这里我们使用keras定义简单的神经网络全连接层训练MNIST数据集和cifar10数据集：

keras_mnist.py

from sklearn.preprocessing import LabelBinarizerfrom sklearn.model_selection import train_test_splitfrom sklearn.metrics import classification_reportfrom keras.models import Sequentialfrom keras.layers.core import Densefrom keras.optimizers import SGDfrom sklearn import datasetsimport matplotlib.pyplot as pltimport numpy as npimport 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--10model = 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"])

使用relu做激活函数：

使用sigmoid做激活函数：

接着我们自己定义一些modules去实现一个简单的卷基层去训练cifar10数据集：

imagetoarraypreprocessor.py

'''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_arrayclass ImageToArrayPreprocessor: def __init__(self, dataFormat=None): self.dataFormat = dataFormat def preprocess(self, image): return img_to_array(image, data_format=self.dataFormat)

shallownet.py

'''定义一个简单的卷基层：input->conv->Relu->FC'''from keras.models import Sequentialfrom keras.layers.convolutional import Conv2Dfrom keras.layers.core import Activation, Flatten, Densefrom 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

然后就是训练代码：

keras_cifar10.py

from sklearn.preprocessing import LabelBinarizerfrom sklearn.metrics import classification_reportfrom shallownet import ShallowNetfrom keras.optimizers import SGDfrom keras.datasets import cifar10import matplotlib.pyplot as pltimport numpy as npimport 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") / 255.0testX = 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stringlabelNames = ['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"])

代码中可以对训练的learning rate进行微调，大概可以接近60%的准确率。

然后修改下代码可以保存训练模型：

from sklearn.preprocessing import LabelBinarizerfrom sklearn.metrics import classification_reportfrom shallownet import ShallowNetfrom keras.optimizers import SGDfrom keras.datasets import cifar10import matplotlib.pyplot as pltimport numpy as npimport 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") / 255.0testX = 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stringlabelNames = ['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"])

命令行运行：

我们使用另一个程序来加载上一次训练保存的模型，然后进行测试：

test.py

from sklearn.preprocessing import LabelBinarizerfrom sklearn.metrics import classification_reportfrom shallownet import ShallowNetfrom keras.optimizers import SGDfrom keras.datasets import cifar10from keras.models import load_modelimport matplotlib.pyplot as pltimport numpy as npimport 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stringlabelNames = ['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") / 255.0testX = 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)

以上这篇keras训练浅层卷积网络并保存和加载模型实例就是小编分享给大家的全部内容了，希望能给大家一个参考，也希望大家多多支持。