> For the complete documentation index, see [llms.txt](https://baozoulin.gitbook.io/neural-networks-and-deep-learning/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://baozoulin.gitbook.io/neural-networks-and-deep-learning/di-si-men-ke-juan-ji-shen-jing-wang-luo-convolutional-neural-networks/convolutional-neural-networks/special-applications/inceptionblocks-py.md). # inception\_blocks.py ```python import tensorflow as tf import numpy as np import os from numpy import genfromtxt from keras import backend as K from keras.layers import Conv2D, ZeroPadding2D, Activation, Input, concatenate from keras.models import Model from keras.layers.normalization import BatchNormalization from keras.layers.pooling import MaxPooling2D, AveragePooling2D import fr_utils from keras.layers.core import Lambda, Flatten, Dense def inception_block_1a(X): """ Implementation of an inception block """ X_3x3 = Conv2D(96, (1, 1), data_format='channels_first', name ='inception_3a_3x3_conv1')(X) X_3x3 = BatchNormalization(axis=1, epsilon=0.00001, name = 'inception_3a_3x3_bn1')(X_3x3) X_3x3 = Activation('relu')(X_3x3) X_3x3 = ZeroPadding2D(padding=(1, 1), data_format='channels_first')(X_3x3) X_3x3 = Conv2D(128, (3, 3), data_format='channels_first', name='inception_3a_3x3_conv2')(X_3x3) X_3x3 = BatchNormalization(axis=1, epsilon=0.00001, name='inception_3a_3x3_bn2')(X_3x3) X_3x3 = Activation('relu')(X_3x3) X_5x5 = Conv2D(16, (1, 1), data_format='channels_first', name='inception_3a_5x5_conv1')(X) X_5x5 = BatchNormalization(axis=1, epsilon=0.00001, name='inception_3a_5x5_bn1')(X_5x5) X_5x5 = Activation('relu')(X_5x5) X_5x5 = ZeroPadding2D(padding=(2, 2), data_format='channels_first')(X_5x5) X_5x5 = Conv2D(32, (5, 5), data_format='channels_first', name='inception_3a_5x5_conv2')(X_5x5) X_5x5 = BatchNormalization(axis=1, epsilon=0.00001, name='inception_3a_5x5_bn2')(X_5x5) X_5x5 = Activation('relu')(X_5x5) X_pool = MaxPooling2D(pool_size=3, strides=2, data_format='channels_first')(X) X_pool = Conv2D(32, (1, 1), data_format='channels_first', name='inception_3a_pool_conv')(X_pool) X_pool = BatchNormalization(axis=1, epsilon=0.00001, name='inception_3a_pool_bn')(X_pool) X_pool = Activation('relu')(X_pool) X_pool = ZeroPadding2D(padding=((3, 4), (3, 4)), data_format='channels_first')(X_pool) X_1x1 = Conv2D(64, (1, 1), data_format='channels_first', name='inception_3a_1x1_conv')(X) X_1x1 = BatchNormalization(axis=1, epsilon=0.00001, name='inception_3a_1x1_bn')(X_1x1) X_1x1 = Activation('relu')(X_1x1) # CONCAT inception = concatenate([X_3x3, X_5x5, X_pool, X_1x1], axis=1) return inception def inception_block_1b(X): X_3x3 = Conv2D(96, (1, 1), data_format='channels_first', name='inception_3b_3x3_conv1')(X) X_3x3 = BatchNormalization(axis=1, epsilon=0.00001, name='inception_3b_3x3_bn1')(X_3x3) X_3x3 = Activation('relu')(X_3x3) X_3x3 = ZeroPadding2D(padding=(1, 1), data_format='channels_first')(X_3x3) X_3x3 = Conv2D(128, (3, 3), data_format='channels_first', name='inception_3b_3x3_conv2')(X_3x3) X_3x3 = BatchNormalization(axis=1, epsilon=0.00001, name='inception_3b_3x3_bn2')(X_3x3) X_3x3 = Activation('relu')(X_3x3) X_5x5 = Conv2D(32, (1, 1), data_format='channels_first', name='inception_3b_5x5_conv1')(X) X_5x5 = BatchNormalization(axis=1, epsilon=0.00001, name='inception_3b_5x5_bn1')(X_5x5) X_5x5 = Activation('relu')(X_5x5) X_5x5 = ZeroPadding2D(padding=(2, 