inception_resnet_v1代码
# @Author: ---chenzhenhua
# @E-mail: [email protected]
import os
os.environ["CUDA_DEVICE_ORDER"]="PCI_BUS_ID"
os.environ["CUDA_VISIBLE_DEVICES"]="3"
import keras
import numpy as np
import math
from tensorflow.python.keras.datasets import cifar10
from tensorflow.python.keras.layers import Conv2D, MaxPooling2D, AveragePooling2D, ZeroPadding2D, GlobalAveragePooling2D
from tensorflow.python.keras.layers import Flatten, Dense, Dropout,BatchNormalization,Activation, Convolution2D, add
from tensorflow.python.keras.layers import Convolution2D
from tensorflow.python.keras.models import Model
from tensorflow.python.keras.layers import Input, concatenate
from tensorflow.python.keras import optimizers, regularizers
from tensorflow.python.keras.preprocessing.image import ImageDataGenerator
from tensorflow.python.keras.initializers import he_normal
from tensorflow.python.keras.callbacks import LearningRateScheduler, TensorBoard, ModelCheckpoint
num_classes = 10
batch_size = 64 # 64 or 32 or other
epochs = 300
iterations = 782
USE_BN=True
DROPOUT=0.2 # keep 80%
CONCAT_AXIS=3
weight_decay=1e-4
DATA_FORMAT='channels_last' # Theano:'channels_first' Tensorflow:'channels_last'
log_filepath = './inception_resnet_v1'
def color_preprocessing(x_train,x_test):
x_train = x_train.astype('float32')
x_test = x_test.astype('float32')
mean = [125.307, 122.95, 113.865]
std = [62.9932, 62.0887, 66.7048]
for i in range(3):
x_train[:,:,:,i] = (x_train[:,:,:,i] - mean[i]) / std[i]
x_test[:,:,:,i] = (x_test[:,:,:,i] - mean[i]) / std[i]
return x_train, x_test
def scheduler(epoch):
if epoch < 100:
return 0.01
if epoch < 200:
return 0.001
return 0.0001
# load data
(x_train, y_train), (x_test, y_test) = cifar10.load_data()
y_train = keras.utils.to_categorical(y_train, num_classes)
y_test = keras.utils.to_categorical(y_test, num_classes)
x_train, x_test = color_preprocessing(x_train, x_test)
def conv_block(x, nb_filter, nb_row, nb_col, border_mode='same', subsample=(1,1), bias=False):
#x = Convolution2D(nb_filter, nb_row, nb_col, subsample=subsample, border_mode=border_mode, bias=bias,
# init="he_normal",dim_ordering='tf',W_regularizer=regularizers.l2(weight_decay))(x)
x = Conv2D(nb_filter, kernel_size = (nb_row, nb_col),padding=border_mode,strides=(1, 1),
kernel_initializer="he_normal")(x)
x = BatchNormalization(momentum=0.9, epsilon=1e-5)(x)
x = Activation('relu')(x)
return x
def create_stem(img_input,concat_axis):
x = Conv2D(32,kernel_size=(3,3),strides=(2,2),padding='same',
kernel_initializer="he_normal",kernel_regularizer=regularizers.l2(weight_decay))(img_input)
x = Activation('relu')(BatchNormalization(momentum=0.9, epsilon=1e-5)(x))
x = Conv2D(32,kernel_size=(3,3),strides=(1,1),padding='same',
kernel_initializer="he_normal",kernel_regularizer=regularizers.l2(weight_decay))(x)
x = Activation('relu')(BatchNormalization(momentum=0.9, epsilon=1e-5)(x))
x = Conv2D(64,kernel_size=(3,3),strides=(1,1),padding='same',
kernel_initializer="he_normal",kernel_regularizer=regularizers.l2(weight_decay))(x)
x = Activation('relu')(BatchNormalization(momentum=0.9, epsilon=1e-5)(x))
x = MaxPooling2D(pool_size=(3,3),strides=2,padding='same',data_format=DATA_FORMAT)(x)
x = Conv2D(80,kernel_size=(1,1),strides=(1,1),padding='same',
