keras-tensorflow CAE维度不匹配

Question

我基本上遵循本指南，以构建使用TensorFlow后端构建卷积自动编码器。指南的主要区别在于我的数据是257x257灰度图像。以下代码：

TRAIN_FOLDER = 'data/OIRDS_gray/'
EPOCHS = 10
SHAPE = (257,257,1)
FILELIST = os.listdir(TRAIN_FOLDER)
def loadTrainData():
    train_data = []
    for fn in FILELIST:
        img = misc.imread(TRAIN_FOLDER + fn)
        img = np.reshape(img,(len(img[0,:]), len(img[:,0]), SHAPE[2]))
        if img.shape != SHAPE:
            print "image shape mismatch!"
            print "Expected: " 
            print SHAPE 
            print "but got:"
            print img.shape
            sys.exit()
        train_data.append (img)
    train_data = np.array(train_data)
    train_data = train_data.astype('float32')/ 255
    return np.array(train_data)
def createModel():
    input_img = Input(shape=SHAPE)
    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',padding='same')(x)
    x = UpSampling2D((2, 2))(x)
    decoded = Conv2D(1, (3, 3), activation='sigmoid',padding='same')(x)
    return Model(input_img, decoded)

x_train = loadTrainData()
autoencoder = createModel()
autoencoder.compile(optimizer='adadelta', loss='binary_crossentropy')
print x_train.shape
autoencoder.summary()
# Run the network
autoencoder.fit(x_train, x_train,
                epochs=EPOCHS,
                batch_size=128,
                shuffle=True)

给我一个错误： ValueError: Error when checking target: expected conv2d_7 to have shape (None, 260, 260, 1) but got array with shape (859, 257, 257, 1)

您可以看到，这不是Theano/Tensorflow后端昏暗订购的标准问题，而是其他问题。我检查了我的数据应该是print x_train.shape：

(859, 257, 257, 1)

我还运行autoencoder.summary()：

_________________________________________________________________
Layer (type)                 Output Shape              Param #
=================================================================
input_1 (InputLayer)         (None, 257, 257, 1)       0
_________________________________________________________________
conv2d_1 (Conv2D)            (None, 257, 257, 16)      160
_________________________________________________________________
max_pooling2d_1 (MaxPooling2 (None, 129, 129, 16)      0
_________________________________________________________________
conv2d_2 (Conv2D)            (None, 129, 129, 8)       1160
_________________________________________________________________
max_pooling2d_2 (MaxPooling2 (None, 65, 65, 8)         0
_________________________________________________________________
conv2d_3 (Conv2D)            (None, 65, 65, 8)         584
_________________________________________________________________
max_pooling2d_3 (MaxPooling2 (None, 33, 33, 8)         0
_________________________________________________________________
conv2d_4 (Conv2D)            (None, 33, 33, 8)         584
_________________________________________________________________
up_sampling2d_1 (UpSampling2 (None, 66, 66, 8)         0
_________________________________________________________________
conv2d_5 (Conv2D)            (None, 66, 66, 8)         584
_________________________________________________________________
up_sampling2d_2 (UpSampling2 (None, 132, 132, 8)       0
_________________________________________________________________
conv2d_6 (Conv2D)            (None, 132, 132, 16)      1168
_________________________________________________________________
up_sampling2d_3 (UpSampling2 (None, 264, 264, 16)      0
_________________________________________________________________
conv2d_7 (Conv2D)            (None, 264, 264, 1)       145
=================================================================
Total params: 4,385
Trainable params: 4,385
Non-trainable params: 0
_________________________________________________________________

现在，我不确定问题在哪里，但是看起来确实出现在Conv2D_6（Param＃太高）上的问题。我确实知道CAE在原则上的工作是如何的，但是我对确切的技术细节尚不那么熟悉，我试图通过弄乱Deonvolution Padding（而不是使用有效）来解决此问题。我与DIM匹配的关闭是(None, 258, 258, 1)。我通过盲目地尝试在反卷积方面的填充组合来实现这一目标，这并不是真正解决问题的明智方法...

在这一点上，我不知所措，任何帮助都将不胜感激

Answer 1

由于您的输入和输出数据相同，因此最终输出形状应与输入形状相同。

最后一个卷积层应具有形状(None, 257,257,1)。

问题之所以发生，是因为您有一个奇数作为图像的尺寸（257）。

应用MaxPooling时，它应将数字除以两个，因此它选择向上或向下舍入（它正在上升，请参阅129，来自257/2 = 128.5）

稍后，当您进行UpSampling时，模型不知道当前尺寸已舍入，它只是将值加倍。序列发生的情况是在最终结果中添加了7个像素。

您可以尝试裁剪结果或填充输入。

我通常使用兼容大小的图像。如果您有3个MaxPooling层，则您的尺寸应为2³的倍数。答案是264。

---

直接填充输入数据：

x_train = numpy.lib.pad(x_train,((0,0),(3,4),(3,4),(0,0)),mode='constant')

这将要求SHAPE=(264,264,1)

填充模型内：

import keras.backend as K
input_img = Input(shape=SHAPE)
x = Lambda(lambda x: K.spatial_2d_padding(x, padding=((3, 4), (3, 4))), output_shape=(264,264,1))(input_img)

裁剪结果：

在您不直接更改实际数据（numpy array）的任何情况下，这都是必需的。

decoded = Lambda(lambda x: x[:,3:-4,3:-4,:], output_shape=SHAPE)(x)