2), data_format='channels_first')(X_5x5) X_5x5 = Conv2D(64, (5, 5), data_format='channels_first', name='inception_3b_5x5_conv2')(X_5x5) X_5x5 = BatchNormalization(axis=1, epsilon=0.00001, name='inception_3b_5x5_bn2')(X_5x5) X_5x5 = Activation('relu')(X_5x5) X_pool = AveragePooling2D(pool_size=(3, 3), strides=(3, 3), data_format='channels_first')(X) X_pool = Conv2D(64, (1, 1), data_format='channels_first', name='inception_3b_pool_conv')(X_pool) X_pool = BatchNormalization(axis=1, epsilon=0.00001, name='inception_3b_pool_bn')(X_pool) X_pool = Activation('relu')(X_pool) X_pool = ZeroPadding2D(padding=(4, 4), data_format='channels_first')(X_pool) X_1x1 = Conv2D(64, (1, 1), data_format='channels_first', name='inception_3b_1x1_conv')(X) X_1x1 = BatchNormalization(axis=1, epsilon=0.00001, name='inception_3b_1x1_bn')(X_1x1) X_1x1 = Activation('relu')(X_1x1) inception = concatenate([X_3x3, X_5x5, X_pool, X_1x1], axis=1) return inception def inception_block_1c(X): X_3x3 = fr_utils.conv2d_bn(X, layer='inception_3c_3x3', cv1_out=128, cv1_filter=(1, 1), cv2_out=256, cv2_filter=(3, 3), cv2_strides=(2, 2), padding=(1, 1)) X_5x5 = fr_utils.conv2d_bn(X, layer='inception_3c_5x5', cv1_out=32, cv1_filter=(1, 1), cv2_out=64, cv2_filter=(5, 5), cv2_strides=(2, 2), padding=(2, 2)) X_pool = MaxPooling2D(pool_size=3, strides=2, data_format='channels_first')(X) X_pool = ZeroPadding2D(padding=((0, 1), (0, 1)), data_format='channels_first')(X_pool) inception = concatenate([X_3x3, X_5x5, X_pool], axis=1) return inception def inception_block_2a(X): X_3x3 = fr_utils.conv2d_bn(X, layer='inception_4a_3x3', cv1_out=96, cv1_filter=(1, 1), cv2_out=192, cv2_filter=(3, 3), cv2_strides=(1, 1), padding=(1, 1)) X_5x5 = fr_utils.conv2d_bn(X, layer='inception_4a_5x5', cv1_out=32, cv1_filter=(1, 1), cv2_out=64, cv2_filter=(5, 5), cv2_strides=(1, 1), padding=(2, 2)) X_pool = AveragePooling2D(pool_size=(3, 3), strides=(3, 3), data_format='channels_first')(X) X_pool = fr_utils.conv2d_bn(X_pool, layer='inception_4a_pool', cv1_out=128, cv1_filter=(1, 1), padding=(2, 2)) X_1x1 = fr_utils.conv2d_bn(X, layer='inception_4a_1x1', cv1_out=256, cv1_filter=(1, 1)) inception = concatenate([X_3x3, X_5x5, X_pool, X_1x1], axis=1) return inception def inception_block_2b(X): #inception4e X_3x3 = fr_utils.conv2d_bn(X, layer='inception_4e_3x3', cv1_out=160, cv1_filter=(1, 1), cv2_out=256, cv2_filter=(3, 3), cv2_strides=(2, 2), padding=(1, 1)) X_5x5 = fr_utils.conv2d_bn(X, layer='inception_4e_5x5', cv1_out=64, cv1_filter=(1, 1), cv2_out=128, cv2_filter=(5, 5), cv2_strides=(2, 2), padding=(2, 2)) X_pool = MaxPooling2D(pool_size=3, strides=2, data_format='channels_first')(X) X_pool = ZeroPadding2D(padding=((0, 1), (0, 1)), data_format='channels_first')(X_pool) inception = concatenate([X_3x3, X_5x5, X_pool], axis=1) return inception def inception_block_3a(X): X_3x3 = fr_utils.conv2d_bn(X, layer='inception_5a_3x3', cv1_out=96, cv1_filter=(1, 1), cv2_out=384, cv2_filter=(3, 3), cv2_strides=(1, 1), padding=(1, 1)) X_pool = AveragePooling2D(pool_size=(3, 3), strides=(3, 3), data_format='channels_first')(X) X_pool = fr_utils.conv2d_bn(X_pool, layer='inception_5a_pool', cv1_out=96, cv1_filter=(1, 1), padding=(1, 1)) X_1x1 = fr_utils.conv2d_bn(X, layer='inception_5a_1x1', cv1_out=256, cv1_filter=(1, 1)) inception = concatenate([X_3x3, X_pool, X_1x1], axis=1) return