Resnet50代码
# @Author: ---chenzhenhua
# @E-mail: [email protected]
def identity_block(X, f, filters, stage, block):
"""
Implementation of the identity block as defined in Figure 4
Arguments:
X -- input tensor of shape (m, n_H_prev, n_W_prev, n_C_prev)
f -- integer, specifying the 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
# Save the input value. You'll need this later to add back to the main path.
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", kernel_initializer=glorot_uniform(seed=0))(X)
# valid mean no padding / glorot_uniform equal to Xaiver initialization - Steve
X = BatchNormalization(axis=3, name=bn_name_base + "2a")(X)
X = Activation("relu")(X)
### START CODE HERE ###
# 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", kernel_initializer=glorot_uniform(seed=0))(X)
X = BatchNormalization(axis=3, name=bn_name_base + "2b")(X)
X = Activation("relu")(X)
# Third component of main path (≈2 lines)
# Final step: Add shortcut value to main path, and pass it through a RELU activation (≈2 lines)
X = Conv2D(filters=F3, kernel_size=(1, 1), strides=(1, 1), padding="valid",
name=conv_name_base + "2c", kernel_initializer=glorot_uniform(seed=0))(X)
X = BatchNormalization(axis=3, name=bn_name_base + "2c")(X)
X = Add()([X, X_shortcut])
X = Activation("relu")(X)
### END CODE HERE ###
return X
def convolutional_block(X, f, filters, stage, block, s=2):
"""
Implementation of the convolutional block as defined in Figure 4
Arguments:
X -- input tensor of shape (m, n_H_prev, n_W_prev, n_C_prev)
f -- integer, specifying the 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
s -- Integer, specifying the stride to be used
Returns:
X -- output of the convolutional 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
# Save the input value
X_shortcut = X
##### MAIN PATH #####
# First component of main path
X = Conv2D(F1, (1, 1), strides=(s, s), name=conv_name_base + '2a', padding='valid',
kernel_initializer=glorot_uniform(seed=0))(X)
X = BatchNormalization(axis=3, name=bn_name_base + '2a')(X)
X = Activation('relu')(X)
### START CODE HERE ###
# Second component of main path (≈3 lines)
X = Conv2D(F2, (f, f), strides=(1, 1), name=conv_name_base + '2b', padding='same',
kernel_initializer=glorot_uniform(seed=0))(X)
X = BatchNormalization(axis=3, name=bn_name_base + '2b')(X)
X = Activation('relu')(X)
# Third component of main path (≈2 lines)
X = Conv2D(F3, (1, 1), strides=(1, 1), name=conv_name_base + '2c', padding='valid',
kernel_initializer=glorot_uniform(seed=0))(X)
X = BatchNormalization(axis=3, name=bn_name_base + '2c')(X)
##### SHORTCUT PATH #### (≈2 lines)
X_shortcut = Conv2D(F3, (1, 1), strides=(s, s), name=conv_name_base + '1', padding='valid',
kernel_initializer=glorot_uniform(seed=0))(X_shortcut)
X_shortcut = BatchNormalization(axis=3, name=bn_name_base + '1')(X_shortcut)
# Final step: Add shortcut value to main path, and pass it through a RELU activation (≈2 lines)
X = layers.add([X, X_shortcut])
X = Activation('relu')(X)
### END CODE HERE ###
return X
def ResNet50(classes=10):
"""
Implementation of the popular ResNet50 the following architecture:
CONV2D -> BATCHNORM -> RELU -> MAXPOOL -> CONVBLOCK -> IDBLOCK*2 -> CONVBLOCK -> IDBLOCK*3
-> CONVBLOCK -> IDBLOCK*5 -> CONVBLOCK -> IDBLOCK*2 -> AVGPOOL -> TOPLAYER
Arguments:
input_shape -- shape of the images of the dataset
classes -- integer, number of classes
Returns:
model -- a Model() instance in Keras
"""
