我正在用自己的數(shù)據(jù)訓(xùn)練 CNN，我在相同的數(shù)據(jù)上嘗試了 resnet50 和 resnet101 以及我自己的模型，準(zhǔn)確度為 63，驗(yàn)證準(zhǔn)確度為 0.08。我知道問題出在我的數(shù)據(jù)上，我想在拆分?jǐn)?shù)據(jù)之前嘗試對(duì)數(shù)據(jù)進(jìn)行洗牌，但我的數(shù)據(jù)分為 26 個(gè)不同的類，如何在將數(shù)據(jù)拆分為訓(xùn)練集和驗(yàn)證集之前對(duì)數(shù)據(jù)進(jìn)行洗牌。我的數(shù)據(jù)集超過 36K 圖像。(trainX, testX, trainY, testY) = train_test_split(data, labels,    test_size=0.25, stratify=labels, random_state=42)# initialize the training data augmentation objecttrainAug = ImageDataGenerator(    rotation_range=30,    zoom_range=0.15,    width_shift_range=0.2,    height_shift_range=0.2,    shear_range=0.15,    horizontal_flip=True,    fill_mode="nearest")# initialize the validation/testing data augmentation object (which# we'll be adding mean subtraction to)valAug = ImageDataGenerator()# define the ImageNet mean subtraction (in RGB order) and set the# the mean subtraction value for each of the data augmentation# objectsmean = np.array([123.68, 116.779, 103.939], dtype='float32')trainAug.mean = meanvalAug.mean = meanmodel = Sequential()# The first two layers with 32 filters of window size 3x3model.add(Conv2D(32, (5, 5), padding='same', activation='relu', input_shape=(224, 224, 3)))model.add(Conv2D(32, (5, 5), activation='relu'))model.add(MaxPooling2D(pool_size=(2, 2)))model.add(Dropout(0.25))model.add(Conv2D(64, (5, 5), padding='same', activation='relu'))model.add(Conv2D(64, (5, 5), activation='relu'))model.add(MaxPooling2D(pool_size=(2, 2)))model.add(Dropout(0.25))model.add(Conv2D(128, (3, 3), padding='same', activation='relu'))model.add(Conv2D(128, (3, 3), activation='relu'))model.add(MaxPooling2D(pool_size=(2, 2)))model.add(Dropout(0.25))model.add(Flatten())model.add(Dense(512, activation='relu'))model.add(Dropout(0.5))model.add(Dense(labels, activation='softmax'))