我训练了一个 CNN 来对图像进行分类，效果很好。我正在尝试添加一个包含数据的 MLP 以改进模型，正如我在多篇论文中读到的那样。
有人可以建议我在何处以及如何将 MLP 连接到 CNN 中吗？
感谢您的任何建议。
创建 CNN：
def plt_imshow(title, image):
# convert the image frame BGR to RGB color space and display it
image = cv2.cvtColor(image, cv2.COLOR_BGR2RGB)
plt.imshow(image)
plt.title(title)
plt.grid(False)
plt.show()
class SmallerVGGNet:
@staticmethod
def build(width, height, depth, classes):
# initialize the model along with the input shape to be
# "channels last" and the channels dimension itself
model = Sequential()
inputShape = (height, width, depth)
chanDim = -1
# if we are using "channels first", update the input shape
# and channels dimension
if K.image_data_format() == "channels_first":
inputShape = (depth, height, width)
chanDim = 1
# CONV => RELU => POOL
model.add(Conv2D(32, (3, 3), padding="same",
input_shape=inputShape))
model.add(Activation("relu"))
model.add(BatchNormalization(axis=chanDim))
model.add(MaxPooling2D(pool_size=(3, 3)))
model.add(Dropout(0.25))
# (CONV => RELU) * 2 => POOL
model.add(Conv2D(64, (3, 3), padding="same"))
model.add(Activation("relu"))
model.add(BatchNormalization(axis=chanDim))
model.add(Conv2D(64, (3, 3), padding="same"))
model.add(Activation("relu"))
model.add(BatchNormalization(axis=chanDim))
model.add(MaxPooling2D(pool_size=(2, 2)))
model.add(Dropout(0.25))
# (CONV => RELU) * 2 => POOL
model.add(Conv2D(128, (3, 3), padding="same"))
model.add(Activation("relu"))
model.add(BatchNormalization(axis=chanDim))
model.add(Conv2D(128, (3, 3), padding="same"))
model.add(Activation("relu"))
model.add(BatchNormalization(axis=chanDim))
model.add(MaxPooling2D(pool_size=(2, 2)))
model.add(Dropout(0.25))
# first (and only) set of FC => RELU layers
model.add(Flatten())
model.add(Dense(1024))
model.add(Activation("relu"))
model.add(BatchNormalization())
model.add(Dropout(0.5))
# softmax classifier
model.add(Dense(classes))
model.add(Activation("softmax"))
# return the constructed network architecture
return model
# initialize the number of epochs to train for, initial learning rate,
# batch size, and image dimensions
EPOCHS = 100
INIT_LR = 1e-3
BS = 32
IMAGE_DIMS = (96, 96, 3)
# initialize the data and labels
data = []
labels = []
# grab the image paths and randomly shuffle them
print("[INFO] loading images...")
imagePaths = sorted(list(paths.list_images(args["dataset"])))
random.seed(42)
random.shuffle(imagePaths)
# loop over the input images
for imagePath in imagePaths:
# load the image, pre-process it, and store it in the data list
image = cv2.imread(imagePath)
image = cv2.resize(image, (IMAGE_DIMS[1], IMAGE_DIMS[0]))
image = img_to_array(image)
data.append(image)
# extract the class label from the image path and update the
# labels list
label = imagePath.split(os.path.sep)[-2]
labels.append(label)
# scale the raw pixel intensities to the range [0, 1]
data = np.array(data, dtype="float") / 255.0
labels = np.array(labels)
print("[INFO] data matrix: {:.2f}MB".format(
data.nbytes / (1024 * 1000.0)))
# binarize the labels
lb = LabelBinarizer()
labels = lb.fit_transform(labels)
# partition the data into training and testing splits using 80% of
# the data for training and the remaining 20% for testing
(trainX, testX, trainY, testY) = train_test_split(data,
labels, test_size=0.2, random_state=42)
# construct the image generator for data augmentation
aug = ImageDataGenerator(rotation_range=25, width_shift_range=0.1,
height_shift_range=0.1, shear_range=0.2, zoom_range=0.2,
horizontal_flip=True, fill_mode="nearest")
# initialize the model
print("[INFO] compiling model...")
model = SmallerVGGNet.build(width=IMAGE_DIMS[1], height=IMAGE_DIMS[0],
depth=IMAGE_DIMS[2], classes=len(lb.classes_))
opt = Adam(lr=INIT_LR, decay=INIT_LR / EPOCHS)
model.compile(loss="categorical_crossentropy", optimizer=opt,
metrics=["accuracy"])
# train the network
print("[INFO] training network...")
H = model.fit(
x=aug.flow(trainX, trainY, batch_size=BS),
validation_data=(testX, testY),
steps_per_epoch=len(trainX) // BS,
epochs=EPOCHS, verbose=1)
创建 MLP：
def load_house_attributes(inputPath):
# initialize the list of column names in the CSV file and then
# load it using Pandas
cols = ["bedrooms", "bathrooms", "area", "zipcode", "price"]
df = pd.read_csv(inputPath, sep=" ", header=None, names=cols)
# determine (1) the unique zip codes and (2) the number of data
# points with each zip code
zipcodes = df["zipcode"].value_counts().keys().tolist()
counts = df["zipcode"].value_counts().tolist()
# loop over each of the unique zip codes and their corresponding
# count
for (zipcode, count) in zip(zipcodes, counts):
# the zip code counts for our housing dataset is *extremely*
# unbalanced (some only having 1 or 2 houses per zip code)
# so let's sanitize our data by removing any houses with less
# than 25 houses per zip code
if count < 25:
idxs = df[df["zipcode"] == zipcode].index
df.drop(idxs, inplace=True)
# return the data frame
return df
def process_house_attributes(df, train, test):
# initialize the column names of the continuous data
continuous = ["bedrooms", "bathrooms", "area"]
# performing min-max scaling each continuous feature column to
# the range [0, 1]
cs = MinMaxScaler()
trainContinuous = cs.fit_transform(train[continuous])
testContinuous = cs.transform(test[continuous])
# one-hot encode the zip code categorical data (by definition of
# one-hot encoding, all output features are now in the range [0, 1])
zipBinarizer = LabelBinarizer().fit(df["zipcode"])
trainCategorical = zipBinarizer.transform(train["zipcode"])
testCategorical = zipBinarizer.transform(test["zipcode"])
# construct our training and testing data points by concatenating
# the categorical features with the continuous features
trainX = np.hstack([trainCategorical, trainContinuous])
testX = np.hstack([testCategorical, testContinuous])
# return the concatenated training and testing data
return (trainX, testX)
def create_mlp(dim, regress=False):
# define our MLP network
model = Sequential()
model.add(Dense(8, input_dim=dim, activation="relu"))
model.add(Dense(4, activation="relu"))
# check to see if the regression node should be added
if regress:
model.add(Dense(1, activation="linear"))
# return our model
return model
# construct the path to the input .txt file that contains information
# on each house in the dataset and then load the dataset
print("[INFO] loading house attributes...")
inputPath = os.path.sep.join([args["dataset"], "HousesInfo.txt"])
df = load_house_attributes(inputPath)
# partition the data into training and testing splits using 75% of
# the data for training and the remaining 25% for testing
print("[INFO] processing data...")
split = train_test_split(df, test_size=0.25, random_state=42)
(trainAttrX, testAttrX) = split
# find the largest house price in the training set and use it to
# scale our house prices to the range [0, 1] (will lead to better
# training and convergence)
maxPrice = trainAttrX["price"].max()
trainY = trainAttrX["price"] / maxPrice
testY = testAttrX["price"] / maxPrice
# process the house attributes data by performing min-max scaling
# on continuous features, one-hot encoding on categorical features,
# and then finally concatenating them together
(trainAttrX, testAttrX) = process_house_attributes(df, trainAttrX, testAttrX)
# create the MLP
mlp = create_mlp(trainAttrX.shape[1], regress=False)