inception def inception_block_3b(X): X_3x3 = fr_utils.conv2d_bn(X, layer='inception_5b_3x3', cv1_out=96, cv1_filter=(1, 1), cv2_out=384, cv2_filter=(3, 3), cv2_strides=(1, 1), padding=(1, 1)) X_pool = MaxPooling2D(pool_size=3, strides=2, data_format='channels_first')(X) X_pool = fr_utils.conv2d_bn(X_pool, layer='inception_5b_pool', cv1_out=96, cv1_filter=(1, 1)) X_pool = ZeroPadding2D(padding=(1, 1), data_format='channels_first')(X_pool) X_1x1 = fr_utils.conv2d_bn(X, layer='inception_5b_1x1', cv1_out=256, cv1_filter=(1, 1)) inception = concatenate([X_3x3, X_pool, X_1x1], axis=1) return inception def faceRecoModel(input_shape): """ Implementation of the Inception model used for FaceNet Arguments: input_shape -- shape of the images of the dataset Returns: model -- a Model() instance in Keras """ # Define the input as a tensor with shape input_shape X_input = Input(input_shape) # Zero-Padding X = ZeroPadding2D((3, 3))(X_input) # First Block X = Conv2D(64, (7, 7), strides = (2, 2), name = 'conv1')(X) X = BatchNormalization(axis = 1, name = 'bn1')(X) X = Activation('relu')(X) # Zero-Padding + MAXPOOL X = ZeroPadding2D((1, 1))(X) X = MaxPooling2D((3, 3), strides = 2)(X) # Second Block X = Conv2D(64, (1, 1), strides = (1, 1), name = 'conv2')(X) X = BatchNormalization(axis = 1, epsilon=0.00001, name = 'bn2')(X) X = Activation('relu')(X) # Zero-Padding + MAXPOOL X = ZeroPadding2D((1, 1))(X) # Second Block X = Conv2D(192, (3, 3), strides = (1, 1), name = 'conv3')(X) X = BatchNormalization(axis = 1, epsilon=0.00001, name = 'bn3')(X) X = Activation('relu')(X) # Zero-Padding + MAXPOOL X = ZeroPadding2D((1, 1))(X) X = MaxPooling2D(pool_size = 3, strides = 2)(X) # Inception 1: a/b/c X = inception_block_1a(X) X = inception_block_1b(X) X = inception_block_1c(X) # Inception 2: a/b X = inception_block_2a(X) X = inception_block_2b(X) # Inception 3: a/b X = inception_block_3a(X) X = inception_block_3b(X) # Top layer X = AveragePooling2D(pool_size=(3, 3), strides=(1, 1), data_format='channels_first')(X) X = Flatten()(X) X = Dense(128, name='dense_layer')(X) # L2 normalization X = Lambda(lambda x: K.l2_normalize(x,axis=1))(X) # Create model instance model = Model(inputs = X_input, outputs = X, name='FaceRecoModel') return model ``` --- # Agent Instructions This documentation is published with GitBook. GitBook is the documentation platform designed so that both humans and AI agents can read, navigate, and reason over technical content effectively. Learn more at gitbook.com. ## Querying This Documentation If you need additional information that is not directly available in this page, you can query the documentation dynamically by asking a question. Perform an HTTP GET request on the current page URL with the `ask` query parameter: ``` GET https://baozoulin.gitbook.io/neural-networks-and-deep-learning/di-si-men-ke-juan-ji-shen-jing-wang-luo-convolutional-neural-networks/convolutional-neural-networks/special-applications/inceptionblocks-py.md?ask= ``` The question should be specific, self-contained, and written in natural language. The response will contain a direct answer to the question and relevant excerpts and sources from the documentation. Use this mechanism when the answer is not explicitly present in the current page, you need clarification or additional context, or you want to retrieve related documentation sections.