Deep.Learning.for.Computer.Vision.with.Python-----chapter10 例子---keras_cifar10.py

---

一、代码演示

keras_cifar10.py：

"""
CIFAR-10，包含60,000张、10个类别 ,32×32RGB图像的集合，这意味着数据集中的每个图像都由32×32×3=3,072个整数表示
"""
from sklearn.preprocessing import LabelBinarizer
from sklearn.metrics import classification_report
from keras.models import Sequential
from keras.layers.core import Dense
from keras.optimizers import SGD
from keras.datasets import cifar10
import matplotlib.pyplot as plt
import numpy as np
import argparse

ap = argparse.ArgumentParser()
ap.add_argument("-o","--output",required=True,help="path to the output loss/accuracy plot")
args = vars(ap.parse_args())

print("[INFO] loading CIFAR-10 data...")
((trainX,trainY),(testX,testY)) = cifar10.load_data()
trainX = trainX.astype("float")/255.0
testX = testX.astype("float")/225.0
print(trainX.shape)#(50000,32,32,3)
"reshape为 （50000,3072）"
trainX = trainX.reshape(trainX.shape[0],3072)
testX = testX.reshape(testX.shape[0],3072)

lb = LabelBinarizer()
#一般对训练集做fit+transform处理，对测试集仅作transform处理
trainY = lb.fit_transform(trainY)
testY = lb.transform(testY)

labelNames = ["airplane", "automobile", "bird", "cat", "deer",
"dog", "frog", "horse", "ship", "truck"]

#使用Keras定义3072-1024-512-10网络结构
model = Sequential()
model.add(Dense(1024, input_shape=(3072,),activation="relu"))
model.add(Dense(512,activation="relu"))
model.add(Dense(10,activation="softmax"))

#训练
print("[INFO] training network...")
sgd = SGD(0.01)
#metrics:评价函数 acc和val_acc就是通过定义评价函数得到的
model.compile(loss="categorical_crossentropy",optimizer=sgd,metrics=["accuracy"])
H = model.fit(trainX,trainY,batch_size=32,epochs=100,validation_data=(testX,testY))

print("[INFO] evaluating network...")
predictions = model.predict(testX,batch_size=32)
#当axis=1，是在行中比较，选出最大的 列 索引
print(classification_report(testY.argmax(axis=1),predictions.argmax(axis=1),target_names=labelNames))

plt.style.use("ggplot")
plt.figure()
plt.plot(np.arange(0, 100), H.history["loss"], label="train_loss")
plt.plot(np.arange(0, 100), H.history["val_loss"], label="val_loss")
plt.plot(np.arange(0, 100), H.history["acc"], label="train_acc")
plt.plot(np.arange(0, 100), H.history["val_acc"], label="val_acc")
plt.title("Training Loss and Accuracy")
plt.xlabel("Epoch #")
plt.ylabel("Loss/Accuracy")
plt.legend()
plt.savefig(args["output"])

二、注意事项

1.执行该程序
方法一：最好从电脑终端（或pycharm终端执行）进入 该程序所在路径 执行语句:python keras_cifar10.py --output output/keras_cifar10.png