# Define the input as a tensor with shape input_shape
# X_input = Input(input_shape)
# #X = tf.reshape(X_input, [-1, 256, 256, 1])
#
# def reshapes(X_input):
# embed = tf.reshape(X_input, [-1, 256, 256, 1])
# return embed
#
# X = layers.Lambda(reshapes)(X_input)
#inputs = Input(shape=(32, 32, 3))
#X_input = Input(shape=input_shape)
#X_input = Input(shape=(150528,))
#X = Reshape(ReShape)(X_input)
#X = Reshape((224,224,3))(X_input)
#inputs = Input(shape=(150528,))
#X = Reshape((224,224,3))(inputs)
inputs = Input(shape=input_shape)
if ReShape:
X = Reshape(ReShape)(inputs)
else:
X = inputs
# Zero-Padding
#X = ZeroPadding2D((3, 3))(X_input)
# Stage 1
X = Conv2D(filters=64, kernel_size=(7, 7), strides=(2, 2), name="conv",
kernel_initializer=glorot_uniform(seed=0))(X)
X = BatchNormalization(axis=3, name="bn_conv1")(X)
X = Activation("relu")(X)
X = MaxPooling2D(pool_size=(3, 3), strides=(2, 2))(X)
# Stage 2
X = convolutional_block(X, f=3, filters=[64, 64, 256], stage=2, block="a", s=1)
X = identity_block(X, f=3, filters=[64, 64, 256], stage=2, block="b")
X = identity_block(X, f=3, filters=[64, 64, 256], stage=2, block="c")
### START CODE HERE ###
# Stage 3 (≈4 lines)
# The convolutional block uses three set of filters of size [128,128,512], "f" is 3, "s" is 2 and the block is "a".
# The 3 identity blocks use three set of filters of size [128,128,512], "f" is 3 and the blocks are "b", "c" and "d".
X = convolutional_block(X, f=3, filters=[128, 128, 512], stage=3, block="a", s=1)
X = identity_block(X, f=3, filters=[128, 128, 512], stage=3, block="b")
X = identity_block(X, f=3, filters=[128, 128, 512], stage=3, block="c")
X = identity_block(X, f=3, filters=[128, 128, 512], stage=3, block="d")
# Stage 4 (≈6 lines)
# The convolutional block uses three set of filters of size [256, 256, 1024], "f" is 3, "s" is 2 and the block is "a".
# The 5 identity blocks use three set of filters of size [256, 256, 1024], "f" is 3 and the blocks are "b", "c", "d", "e" and "f".
X = convolutional_block(X, f=3, filters=[256, 256, 1024], stage=4, block="a", s=2)
X = identity_block(X, f=3, filters=[256, 256, 1024], stage=4, block="b")
X = identity_block(X, f=3, filters=[256, 256, 1024], stage=4, block="c")
X = identity_block(X, f=3, filters=[256, 256, 1024], stage=4, block="d")
X = identity_block(X, f=3, filters=[256, 256, 1024], stage=4, block="e")
X = identity_block(X, f=3, filters=[256, 256, 1024], stage=4, block="f")
# Stage 5 (≈3 lines)
# The convolutional block uses three set of filters of size [512, 512, 2048], "f" is 3, "s" is 2 and the block is "a".
# The 2 identity blocks use three set of filters of size [256, 256, 2048], "f" is 3 and the blocks are "b" and "c".
X = convolutional_block(X, f=3, filters=[512, 512, 2048], stage=5, block="a", s=2)
X = identity_block(X, f=3, filters=[512, 512, 2048], stage=5, block="b")
X = identity_block(X, f=3, filters=[512, 512, 2048], stage=5, block="c")
# filters should be [256, 256, 2048], but it fail to be graded. Use [512, 512, 2048] to pass the grading
# AVGPOOL (≈1 line). Use "X = AveragePooling2D(...)(X)"
# The 2D Average Pooling uses a window of shape (2,2) and its name is "avg_pool".
X = AveragePooling2D(pool_size=(2, 2), padding="same")(X)
### END CODE HERE ###
# output layer
X = Flatten()(X)
X = Dense(classes, activation="softmax", name="fc" + str(classes), kernel_initializer=glorot_uniform(seed=0))(X)
#output = Reshape((150528,))(X)
# Create model
model = Model(inputs=inputs, outputs=X, name="model_ResNet50")
return model
