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