【连载13】详解CNN五大经典模型之一AlexNet
网络结构分析
ReLu激活函数
Local Response Normalization
Overlapping Pooling
Dropout
数据扩充
多GPU训练
AlexNet代码实践
# -*- coding: utf-8 -*-
import copy
import numpy as np
import pandas as pd
import matplotlib
matplotlib.use("Agg")
import matplotlib.pyplot as plt
import os
from matplotlib.pyplot import plot,savefig
from scipy.misc import toimage
from keras.datasets import cifar10,mnist
from keras.models import Sequential, Graph
from keras.layers.core import Dense, Dropout, Activation, Flatten, Reshape
from keras.optimizers import SGD, RMSprop
from keras.utils import np_utils
from keras.regularizers import l2
from keras.layers.convolutional import Convolution2D, MaxPooling2D, ZeroPadding2D, AveragePooling2D
from keras.callbacks import EarlyStopping
from keras.preprocessing.image import ImageDataGenerator
from keras.layers.normalization import BatchNormalization
from keras.callbacks import ModelCheckpoint
from keras import backend as K
import tensorflow as tf
tf.python.control_flow_ops = tf
from PIL import Image
def data_visualize(x, y, num):
plt.figure()
for i in range(0, num*num):
axes=plt.subplot(num,num,i + 1)
axes.set_title("label=" + str(y[i]))
axes.set_xticks([0,10,20,30])
axes.set_yticks([0,10,20,30])
plt.imshow(toimage(x[i]))
plt.tight_layout()
plt.savefig('sample.jpg')
#以下结构统一忽略LRN层
def build_AlexNet(s):
model = Sequential()
#第一层，卷积层 + max pooling
model.add(Convolution2D(96, 11, 11, border_mode='same', input_shape = s))
model.add(Activation("relu"))
model.add(MaxPooling2D(pool_size=(2, 2)))
#第二层，卷积层 + max pooling
model.add(Convolution2D(256, 5, 5, border_mode='same', activation='relu'))
model.add(MaxPooling2D(pool_size=(2, 2)))
#第三层，卷积层
model.add(ZeroPadding2D((1,1)))
model.add(Convolution2D(512, 3, 3, border_mode='same', activation='relu'))
#第四层，卷积层
model.add(ZeroPadding2D((1,1)))
model.add(Convolution2D(1024, 3, 3, border_mode='same', activation='relu'))
#第五层，卷积层
model.add(ZeroPadding2D((1,1)))
model.add(Convolution2D(1024, 3, 3, border_mode='same', activation='relu'))
model.add(MaxPooling2D(pool_size=(2, 2)))
model.add(Flatten())
#第六层，全连接层
model.add(Dense(3072, activation='relu'))
model.add(Dropout(0.5))
#第七层，全连接层
model.add(Dense(4096, activation='relu'))
model.add(Dropout(0.5))
#第八层， 输出层
model.add(Dense(10))
model.add(Activation('softmax'))
return model
if __name__=="__main__":
from keras.utils.visualize_util import plot
//使用第三个GPU卡
with tf.device('/gpu:3'):
gpu_options = tf.GPUOptions(per_process_gpu_memory_fraction=1, allow_growth=True)
//只有卡3可见防止tensorflow占用所有卡
os.environ["CUDA_VISIBLE_DEVICES"]="3"
tf.Session(config=K.tf.ConfigProto(allow_soft_placement=True,
log_device_placement=True,
gpu_options=gpu_options))
(X_train, y_train), (X_test, y_test) = cifar10.load_data()
data_visualize(X_train, y_train, 4)
s = X_train.shape[1:]
model = build_AlexNet(s)
model.summary()
plot(model, to_file="AlexNet.jpg", show_shapes=True)
#定义输入数据并做归一化
dim = 32
channel = 3
class_num = 10
X_train = X_train.reshape(X_train.shape[0], dim, dim, channel).astype('float32') / 255
X_test = X_test.reshape(X_test.shape[0], dim, dim, channel).astype('float32') / 255
Y_train = np_utils.to_categorical(y_train, class_num)
Y_test = np_utils.to_categorical(y_test, class_num)
#预处理与数据扩充
datagen = ImageDataGenerator(
featurewise_center=False,
samplewise_center=False,
featurewise_std_normalization=False,
samplewise_std_normalization=False,
zca_whitening=False,
rotation_range=25,
width_shift_range=0.1,
height_shift_range=0.1,
horizontal_flip=False,
vertical_flip=False)
datagen.fit(X_train)
model.compile(loss='categorical_crossentropy',
optimizer='adadelta',
metrics=['accuracy'])
batch_size = 32
nb_epoch = 10
#import pdb
#pdb.set_trace()
ModelCheckpoint("weights-improvement-{epoch:02d}-{val_acc:.2f}.hdf5", monitor='val_loss', verbose=0, save_best_only=True, save_weights_only=False, mode='auto')
model.fit(X_train, Y_train, batch_size=batch_size, nb_epoch=nb_epoch,
verbose=1, validation_data=(X_test, Y_test))
score = model.evaluate(X_test, Y_test, verbose=0)
print('Test score:', score[0])
print('Test accuracy:', score[1])
y_hat = model.predict_classes(X_test)
test_wrong = [im for im in zip(X_test,y_hat,y_test) if im[1] != im[2]]
plt.figure(figsize=(10, 10))
for ind, val in enumerate(test_wrong[:100]):
plt.subplots_adjust(left=0, right=1, bottom=0, top=1)
plt.subplot(10, 10, ind + 1)
plt.axis("off")
plt.text(0, 0, val[2][0], fontsize=14, color='blue')
plt.text(8, 0, val[1], fontsize=14, color='red')
plt.imshow(toimage(val[0]))
savefig('Wrong.jpg') 赞 (0)