kernel_initializer="he_normal",kernel_regularizer=regularizers.l2(weight_decay))(x)
x = Activation('relu')(BatchNormalization(momentum=0.9, epsilon=1e-5)(x))
x = Conv2D(192,kernel_size=(3,3),strides=(1,1),padding='same',
kernel_initializer="he_normal",kernel_regularizer=regularizers.l2(weight_decay))(x)
x = Activation('relu')(BatchNormalization(momentum=0.9, epsilon=1e-5)(x))
x = Conv2D(256,kernel_size=(3,3),strides=(2,2),padding='same',
kernel_initializer="he_normal",kernel_regularizer=regularizers.l2(weight_decay))(x)
x = Activation('relu')(BatchNormalization(momentum=0.9, epsilon=1e-5)(x))
return x
def inception_A(x,params,concat_axis,padding='same',data_format=DATA_FORMAT,scale_residual=False,use_bias=True,kernel_initializer="he_normal",bias_initializer='zeros',kernel_regularizer=None,bias_regularizer=None,activity_regularizer=None,kernel_constraint=None,bias_constraint=None,weight_decay=weight_decay):
(branch1,branch2,branch3,branch4)=params
if weight_decay:
kernel_regularizer=regularizers.l2(weight_decay)
bias_regularizer=regularizers.l2(weight_decay)
else:
kernel_regularizer=None
bias_regularizer=None
#1x1
pathway1=Conv2D(filters=branch1[0],kernel_size=(1,1),strides=1,padding=padding,data_format=data_format,use_bias=use_bias,kernel_initializer=kernel_initializer,bias_initializer=bias_initializer,kernel_regularizer=kernel_regularizer,bias_regularizer=bias_regularizer,activity_regularizer=activity_regularizer,kernel_constraint=kernel_constraint,bias_constraint=bias_constraint)(x)
pathway1 = Activation('relu')(BatchNormalization(momentum=0.9, epsilon=1e-5)(pathway1))
#1x1->3x3
pathway2=Conv2D(filters=branch2[0],kernel_size=(1,1),strides=1,padding=padding,data_format=data_format,use_bias=use_bias,kernel_initializer=kernel_initializer,bias_initializer=bias_initializer,kernel_regularizer=kernel_regularizer,bias_regularizer=bias_regularizer,activity_regularizer=activity_regularizer,kernel_constraint=kernel_constraint,bias_constraint=bias_constraint)(x)
pathway2 = Activation('relu')(BatchNormalization(momentum=0.9, epsilon=1e-5)(pathway2))
pathway2=Conv2D(filters=branch2[1],kernel_size=(3,3),strides=1,padding=padding,data_format=data_format,use_bias=use_bias,kernel_initializer=kernel_initializer,bias_initializer=bias_initializer,kernel_regularizer=kernel_regularizer,bias_regularizer=bias_regularizer,activity_regularizer=activity_regularizer,kernel_constraint=kernel_constraint,bias_constraint=bias_constraint)(pathway2)
pathway2 = Activation('relu')(BatchNormalization(momentum=0.9, epsilon=1e-5)(pathway2))
#1x1->3x3->3x3
pathway3=Conv2D(filters=branch3[0],kernel_size=(1,1),strides=1,padding=padding,data_format=data_format,use_bias=use_bias,kernel_initializer=kernel_initializer,bias_initializer=bias_initializer,kernel_regularizer=kernel_regularizer,bias_regularizer=bias_regularizer,activity_regularizer=activity_regularizer,kernel_constraint=kernel_constraint,bias_constraint=bias_constraint)(x)
pathway3 = Activation('relu')(BatchNormalization(momentum=0.9, epsilon=1e-5)(pathway3))
pathway3=Conv2D(filters=branch3[1],kernel_size=(3,3),strides=1,padding=padding,data_format=data_format,use_bias=use_bias,kernel_initializer=kernel_initializer,bias_initializer=bias_initializer,kernel_regularizer=kernel_regularizer,bias_regularizer=bias_regularizer,activity_regularizer=activity_regularizer,kernel_constraint=kernel_constraint,bias_constraint=bias_constraint)(pathway3)
