BatchNormalization(axis = 3, name = bn_name_base + '2a')(X)  # normalization on channels
    X = Activation('relu')(X)


    # Second layer  (f,f)=3*3 filter by default
    X = Conv2D(filters = F2, kernel_size = (f, f), strides = (1,1), padding = 'same', name = conv_name_base + '2b')(X)
    X = BatchNormalization(axis = 3, name = bn_name_base + '2b')(X)
    X = Activation('relu')(X)


    # Third layer
    X = Conv2D(filters = F3, kernel_size = (1, 1), strides = (1,1), padding = 'valid', name = conv_name_base + '2c')(X)
    X = BatchNormalization(axis = 3, name = bn_name_base + '2c')(X)


    ##### SHORTCUT PATH ####
    X_shortcut = Conv2D(filters = F3, kernel_size = (1, 1), strides = (s,s), padding = 'valid', name = conv_name_base + '1')(X_shortcut)
    X_shortcut = BatchNormalization(axis = 3, name = bn_name_base + '1')(X_shortcut)

    # Final step: Add shortcut value here, and pass it through a RELU activation
    X = Add()([X, X_shortcut])
    X = Activation('relu')(X)


    return X

#Each ResNet block is either 2 layer deep
def ResNet50(input_shape=(64, 64, 3)):
    """
    Implementation of the ResNet50 architecture:
    CONV2D -> BATCHNORM -> RELU -> MAXPOOL -> CONVBLOCK -> IDBLOCK*2 -> CONVBLOCK -> IDBLOCK*3
    -> CONVBLOCK -> IDBLOCK*5 -> CONVBLOCK -> IDBLOCK*2 -> AVGPOOL -> TOPLAYER

    """

    # Define the input as a tensor with shape input_shape
    X_input = Input(input_shape)

    # Zero-Padding
    X = ZeroPadding2D((3, 3))(X_input) #3,3 padding

    # Stage 1
    X = Conv2D(64, (7, 7), strides=(2, 2), name='conv1')(X) #64 filters of 7*7
    X = BatchNormalization(axis=3, name='bn_conv1')(X) #batchnorm applied on channels
    X = Activation('relu')(X)
    X = MaxPooling2D((3, 3), strides=(2, 2))(X) #window size is 3*3

    # Stage 2
    X = convolutional_block(X, f=3, filters=[64, 64, 256], stage=2, block='a', s=1)


    X = identity_block(X, 3, [64, 64, 256], stage=2, block='b')


    X = identity_block(X, 3, [64, 64, 256], stage=2, block='c')


    ### START CODE HERE ###

    # Stage 3
    X = convolutional_block(X, f = 3, filters = [128, 128, 512], stage = 3, block='a', s = 2)
    X = identity_block(X, 3, [128, 128, 512], stage=3, block='b')
    X = identity_block(X, 3, [128, 128, 512], stage=3, block='c')
    X = identity_block(X, 3, [128, 128, 512], stage=3, block='d')

    # Stage 4
    X = convolutional_block(X, f = 3, filters = [256, 256, 1024], stage = 4, block='a', s = 2)
    X = identity_block(X, 3, [256, 256, 1024], stage=4, block='b')
    X = identity_block(X, 3, [256, 256, 1024], stage=4, block='c')
    X = identity_block(X, 3, [256, 256, 1024], stage=4, block='d')
    X = identity_block(X, 3, [256, 256, 1024], stage=4, block='e')
    X = identity_block(X, 3, [256, 256, 1024], stage=4, block='f')

    # Stage 5
    X = convolutional_block(X, f = 3, filters = [512, 512, 2048], stage = 5, block='a', s = 2)
    X = identity_block(X, 3, [512, 512, 2048], stage=5, block='b')
    X = identity_block(X, 3, [512, 512, 2048], stage=5, block='c')

    # AVGPOOL
    X = AveragePooling2D((2,2), name="avg_pool")(X)

    ### END CODE HERE ###

    # output layer
    X = Flatten()(X)
    X = Dense(512, activation='relu')(X)
    X = Dense(128, activation='relu')(X)
    X = Dense(1, name='output')(X)

    # Create model
    model = Model(inputs = X_input, outputs = X, name='ResNet50')

    return model