2

我使用 Theano 后端实现了一个带有 Keras 的卷积自动编码器。我正在改变我的方法来尝试处理不同尺寸的图像。只要我使用 numpy 的stack函数来构建数据集（相同大小的图像），我就很成功。但是，对于不同大小的图像，我们不能使用stack，并且fit需要一个 numpy 数组。所以我改为fit_generator避免尺寸检查。问题是最后一层期望 16 作为输入中的最后一个维度，我不明白为什么它会获取原始图像的维度。

看看下面的代码和错误输出。


import numpy as np
import keras
from keras.models import Sequential, Model
from keras.layers import Input, Conv2D, MaxPooling2D, UpSampling2D

AE_EPOCHS = 10
VERB = 1
batchsz = 16
outfun = 'sigmoid'

data = []
dimensions = [(10, 15), (12, 15), (7,15), (20,15), (25,15)]

for d in dimensions:
    dd = np.random.rand(*d)
    dd = dd.reshape((1,)+dd.shape)
    data.append(dd)

input_img = Input(shape=(1, None, 15))
filtersz = 3
pad_it = 'same'
size1 = 16
size2 = 8
x = Conv2D(size1, (filtersz, filtersz), activation='relu', padding=pad_it)(input_img)
x = MaxPooling2D((2, 2), padding=pad_it)(x)
x = Conv2D(size2, (filtersz, filtersz), activation='relu', padding=pad_it)(x)
x = MaxPooling2D((2, 2), padding=pad_it)(x)
x = Conv2D(size2, (filtersz, filtersz), activation='relu', padding=pad_it)(x)
encoded = MaxPooling2D((2, 2), padding=pad_it)(x)

x = Conv2D(size2, (filtersz, filtersz), activation='relu', padding=pad_it)(encoded)
x = UpSampling2D((2, 2), data_format="channels_first")(x)
x = Conv2D(size2, (filtersz, filtersz), activation='relu', padding=pad_it)(x)
x = UpSampling2D((2, 2), data_format="channels_first")(x)
x = Conv2D(size1, (filtersz, filtersz), activation='relu', padding=pad_it)(x)
x = UpSampling2D((2, 2), data_format="channels_first")(x)
decoded = Conv2D(1, (filtersz, filtersz), activation=outfun, padding=pad_it)(x)

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

x_train = data[1:]
x_test= data[0].reshape((1,)+ data[0].shape)

def mygen(xx, *args, **kwargs):
    for i in xx:
        yield (i,i)

thegen = mygen(x_train)
#If I use this generator somehow None is returned so it is not used
thegenval = mygen(np.array([x_test]))

hist = autoencoder.fit_generator(thegen,
                epochs=AE_EPOCHS,
                steps_per_epoch=4,
                verbose=VERB,
                validation_data=(x_test, x_test),
                validation_steps=1
                )

回溯（最近一次通话最后）：

文件“stacko.py”，第 107 行，validation_steps=1

包装器中的文件“/usr/local/lib/python3.5/dist-packages/keras/legacy/interfaces.py”，第 88 行，返回 func(*args, **kwargs)

文件“/usr/local/lib/python3.5/dist-packages/keras/engine/training.py”，第 1847 行，在 fit_generator val_x、val_y、val_sample_weight 中）

文件“/usr/local/lib/python3.5/dist-packages/keras/engine/training.py”，第 1315 行，在 _standardize_user_data exception_prefix='target'）

文件“/usr/local/lib/python3.5/dist-packages/keras/engine/training.py”，第 139 行，在 _standardize_input_data str(array.shape))

ValueError：检查目标时出错：预期 conv2d_7 的形状为 (None, 1, None, 16) 但数组的形状为 (1, 1, 10, 15)

4

1 回答 1

0

上面的代码有两个问题：首先，图像轴的大小必须是每层最小过滤器数量的倍数（在本例中为 8）；其次，生成器fit_generator必须返回批次（4D numpy 数组）。

生成器通过itertools.cycle将图形作为一个样本批次来实现并将其重塑为一个样本批次（如果使用具有共同尺寸的多个图像，则每组尺寸可能具有可变尺寸的批次）。工作示例如下。


import numpy as np
from itertools import cycle

import keras
from keras.models import Sequential, Model
from keras.layers import Input, Dense, Conv2D, MaxPooling2D, UpSampling2D

AE_EPOCHS = 10
VERB = 1
outfun = 'sigmoid'

data = []
dimensions = [(16, 32), (24, 32), (8,32), (32,32)]
for d in dimensions:
    dd = np.random.rand(*d)
    dd = dd.reshape((1,)+dd.shape)
    data.append(dd)

input_img = Input(shape=(1, None, 32))
filtersz = 3
pad_it = 'same'
size1 = 16
size2 = 8
x = Conv2D(size1, (filtersz, filtersz), activation='relu', padding=pad_it)(input_img)
x = MaxPooling2D((2, 2), padding=pad_it)(x)
x = Conv2D(size2, (filtersz, filtersz), activation='relu', padding=pad_it)(x)
x = MaxPooling2D((2, 2), padding=pad_it)(x)
x = Conv2D(size2, (filtersz, filtersz), activation='relu', padding=pad_it)(x)
encoded = MaxPooling2D((2, 2), padding=pad_it)(x)

x = Conv2D(size2, (filtersz, filtersz), activation='relu', padding=pad_it)(encoded)
x = UpSampling2D((2, 2), data_format="channels_first")(x)
x = Conv2D(size2, (filtersz, filtersz), activation='relu', padding=pad_it)(x)
x = UpSampling2D((2, 2), data_format="channels_first")(x)
x = Conv2D(size1, (filtersz, filtersz), activation='relu', padding=pad_it)(x)
x = UpSampling2D((2, 2), data_format="channels_first")(x)
decoded = Conv2D(1, (filtersz, filtersz), activation=outfun, padding=pad_it)(x)

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


x_train = data[1:]
x_test= [data[0]]

def mygen(xx, *args, **kwargs):
    for i in cycle(xx):
        ii = i.reshape((1,)+i.shape)
        yield ii,ii

thegen = mygen(x_train)
thegenval = mygen(x_test)

hist = autoencoder.fit_generator(
                thegen,
                epochs=AE_EPOCHS,
                steps_per_epoch=3,
                verbose=VERB,
                validation_data=thegenval,
                validation_steps=1
                )
于 2017-07-15T15:20:06.027 回答