keras训练浅层卷积网络并保存和加载模型实例

from sklearn.preprocessing import LabelBinarizer
from sklearn.model_selection import train_test_split
from sklearn.metrics import classification_report
from keras.models import Sequential
from keras.layers.core import Dense
from keras.optimizers import SGD
from sklearn import datasets
import matplotlib.pyplot as plt
import numpy as np
import argparse
# 命令行参数运行
ap = argparse.ArgumentParser()
ap.add_argument("-o", "--output", required=True, help="path to the output loss/accuracy plot")
args =vars(ap.parse_args())
# 加载数据MNIST，然后归一化到【0,1】，同时使用75%做训练，25%做测试
print("[INFO] loading MNIST (full) dataset")
dataset = datasets.fetch_mldata("MNIST Original", data_home="/home/king/test/python/train/pyimagesearch/nn/data/")
data = dataset.data.astype("float") / 255.0
(trainX, testX, trainY, testY) = train_test_split(data, dataset.target, test_size=0.25)
# 将label进行one-hot编码
lb = LabelBinarizer()
trainY = lb.fit_transform(trainY)
testY = lb.transform(testY)
# keras定义网络结构784--256--128--10
model = Sequential()
model.add(Dense(256, input_shape=(784,), activation="relu"))
model.add(Dense(128, activation="relu"))
model.add(Dense(10, activation="softmax"))
# 开始训练
print("[INFO] training network...")
# 0.01的学习率
sgd = SGD(0.01)
# 交叉验证
model.compile(loss="categorical_crossentropy", optimizer=sgd, metrics=['accuracy'])
H = model.fit(trainX, trainY, validation_data=(testX, testY), epochs=100, batch_size=128)
# 测试模型和评估
print("[INFO] evaluating network...")
predictions = model.predict(testX, batch_size=128)
print(classification_report(testY.argmax(axis=1), predictions.argmax(axis=1), 
	target_names=[str(x) for x in lb.classes_]))
# 保存可视化训练结果
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"])

'''
该函数主要是实现keras的一个细节转换，因为训练的图像时RGB三颜色通道，读取进来的数据是有depth的，keras为了兼容一些后台，默认是按照（height， width， depth）读取，但有时候就要改变成（depth， height， width）
'''
from keras.preprocessing.image import img_to_array
class ImageToArrayPreprocessor:
	def __init__(self, dataFormat=None):
		self.dataFormat = dataFormat
 
	def preprocess(self, image):
		return img_to_array(image, data_format=self.dataFormat)
 

'''
定义一个简单的卷基层：
input->conv->Relu->FC
'''
from keras.models import Sequential
from keras.layers.convolutional import Conv2D
from keras.layers.core import Activation, Flatten, Dense
from keras import backend as K
 
class ShallowNet:
	@staticmethod
	def build(width, height, depth, classes):
		model = Sequential()
		inputShape = (height, width, depth)
 
		if K.image_data_format() == "channels_first":
			inputShape = (depth, height, width)
 
		model.add(Conv2D(32, (3, 3), padding="same", input_shape=inputShape))
		model.add(Activation("relu"))
 
		model.add(Flatten())
		model.add(Dense(classes))
		model.add(Activation("softmax"))
 
		return model

from sklearn.preprocessing import LabelBinarizer
from sklearn.metrics import classification_report
from shallownet import ShallowNet
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 dataset")
((trainX, trainY), (testX, testY)) = cifar10.load_data()
trainX = trainX.astype("float") / 255.0
testX = testX.astype("float") / 255.0
 
lb = LabelBinarizer()
trainY = lb.fit_transform(trainY)
testY = lb.transform(testY)
# 标签0-9代表的类别string
labelNames = ['airplane', 'automobile', 'bird', 'cat', 
	'deer', 'dog', 'frog', 'horse', 'ship', 'truck']
 
print("[INFO] compiling model...")
opt = SGD(lr=0.0001)
model = ShallowNet.build(width=32, height=32, depth=3, classes=10)
model.compile(loss="categorical_crossentropy", optimizer=opt, metrics=["accuracy"])
 
print("[INFO] training network...")
H = model.fit(trainX, trainY, validation_data=(testX, testY), batch_size=32, epochs=1000, verbose=1)
 
print("[INFO] evaluating network...")
predictions = model.predict(testX, batch_size=32)
print(classification_report(testY.argmax(axis=1), predictions.argmax(axis=1), 
	target_names=labelNames))
 