pathway3 = Activation('relu')(BatchNormalization(momentum=0.9, epsilon=1e-5)(pathway3))
pathway3=Conv2D(filters=branch3[1],kernel_size=(3,3),strides=1,padding=padding,data_format=data_format,use_bias=use_bias,kernel_initializer=kernel_initializer,bias_initializer=bias_initializer,kernel_regularizer=kernel_regularizer,bias_regularizer=bias_regularizer,activity_regularizer=activity_regularizer,kernel_constraint=kernel_constraint,bias_constraint=bias_constraint)(pathway3)
pathway3 = Activation('relu')(BatchNormalization(momentum=0.9, epsilon=1e-5)(pathway3))
# concatenate
pathway_123 = concatenate([pathway1,pathway2,pathway3],axis=concat_axis)
pathway_123 = Conv2D(branch4[0],kernel_size=(1,1),strides=(1,1),padding='same',activation = 'linear',
kernel_initializer="he_normal",kernel_regularizer=regularizers.l2(weight_decay))(pathway_123)
if scale_residual:
x = Lambda(lambda p: p * 0.1)(x)
return add([x,pathway_123])
def reduce_A(x,params,concat_axis,padding='same',data_format=DATA_FORMAT,use_bias=True,kernel_initializer="he_normal",bias_initializer='zeros',kernel_regularizer=None,bias_regularizer=None,activity_regularizer=None,kernel_constraint=None,bias_constraint=None,weight_decay=weight_decay):
(branch1,branch2)=params
if weight_decay:
kernel_regularizer=regularizers.l2(weight_decay)
bias_regularizer=regularizers.l2(weight_decay)
else:
kernel_regularizer=None
bias_regularizer=None
#1x1
pathway1 = Conv2D(filters=branch1[0],kernel_size=(3,3),strides=2,padding=padding,data_format=data_format,use_bias=use_bias,kernel_initializer=kernel_initializer,bias_initializer=bias_initializer,kernel_regularizer=kernel_regularizer,bias_regularizer=bias_regularizer,activity_regularizer=activity_regularizer,kernel_constraint=kernel_constraint,bias_constraint=bias_constraint)(x)
pathway1 = Activation('relu')(BatchNormalization(momentum=0.9, epsilon=1e-5)(pathway1))
#1x1->3x3->3x3
pathway2 = Conv2D(filters=branch2[0],kernel_size=(1,1),strides=1,padding=padding,data_format=data_format,use_bias=use_bias,kernel_initializer=kernel_initializer,bias_initializer=bias_initializer,kernel_regularizer=kernel_regularizer,bias_regularizer=bias_regularizer,activity_regularizer=activity_regularizer,kernel_constraint=kernel_constraint,bias_constraint=bias_constraint)(x)
pathway2 = Activation('relu')(BatchNormalization(momentum=0.9, epsilon=1e-5)(pathway2))
pathway2 = Conv2D(filters=branch2[1],kernel_size=(3,3),strides=1,padding=padding,data_format=data_format,use_bias=use_bias,kernel_initializer=kernel_initializer,bias_initializer=bias_initializer,kernel_regularizer=kernel_regularizer,bias_regularizer=bias_regularizer,activity_regularizer=activity_regularizer,kernel_constraint=kernel_constraint,bias_constraint=bias_constraint)(pathway2)
pathway2 = Activation('relu')(BatchNormalization(momentum=0.9, epsilon=1e-5)(pathway2))
pathway2 = Conv2D(filters=branch2[2],kernel_size=(3,3),strides=2,padding=padding,data_format=data_format,use_bias=use_bias,kernel_initializer=kernel_initializer,bias_initializer=bias_initializer,kernel_regularizer=kernel_regularizer,bias_regularizer=bias_regularizer,activity_regularizer=activity_regularizer,kernel_constraint=kernel_constraint,bias_constraint=bias_constraint)(pathway2)
