Python 3.x 具有可变尺寸图像的二维卷积神经网络

我用Keras实现了一个卷积自动编码器，使用Theano后端。我正在改变我的方法，尝试处理不同大小的图像。只要我使用numpy的

stack

函数来构建数据集（大小相等的图像），我就是黄金。但是，对于不同大小的图像，我们不能使用

stack

，而

fit

需要一个numpy数组。因此我改为

fit_generator

，以避免尺寸检查。问题是最后一层期望16作为输入中的最后一个维度，我无法理解为什么它得到原始图像的维度

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（最近一次呼叫最后一次）：

文件“stacko.py”，第107行，在 验证步骤=1

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

文件“/usr/local/lib/python3.5/dist-packages/keras/engine/training.py”，第1847行，在fit_生成器中 val_x，val_y，val_样品重量）

文件“/usr/local/lib/python3.5/dist-packages/keras/engine/training.py”，第1315行，在用户数据中 异常（前缀='target'）

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

ValueError:检查目标时出错：预期conv2d_7具有形状（无，1，无，16），但获得具有形状（1，1，10，15）的数组

---

上面的代码有两个问题：第一，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，

fit\u generator

的生成器必须返回批（4D numpy数组）

生成器使用

itertools.cycle

实现，并将图形重塑为一个样本批次（如果使用多个具有常见尺寸的图像，则每个尺寸组可以有不同尺寸的批次）。工作示例如下所示

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
                )