仅仅为了学习Keras的使用,使用一个四层的全连接网络对MNIST数据集进行分类,网络模型各层结点数为:3072: : 1024 : 512:10;
使用50000张图片进行训练,10000张测试:
precision recall f1-score support airplane 0.61 0.69 0.65 1000 automobile 0.69 0.67 0.68 1000 bird 0.43 0.49 0.45 1000 cat 0.40 0.32 0.36 1000 dear 0.49 0.50 0.50 1000 dog 0.45 0.48 0.47 1000 frog 0.58 0.65 0.61 1000 horse 0.63 0.60 0.62 1000 ship 0.72 0.66 0.69 1000 truck 0.63 0.58 0.60 1000 micro avg 0.56 0.56 0.56 10000 macro avg 0.56 0.56 0.56 10000 weighted avg 0.56 0.56 0.56 10000
训练过程中,损失和正确率曲线:
可以看到,训练集的损失在一直降低,而测试集的损失出现大范围波动,并趋于上升,说明在一些epoch之后,出现过拟合;
训练集的正确率也在一直上升,并接近100%;而测试集的正确率达到50%就趋于平稳了;
代码:
#!/usr/bin/env python # -*- coding: utf-8 -*- # @Time : 19-5-9 """ implement classification for CIFAR-10 with Keras """ __author__ = 'Zhen Chen' # import the necessary packages from sklearn.preprocessing import LabelBinarizer from sklearn.metrics import classification_report from keras.models import Sequential from keras.layers import Dense from keras.optimizers import SGD from keras.datasets import cifar10 import matplotlib.pyplot as plt import numpy as np import argparse # construct the argument parse and parse the arguments parser = argparse.ArgumentParser() parser.add_argument("-o", "--output", default="./Training Loss and Accuracy_CIFAR10.png") args = parser.parse_args() # load the training and testing data, scale it into the range [0, 1], # then reshape the design matrix print("[INFO] loading CIFAR-10 data...") ((trainX, trainY), (testX, testY)) = cifar10.load_data() trainX = trainX.astype("float") / 255.0 testX = testX.astype("float") / 255.0 trainX = trainX.reshape((trainX.shape[0], 3072)) testX = testX.reshape((testX.shape[0], 3072)) # convert the labels from integers to vectors lb = LabelBinarizer() trainY = lb.fit_transform(trainY) testY = lb.fit_transform(testY) # initialize the label names for the CIFAR-10 dataset labelNames = ["airplane", "automobile", "bird", "cat", "dear", "dog", "frog", "horse", "ship", "truck"] # define the 2072-1024-512-10 architecture Keras model = Sequential() model.add(Dense(1024, input_shape=(3072,), activation="relu")) model.add(Dense(512, activation="relu")) model.add(Dense(10, activation="softmax")) # train the model using SGD print("[INFO] training network...") sgd = SGD(0.01) model.compile(loss="categorical_crossentropy", optimizer=sgd, metrics=["accuracy"]) H = model.fit(trainX, trainY, validation_data=(testX, testY), epochs=100, batch_size=32) model.save_weights('SGD_100_32.h5') # evaluate the network 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)) # plot the training losss and accuracy 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 on CIRFAR-10") plt.xlabel("Epoch #") plt.ylabel("Loss/Accuracy") plt.legend() plt.savefig(args.output)
来源:https://www.cnblogs.com/chenzhen0530/p/10837622.html