代码是《Python深度学习》上的,自己敲一遍看看,我自己的联想拯救者跑起来都比较慢,GPU will be better!
# -*- coding: utf-8 -*-
"""
Created on Tue Oct 30 22:04:30 2018
@author: Lxiao217
"""
import os
import numpy as np
from keras.preprocessing.image import ImageDataGenerator
from keras.applications import VGG16
conv_base = VGG16(weights = 'imagenet',
include_top = False,
input_shape = (150,150,3))
base_dir = 'F:\\python\\DeepLearning\\cats_and_dogs_small'
train_dir = os.path.join(base_dir, 'train')
validation_dir = os.path.join(base_dir, 'validation')
test_dir = os.path.join(base_dir, 'test')
datagen = ImageDataGenerator(rescale = 1./255)
batch_size = 20
def extract_features(directory, sample_count):
features = np.zeros(shape = (sample_count, 4, 4, 512))
labels = np.zeros(shape = (sample_count))
generator = datagen.flow_from_directory(
directory,
target_size = (150, 150),
batch_size = batch_size,
class_mode = 'binary')
i = 0
for input_batch, labels_batch in generator:
features_batch = conv_base.predict(input_batch)
features[i * batch_size : (i+1)*batch_size] = features_batch
labels[i*batch_size : (i+1)*batch_size] = labels_batch
i += 1
#注意:这些生成器在循环中不断地生成数据,所以你必须在读取完所有的图像后终止循环
if i * batch_size >= sample_count:
break
return features, labels
train_features, train_labels = extract_features(train_dir, 2000)
validation_features, validation_labels = extract_features(validation_dir, 1000)
test_features, test_labels = extract_features(test_dir, 1000)
#将提取的特征展平
train_features = np.reshape(train_features, (2000, 4*4*512))
validation_features = np.reshape(validation_features, (1000, 4*4*512))
test_features = np.reshape(test_features, (1000, 4*4*512))
from keras import models
from keras import layers
from keras import optimizers
#conv_base.trainable = False #冻结卷积基,不训练这个,因为参数太多
model = models.Sequential()
#model.add(conv_base) #特征提取的第二种方法:扩展conv_base 模型,然后在输入数据上端到端地运行模型
model.add(layers.Dense(256, activation = 'relu', input_dim = 4*4*512))
model.add(layers.Dropout(0.5))
model.add(layers.Dense(1, activation = 'sigmoid'))
model.compile(optimizer = optimizers.RMSprop(lr = 8e-4),
loss = 'binary_crossentropy',
metrics = ['acc'])
history = model.fit(train_features,
train_labels,
epochs = 30,
batch_size = 20,
validation_data = (validation_features, validation_labels))
import matplotlib.pyplot as plt
acc = history.history['acc']
val_acc = history.history['val_acc']
loss = history.history['loss']
val_loss = history.history['val_loss']
epochs = range(1, len(acc) + 1)
plt.plot(epochs, acc, 'b*', label = 'Train_acc')
plt.plot(epochs, val_acc, 'b', label = 'Validation_acc')
plt.title('Training and Validation Accuracy')
plt.legend()
plt.figure()
plt.plot(epochs, loss, 'r*', label = 'Train_loss')
plt.plot(epochs, val_loss, 'r', label = 'Validation_loss')
plt.title('Training and Validation Loss')
plt.legend()
plt.show()
运行的结果如下:
验证精度90%,基本上第四代开始就开始过拟合了,后面使用“微调模型”能达到96%的精度。