pathway2 = Activation('relu')(BatchNormalization(momentum=0.9, epsilon=1e-5)(pathway2))
# max pooling
pathway3 = MaxPooling2D(pool_size=(3,3),strides=2,padding=padding,data_format=DATA_FORMAT)(x)
return concatenate([pathway1,pathway2,pathway3],axis=concat_axis)
def inception_B(x,params,concat_axis,padding='same',data_format=DATA_FORMAT,scale_residual=False,use_bias=True,kernel_initializer="he_normal",bias_initializer='zeros',kernel_regularizer=None,bias_regularizer=None,activity_regularizer=None,kernel_constraint=None,bias_constraint=None,weight_decay=weight_decay):
(branch1,branch2,branch3)=params
if weight_decay:
kernel_regularizer=regularizers.l2(weight_decay)
bias_regularizer=regularizers.l2(weight_decay)
else:
kernel_regularizer=None
bias_regularizer=None
#1x1
pathway1=Conv2D(filters=branch1[0],kernel_size=(1,1),strides=1,padding=padding,data_format=data_format,use_bias=use_bias,kernel_initializer=kernel_initializer,bias_initializer=bias_initializer,kernel_regularizer=kernel_regularizer,bias_regularizer=bias_regularizer,activity_regularizer=activity_regularizer,kernel_constraint=kernel_constraint,bias_constraint=bias_constraint)(x)
pathway1 = Activation('relu')(BatchNormalization(momentum=0.9, epsilon=1e-5)(pathway1))
#1x1->1x7->7x1
pathway2=Conv2D(filters=branch2[0],kernel_size=(1,1),strides=1,padding=padding,data_format=data_format,use_bias=use_bias,kernel_initializer=kernel_initializer,bias_initializer=bias_initializer,kernel_regularizer=kernel_regularizer,bias_regularizer=bias_regularizer,activity_regularizer=activity_regularizer,kernel_constraint=kernel_constraint,bias_constraint=bias_constraint)(x)
pathway2 = Activation('relu')(BatchNormalization(momentum=0.9, epsilon=1e-5)(pathway2))
pathway2 = conv_block(pathway2,branch2[1],1,7)
pathway2 = conv_block(pathway2,branch2[2],7,1)
# concatenate
pathway_12 = concatenate([pathway1,pathway2],axis=concat_axis)
pathway_12 = Conv2D(branch3[0],kernel_size=(1,1),strides=(1,1),padding='same',activation = 'linear',
kernel_initializer="he_normal",kernel_regularizer=regularizers.l2(weight_decay))(pathway_12)
if scale_residual:
x = Lambda(lambda p: p * 0.1)(x)
return add([x,pathway_12])
def reduce_B(x,params,concat_axis,padding='same',data_format=DATA_FORMAT,use_bias=True,kernel_initializer="he_normal",bias_initializer='zeros',kernel_regularizer=None,bias_regularizer=None,activity_regularizer=None,kernel_constraint=None,bias_constraint=None,weight_decay=weight_decay):
(branch1,branch2,branch3)=params
if weight_decay:
kernel_regularizer=regularizers.l2(weight_decay)
bias_regularizer=regularizers.l2(weight_decay)
else:
kernel_regularizer=None
bias_regularizer=None
#1x1->3x3
pathway1 = Conv2D(filters=branch1[0],kernel_size=(1,1),strides=1,padding=padding,data_format=data_format,use_bias=use_bias,kernel_initializer=kernel_initializer,bias_initializer=bias_initializer,kernel_regularizer=kernel_regularizer,bias_regularizer=bias_regularizer,activity_regularizer=activity_regularizer,kernel_constraint=kernel_constraint,bias_constraint=bias_constraint)(x)
pathway1 = Activation('relu')(BatchNormalization(momentum=0.9, epsilon=1e-5)(pathway1))
