ValueError：檢查目標時出錯：預期conv2d_21具有4個維，但數組的形狀為（26，1）

Question

我有形狀為(3600, 3600, 3) 。 我想對它們使用自動編碼器。 我的代碼是：

from keras.layers import Input, Dense, Conv2D, MaxPooling2D, UpSampling2D
from keras.models import Model
from keras import backend as K
from keras.preprocessing.image import ImageDataGenerator


input_img = Input(shape=(3600, 3600, 3))  

x = Conv2D(16, (3, 3), activation='relu', padding='same')(input_img)
x = MaxPooling2D((2, 2), padding='same')(x)
x = Conv2D(8, (3, 3), activation='relu', padding='same')(x)
x = MaxPooling2D((2, 2), padding='same')(x)
x = Conv2D(8, (3, 3), activation='relu', padding='same')(x)
encoded = MaxPooling2D((2, 2), padding='same')(x)



x = Conv2D(8, (3, 3), activation='relu', padding='same')(encoded)
x = UpSampling2D((2, 2))(x)
x = Conv2D(8, (3, 3), activation='relu', padding='same')(x)
x = UpSampling2D((2, 2))(x)
x = Conv2D(16, (3, 3), activation='relu')(x)
x = UpSampling2D((2, 2))(x)
decoded = Conv2D(1, (3, 3), activation='sigmoid', padding='same')(x)

autoencoder = Model(input_img, decoded)
autoencoder.compile(optimizer='adadelta', loss='binary_crossentropy')




batch_size=2


datagen = ImageDataGenerator(rescale=1. / 255)

# dimensions of our images.
img_width, img_height = 3600, 3600

train_data_dir = 'train'
validation_data_dir = validation




generator_train = datagen.flow_from_directory(
        train_data_dir,
        target_size=(img_width, img_height),
        )



generator_valid = datagen.flow_from_directory(
        validation_data_dir,
        target_size=(img_width, img_height),
        batch_size=batch_size,
        class_mode=None,
        shuffle=False)



autoencoder.fit_generator(generator=generator_train,
            validation_data = generator_valid,
            )

當我運行代碼時，出現以下錯誤消息：

ValueError: Error when checking target: expected conv2d_21 to have 4 dimensions, but got array with shape (26, 1)

我知道問題出在層的形狀中，但是我找不到它。 有人可以幫我解釋一下解決方案嗎？

Answer 1

您的代碼中存在以下問題：

1. 將class_mode='input'傳遞給flow_from_directory方法以將輸入圖像也作為標簽提供（因為您正在創建自動編碼器）。

2. 將padding='same'傳遞到解碼器中的第三個Conv2D層：

    x = Conv2D(16, (3, 3), activation='relu', padding='same')(x) 

3. 由於您的圖像是RGB，請在最后一層使用三個濾鏡：

    decoded = Conv2D(3, (3, 3), activation='sigmoid', padding='same')(x)