Question

我想使用conv3d在同一CNN结构中同时输入8张图像。我的CNN模型如下：

def build(sample, frame, height, width, channels,  classes):
    model = Sequential()
    inputShape = (sample, frame, height, width, channels)
    chanDim = -1

    if K.image_data_format() == "channels_first":
        inputShape = (sample, frame, channels, height, width)
        chanDim = 1


    model.add(Conv3D(32, (3, 3, 3), padding="same", input_shape=inputShape))
    model.add(Activation("relu"))
    model.add(BatchNormalization(axis=chanDim))
    model.add(MaxPooling3D(pool_size=(2, 2, 2), padding="same", data_format="channels_last"))
    model.add(Dropout(0.25))

    model.add(Conv3D(64, (3, 3, 3), padding="same"))
    model.add(Activation("relu"))
    model.add(BatchNormalization(axis=chanDim))
    model.add(MaxPooling3D(pool_size=(2, 2, 2), padding="same", data_format="channels_last"))
    model.add(Dropout(0.25))
    model.add(Flatten())
    model.add(Dense(128))    #(Dense(1024))
    model.add(Activation("relu"))
    model.add(BatchNormalization())
    model.add(Dropout(0.5))

    # softmax classifier
    model.add(Dense(classes))
    model.add(Activation("softmax")

模型训练如下：

IMAGE_DIMS = (57, 8, 60, 60, 3) # since I have 460 images so 57 sample with 8 image each
data = np.array(data, dtype="float") / 255.0
labels = np.array(labels)
# binarize the labels
lb = LabelBinarizer()
labels = lb.fit_transform(labels)
# note: data is a list of all dataset images
(trainX, testX, trainY, testY) train_test_split(data, labels, test_size=0.2, random_state=42)                                                                                                          
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
model = CNN_Network.build(sample= IMAGE_DIMS[0], frame=IMAGE_DIMS[1],
                      height = IMAGE_DIMS[2], width=IMAGE_DIMS[3],
                      channels=IMAGE_DIMS[4], 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
model.fit_generator(
aug.flow(trainX, trainY, batch_size=BS),
validation_data=(testX, testY),
steps_per_epoch=len(trainX) // BS,
epochs=EPOCHS, verbose=1)

我对input_shape感到困惑，我知道Conv3D需要5D输入，输入是从keras添加批处理的4D，但是我遇到以下错误：

ValueError: Error when checking input: expected conv3d_1_input to have 5 dimensions, but got array with shape (92, 60, 60, 3)

谁能帮助我该怎么办？ 92的结果是什么，我用（57，8，60，60，3）确定input_shape。我的input_shape应该是什么，才能同时将8张彩色图像输入到同一模型。

Answer 1

在Keras Python 3中，输入形状可以如下：

x1-x2

位置：

值1（input_shape = (8, 64, 64, 1)）是帧数
值2（8）是宽度
值3（64）是高度
值4（64）是渠道数量

在python中输入3d-CNN的形状

1 个答案: