训练具有不同颜色特征的深度分类模型

Question

我有一个简单的顺序深度模型，如下所示，它执行二进制分类。我将数据集图像的 3 个颜色通道传递给模型进行训练。如何将灰度作为第 4 通道添加到模型中？我需要进行哪些更改？

from keras.models import Sequential, load_model, Model
from keras.layers import Dense, Dropout, Flatten, Conv2D, MaxPooling2D
from keras.layers.normalization import BatchNormalization
from PIL import Image
from random import shuffle, choice
import numpy as np
import os
from keras.callbacks import ModelCheckpoint
from keras.preprocessing.image import ImageDataGenerator
from sklearn.model_selection import train_test_split
from keras import optimizers

IMAGE_SIZE = 300
epochs_num = 100
batch_size = 64
IMAGE_DIRECTORY = './data'

def label_img(name):
    if name == 'fire': return np.array([1, 0])
    elif name == 'none' : return np.array([0, 1])

def load_data():
    print("Loading images...")
    train_data = []
    directories = next(os.walk(IMAGE_DIRECTORY))[1]

    for dirname in directories:
        print("Loading {0}".format(dirname))
        file_names = next(os.walk(os.path.join(IMAGE_DIRECTORY, dirname)))[2]
        for i in range(len(file_names)):
            image_name = choice(file_names)
            image_path = os.path.join(IMAGE_DIRECTORY, dirname, image_name)
            label = label_img(dirname)
            if "DS_Store" not in image_path:
                img = Image.open(image_path)
                img = img.resize((IMAGE_SIZE, IMAGE_SIZE), Image.ANTIALIAS)
                train_data.append([np.array(img), label])
    shuffle(train_data)
    return train_data

def create_model():
    model = Sequential()
    model.add(Conv2D(32, kernel_size = (5, 5), activation='relu', input_shape=(IMAGE_SIZE, IMAGE_SIZE, 3)))
    model.add(MaxPooling2D(pool_size=(2,2)))
    model.add(BatchNormalization())
    model.add(Conv2D(64, kernel_size=(3,3), activation='relu'))
    model.add(MaxPooling2D(pool_size=(2,2)))
    model.add(BatchNormalization())
    model.add(Conv2D(128, kernel_size=(3,3), activation='relu'))
    model.add(MaxPooling2D(pool_size=(2,2)))
    model.add(BatchNormalization())
    model.add(Conv2D(64, kernel_size=(3,3), activation='relu'))
    model.add(MaxPooling2D(pool_size=(2,2)))
    model.add(BatchNormalization())
    model.add(Dropout(0.2))
    model.add(Flatten())
    model.add(Dense(256, activation='relu'))
    model.add(Dropout(0.2))
    model.add(Dense(128, activation='relu'))
    model.add(Dense(2, activation = 'softmax'))

    return model

training_data = load_data()
training_images = np.array([i[0] for i in training_data])
training_labels = np.array([i[1] for i in training_data])

print(str(len(training_images)))
# Split the data
training_images, validation_images, training_labels, validation_labels = train_test_split(training_images, training_labels, test_size=0.2, shuffle= True)
print(str(len(training_images)))

print('creating model')
#========================
model = create_model()
model.compile(loss='binary_crossentropy', optimizer='adam', metrics=['accuracy'])

filepath="./checkpoints/model_{epoch:03d}_{accuracy:.4f}_{val_accuracy:.4f}_{val_loss:.7f}.h5"
checkpoint = ModelCheckpoint(filepath, monitor=["accuracy"], verbose=1, mode='max', save_weights_only=False)
callbacks_list = [checkpoint]

datagen = ImageDataGenerator(zoom_range=0.2, horizontal_flip=True)
datagen.fit(training_images)
train_gen=datagen.flow(training_images, training_labels, batch_size=batch_size)
#validation
val_datagen = ImageDataGenerator(horizontal_flip=True)
val_datagen.fit(training_images)
val_gen=datagen.flow(validation_images, validation_labels, batch_size=batch_size)
model.fit(train_gen, validation_data=val_gen, epochs=epochs_num, verbose=1, callbacks=callbacks_list)

Answer 1

我认为您不需要添加灰度，我不确定您是否可以将其“添加”为额外的通道。灰度图像是在同一像素上 RGB 值相同的图像。您可以训练分类器对灰度图像或彩色图像或两者进行分类（不推荐）。但是，如果您的原始数据是彩色图像，请保持原样，如果您需要更多数据，请使用数据增强。