# 保存可视化训练结果
plt.style.use("ggplot")
plt.figure()
plt.plot(np.arange(0, 1000), H.history["loss"], label="train_loss")
plt.plot(np.arange(0, 1000), H.history["val_loss"], label="val_loss")
plt.plot(np.arange(0, 1000), H.history["acc"], label="train_acc")
plt.plot(np.arange(0, 1000), 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"])
 

from sklearn.preprocessing import LabelBinarizer
from sklearn.metrics import classification_report
from shallownet import ShallowNet
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")
ap.add_argument("-m", "--model", required=True, help="path to save train model")
args = vars(ap.parse_args())
 
print("[INFO] loading CIFAR-10 dataset")
((trainX, trainY), (testX, testY)) = cifar10.load_data()
trainX = trainX.astype("float") / 255.0
testX = testX.astype("float") / 255.0
 
lb = LabelBinarizer()
trainY = lb.fit_transform(trainY)
testY = lb.transform(testY)
# 标签0-9代表的类别string
labelNames = ['airplane', 'automobile', 'bird', 'cat', 
	'deer', 'dog', 'frog', 'horse', 'ship', 'truck']
 
print("[INFO] compiling model...")
opt = SGD(lr=0.005)
model = ShallowNet.build(width=32, height=32, depth=3, classes=10)
model.compile(loss="categorical_crossentropy", optimizer=opt, metrics=["accuracy"])
 
print("[INFO] training network...")
H = model.fit(trainX, trainY, validation_data=(testX, testY), batch_size=32, epochs=50, verbose=1)
 
model.save(args["model"])
 
print("[INFO] evaluating network...")
predictions = model.predict(testX, batch_size=32)
print(classification_report(testY.argmax(axis=1), predictions.argmax(axis=1), 
	target_names=labelNames))
 
# 保存可视化训练结果
plt.style.use("ggplot")
plt.figure()
plt.plot(np.arange(0, 5), H.history["loss"], label="train_loss")
plt.plot(np.arange(0, 5), H.history["val_loss"], label="val_loss")
plt.plot(np.arange(0, 5), H.history["acc"], label="train_acc")
plt.plot(np.arange(0, 5), 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"])
 

from sklearn.preprocessing import LabelBinarizer
from sklearn.metrics import classification_report
from shallownet import ShallowNet
from keras.optimizers import SGD
from keras.datasets import cifar10
from keras.models import load_model
import matplotlib.pyplot as plt
import numpy as np
import argparse
 
ap = argparse.ArgumentParser()
ap.add_argument("-m", "--model", required=True, help="path to save train model")
args = vars(ap.parse_args())
 
# 标签0-9代表的类别string
labelNames = ['airplane', 'automobile', 'bird', 'cat', 
	'deer', 'dog', 'frog', 'horse', 'ship', 'truck']
 
print("[INFO] loading CIFAR-10 dataset")
((trainX, trainY), (testX, testY)) = cifar10.load_data()
 
idxs = np.random.randint(0, len(testX), size=(10,))
testX = testX[idxs]
testY = testY[idxs]
 
trainX = trainX.astype("float") / 255.0
testX = testX.astype("float") / 255.0
 
lb = LabelBinarizer()
trainY = lb.fit_transform(trainY)
testY = lb.transform(testY)
 
print("[INFO] loading pre-trained network...")
model = load_model(args["model"])
 
print("[INFO] evaluating network...")
predictions = model.predict(testX, batch_size=32).argmax(axis=1)
print("predictions\n", predictions)
for i in range(len(testY)):
	print("label:{}".format(labelNames[predictions[i]]))
 
trueLabel = []
for i in range(len(testY)):
	for j in range(len(testY[i])):
		if testY[i][j] != 0:
			trueLabel.append(j)
print(trueLabel)
 
print("ground truth testY:")
for i in range(len(trueLabel)):
	print("label:{}".format(labelNames[trueLabel[i]]))
 
print("TestY\n", testY)