keras入门-04-图片分类

布满荆棘的人生 2023-02-25 08:52 111阅读 0赞

# 导入所需工具包 #https://keras.io/
    
    import matplotlib
    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 import Dropout
    from keras.layers.core import Dense
    from keras.optimizers import SGD
    from keras import initializers
    from keras import regularizers
    from my_utils import utils_paths
    import matplotlib.pyplot as plt
    import numpy as np
    import argparse
    import random
    import pickle
    import cv2
    import os
    
    print("[INFO] 开始读取数据")
    data = []
    labels = []
    
    # 拿到图像数据路径，方便后续读取
    imagePaths = sorted(list(utils_paths.list_images('./dataset')))
    random.seed(42)
    random.shuffle(imagePaths)
    
    # 遍历读取数据
    for imagePath in imagePaths:
    	# 读取图像数据，由于使用神经网络，需要给定成一维
    	image = cv2.imread(imagePath)
    	image = cv2.resize(image, (32, 32)).flatten()
    	data.append(image)
    
    	# 读取标签
    	label = imagePath.split(os.path.sep)[-2]
    	labels.append(label)
    
    # scale图像数据
    data = np.array(data, dtype="float") / 255.0
    labels = np.array(labels)
    
    # 数据集切分
    (trainX, testX, trainY, testY) = train_test_split(data,
    	labels, test_size=0.25, random_state=42)
    
    # 转换标签，one-hot格式
    lb = LabelBinarizer()
    trainY = lb.fit_transform(trainY)
    testY = lb.transform(testY)
    
    # 网络模型结构：3072-512-256-3 
    model = Sequential()
    # kernel_regularizer=regularizers.l2(0.01)
    # keras.initializers.TruncatedNormal(mean=0.0, stddev=0.05, seed=None)    #截断的高斯分布
    # initializers.random_normal
    # #model.add(Dropout(0.8))
    model.add(Dense(512, input_shape=(3072,), activation="relu" ,kernel_initializer = initializers.TruncatedNormal(mean=0.0, stddev=0.05, seed=None),kernel_regularizer=regularizers.l2(0.01)))
    model.add(Dropout(0.5))
    model.add(Dense(256, activation="relu",kernel_initializer = initializers.TruncatedNormal(mean=0.0, stddev=0.05, seed=None),kernel_regularizer=regularizers.l2(0.01)))
    model.add(Dropout(0.5))
    model.add(Dense(len(lb.classes_), activation="softmax",kernel_initializer = initializers.TruncatedNormal(mean=0.0, stddev=0.05, seed=None),kernel_regularizer=regularizers.l2(0.01)))
    
    # 初始化参数
    INIT_LR = 0.001
    EPOCHS = 20
    
    # 给定损失函数和评估方法
    print("[INFO] 准备训练网络...")
    opt = SGD(lr=INIT_LR)
    model.compile(loss="categorical_crossentropy", optimizer=opt,
    	metrics=["accuracy"])
    
    # 训练网络模型
    H = model.fit(trainX, trainY, validation_data=(testX, testY),
    	epochs=EPOCHS, batch_size=32)
    
    # 测试网络模型
    print("[INFO] 正在评估模型")
    predictions = model.predict(testX, batch_size=32)
    print(classification_report(testY.argmax(axis=1),
    	predictions.argmax(axis=1), target_names=lb.classes_))
    
    # 当训练完成时，绘制结果曲线
    N = np.arange(0, EPOCHS)
    plt.style.use("ggplot")
    plt.figure()
    print(H.history)
    #plt.plot(N[150:], H.history["loss"][150:], label="train_loss")
    #plt.plot(N[150:], H.history["val_loss"][150:], label="val_loss")
    plt.plot(N[150:], H.history["accuracy"][150:], label="train_acc")
    plt.plot(N[150:], H.history["val_accuracy"][150:], label="val_acc")
    plt.title("Training Loss and Accuracy (Simple NN)")
    plt.xlabel("Epoch #")
    plt.ylabel("Loss/Accuracy")
    plt.legend()
    plt.savefig('./output/simple_nn_plot.png')
    
    # 保存模型到本地
    print("[INFO] 正在保存模型")
    model.save('./output/simple_nn_lb.model')
    f = open('./output/simple_nn_lb.pickle', "wb")
    f.write(pickle.dumps(lb))
    f.close()

## lr=0.01 ##

![在这里插入图片描述][watermark_type_ZmFuZ3poZW5naGVpdGk_shadow_10_text_aHR0cHM6Ly9ibG9nLmNzZG4ubmV0L3dlaXhpbl80MzY3MzE1Ng_size_16_color_FFFFFF_t_70]

## lr=0.001 ##

![在这里插入图片描述][watermark_type_ZmFuZ3poZW5naGVpdGk_shadow_10_text_aHR0cHM6Ly9ibG9nLmNzZG4ubmV0L3dlaXhpbl80MzY3MzE1Ng_size_16_color_FFFFFF_t_70 1]

## lr=0.001+Dropout(0.5) ##

![在这里插入图片描述][watermark_type_ZmFuZ3poZW5naGVpdGk_shadow_10_text_aHR0cHM6Ly9ibG9nLmNzZG4ubmV0L3dlaXhpbl80MzY3MzE1Ng_size_16_color_FFFFFF_t_70 2]  
train和test的相差较少！！！

调参数的过程，lr和Dropout（防止过拟合）

## 需要数据可以私聊哦！！！！ ##

[watermark_type_ZmFuZ3poZW5naGVpdGk_shadow_10_text_aHR0cHM6Ly9ibG9nLmNzZG4ubmV0L3dlaXhpbl80MzY3MzE1Ng_size_16_color_FFFFFF_t_70]: /images/20230209/30d4c3f31034443c830969044a399def.png
[watermark_type_ZmFuZ3poZW5naGVpdGk_shadow_10_text_aHR0cHM6Ly9ibG9nLmNzZG4ubmV0L3dlaXhpbl80MzY3MzE1Ng_size_16_color_FFFFFF_t_70 1]: /images/20230209/22860cbb163e4eaa811053d0467ee09e.png
[watermark_type_ZmFuZ3poZW5naGVpdGk_shadow_10_text_aHR0cHM6Ly9ibG9nLmNzZG4ubmV0L3dlaXhpbl80MzY3MzE1Ng_size_16_color_FFFFFF_t_70 2]: /images/20230209/da92b07d7f76463e886c66d37fa2c87b.png