pathway1 = Conv2D(filters=branch1[1],kernel_size=(3,3),strides=2,padding=padding,data_format=data_format,use_bias=use_bias,kernel_initializer=kernel_initializer,bias_initializer=bias_initializer,kernel_regularizer=kernel_regularizer,bias_regularizer=bias_regularizer,activity_regularizer=activity_regularizer,kernel_constraint=kernel_constraint,bias_constraint=bias_constraint)(pathway1)
pathway1 = Activation('relu')(BatchNormalization(momentum=0.9, epsilon=1e-5)(pathway1))
#1x1->3x3
pathway2 = Conv2D(filters=branch2[0],kernel_size=(1,1),strides=1,padding=padding,data_format=data_format,use_bias=use_bias,kernel_initializer=kernel_initializer,bias_initializer=bias_initializer,kernel_regularizer=kernel_regularizer,bias_regularizer=bias_regularizer,activity_regularizer=activity_regularizer,kernel_constraint=kernel_constraint,bias_constraint=bias_constraint)(x)
pathway2 = Activation('relu')(BatchNormalization(momentum=0.9, epsilon=1e-5)(pathway2))
pathway2 = Conv2D(filters=branch2[1],kernel_size=(3,3),strides=2,padding=padding,data_format=data_format,use_bias=use_bias,kernel_initializer=kernel_initializer,bias_initializer=bias_initializer,kernel_regularizer=kernel_regularizer,bias_regularizer=bias_regularizer,activity_regularizer=activity_regularizer,kernel_constraint=kernel_constraint,bias_constraint=bias_constraint)(pathway2)
pathway2 = Activation('relu')(BatchNormalization(momentum=0.9, epsilon=1e-5)(pathway2))
#1x1->3x3->3x3
pathway3 = Conv2D(filters=branch3[0],kernel_size=(1,1),strides=1,padding=padding,data_format=data_format,use_bias=use_bias,kernel_initializer=kernel_initializer,bias_initializer=bias_initializer,kernel_regularizer=kernel_regularizer,bias_regularizer=bias_regularizer,activity_regularizer=activity_regularizer,kernel_constraint=kernel_constraint,bias_constraint=bias_constraint)(x)
pathway3 = Activation('relu')(BatchNormalization(momentum=0.9, epsilon=1e-5)(pathway3))
pathway3 = Conv2D(filters=branch3[1],kernel_size=(3,3),strides=1,padding=padding,data_format=data_format,use_bias=use_bias,kernel_initializer=kernel_initializer,bias_initializer=bias_initializer,kernel_regularizer=kernel_regularizer,bias_regularizer=bias_regularizer,activity_regularizer=activity_regularizer,kernel_constraint=kernel_constraint,bias_constraint=bias_constraint)(pathway3)
pathway3 = Activation('relu')(BatchNormalization(momentum=0.9, epsilon=1e-5)(pathway3))
pathway3 = Conv2D(filters=branch3[2],kernel_size=(3,3),strides=2,padding=padding,data_format=data_format,use_bias=use_bias,kernel_initializer=kernel_initializer,bias_initializer=bias_initializer,kernel_regularizer=kernel_regularizer,bias_regularizer=bias_regularizer,activity_regularizer=activity_regularizer,kernel_constraint=kernel_constraint,bias_constraint=bias_constraint)(pathway3)
pathway3 = Activation('relu')(BatchNormalization(momentum=0.9, epsilon=1e-5)(pathway3))
# max pooling
pathway4 = MaxPooling2D(pool_size=(3,3),strides=2,padding=padding,data_format=DATA_FORMAT)(x)
return concatenate([pathway1,pathway2,pathway3,pathway4],axis=concat_axis)
def inception_C(x,params,concat_axis,padding='same',data_format=DATA_FORMAT,scale_residual=False,use_bias=True,kernel_initializer="he_normal",bias_initializer='zeros',kernel_regularizer=None,bias_regularizer=None,activity_regularizer=None,kernel_constraint=None,bias_constraint=None,weight_decay=weight_decay):
(branch1,branch2,branch3)=params
if weight_decay:
kernel_regularizer=regularizers.l2(weight_decay)
bias_regularizer=regularizers.l2(weight_decay)
else:
kernel_regularizer=None
bias_regularizer=None
#1x1
pathway1=Conv2D(filters=branch1[0],kernel_size=(1,1),strides=1,padding=padding,data_format=data_format,use_bias=use_bias,kernel_initializer=kernel_initializer,bias_initializer=bias_initializer,kernel_regularizer=kernel_regularizer,bias_regularizer=bias_regularizer,activity_regularizer=activity_regularizer,kernel_constraint=kernel_constraint,bias_constraint=bias_constraint)(x)
pathway1 = Activation('relu')(BatchNormalization(momentum=0.9, epsilon=1e-5)(pathway1))
#1x1->1x3->3x1
pathway2=Conv2D(filters=branch2[0],kernel_size=(1,1),strides=1,padding=padding,data_format=data_format,use_bias=use_bias,kernel_initializer=kernel_initializer,bias_initializer=bias_initializer,kernel_regularizer=kernel_regularizer,bias_regularizer=bias_regularizer,activity_regularizer=activity_regularizer,kernel_constraint=kernel_constraint,bias_constraint=bias_constraint)(x)
pathway2 = Activation('relu')(BatchNormalization(momentum=0.9, epsilon=1e-5)(pathway2))
pathway2 = conv_block(pathway2,branch2[1],1,3)
pathway2 = conv_block(pathway2,branch2[2],3,1)
# concatenate
pathway_12 = concatenate([pathway1,pathway2],axis=concat_axis)
pathway_12 = Conv2D(branch3[0],kernel_size=(1,1),strides=(1,1),padding='same',activation = 'linear',
kernel_initializer="he_normal",kernel_regularizer=regularizers.l2(weight_decay))(pathway_12)
if scale_residual:
x = Lambda(lambda p: p * 0.1)(x)
return add([x,pathway_12])
def create_model(img_input):
# stem
x = create_stem(img_input,concat_axis=CONCAT_AXIS)
# 5 x inception_A
for _ in range(5):
x=inception_A(x,params=[(32,),(32,32),(32,32,32),(256,)],concat_axis=CONCAT_AXIS)
# reduce A
x=reduce_A(x,params=[(384,),(192,224,256)],concat_axis=CONCAT_AXIS) # 768
# 10 x inception_B
for _ in range(10):
x=inception_B(x,params=[(128,),(128,128,128),(896,)],concat_axis=CONCAT_AXIS)
# reduce B
x=reduce_B(x,params=[(256,384),(256,256),(256,256,256)],concat_axis=CONCAT_AXIS) # 1280
# 5 x inception_C
for _ in range(5):
x=inception_C(x,params=[(192,),(192,192,192),(1792,)],concat_axis=CONCAT_AXIS)
x=GlobalAveragePooling2D()(x)
x=Dropout(DROPOUT)(x)
x = Dense(num_classes,activation='softmax',kernel_initializer="he_normal",
kernel_regularizer=regularizers.l2(weight_decay))(x)
return x
img_input=Input(shape=(32,32,3))
output = create_model(img_input)
model=Model(img_input,output)
model.summary()
# set optimizer
sgd = optimizers.SGD(lr=.1, momentum=0.9, nesterov=True)
model.compile(loss='categorical_crossentropy', optimizer=sgd, metrics=['accuracy'])
# set callback
tb_cb = TensorBoard(log_dir=log_filepath, histogram_freq=0)
change_lr = LearningRateScheduler(scheduler)
cbks = [change_lr,tb_cb]
# set data augmentation
datagen = ImageDataGenerator(horizontal_flip=True,
width_shift_range=0.125,
height_shift_range=0.125,
fill_mode='constant',cval=0.)
datagen.fit(x_train)
# start training
model.fit_generator(datagen.flow(x_train, y_train,batch_size=batch_size),
steps_per_epoch=iterations,
epochs=epochs,
callbacks=cbks,
validation_data=(x_test, y_test))
model.save('inception_resnet_v1.h5')
