数据挖掘 - 将卷积层的输出重塑为哪些维度？ - 吾爱随笔录

我有一个卷积网络，取自这个github，在build.py. 因为它是在过时的 keras 版本中制作的，所以我正在尝试将其重写为 2.1.4 版本。我走了很长一段路，但我（希望）最后一步遇到了一些麻烦。下面我发布了我现在拥有的代码，但我需要做的是最终的重塑。我收到了错误ValueError: total size of new array must be unchanged，根据这个答案我收到了这个错误，因为我的输出形状与我想要重塑的形状不对应。但是我的高度和宽度都是 32 的因数，所以我不明白这个问题。网络的最后一层（批量标准化）返回(Bat (None, 0, 256, 2). 根据我发现的代码，我必须使用

autoencoder.add(Reshape((n_labels, img_h*img_w))

这将是(2, (256 * 256))。这听起来不正确，256 * 256 部分非常大，但我不完全理解重塑功能。毕竟我是从 github 获取的，所以它应该是正确的，但是随着新 keras 版本的引入，符号可以改变。

有人可以阐明这种重塑的作用，并可能建议我需要重塑哪些维度？

这是我正在使用的整个模型：

from keras import models
from keras.layers.core import Activation, Reshape, Permute
from keras.layers.convolutional import Conv2D, MaxPooling2D, UpSampling2D
from keras.layers.normalization import BatchNormalization
import json

img_w = 256
img_h = 256
n_labels = 2

kernel = 3

encoding_layers = [
    Conv2D(64, (kernel,kernel), padding='same', input_shape=(1, img_h, img_w)),
    BatchNormalization(),
    Activation('relu'),
    Conv2D(64, (kernel,kernel), padding='same'),
    BatchNormalization(),
    Activation('relu'),
    MaxPooling2D(),

    Conv2D(128, (kernel,kernel), padding='same'),
    BatchNormalization(),
    Activation('relu'),
    Conv2D(128, (kernel,kernel), padding='same'),
    BatchNormalization(),
    Activation('relu'),
    MaxPooling2D(),

    Conv2D(256, (kernel,kernel), padding='same'),
    BatchNormalization(),
    Activation('relu'),
    Conv2D(256, (kernel,kernel), padding='same'),
    BatchNormalization(),
    Activation('relu'),
    Conv2D(256, (kernel,kernel), padding='same'),
    BatchNormalization(),
    Activation('relu'),
    MaxPooling2D(),

    Conv2D(512, (kernel,kernel), padding='same'),
    BatchNormalization(),
    Activation('relu'),
    Conv2D(512, (kernel,kernel), padding='same'),
    BatchNormalization(),
    Activation('relu'),
    Conv2D(512, (kernel,kernel), padding='same'),
    BatchNormalization(),
    Activation('relu'),
    MaxPooling2D(),

    Conv2D(512, (kernel,kernel), padding='same'),
    BatchNormalization(),
    Activation('relu'),
    Conv2D(512, (kernel,kernel), padding='same'),
    BatchNormalization(),
    Activation('relu'),
    Conv2D(512, (kernel,kernel), padding='same'),
    BatchNormalization(),
    Activation('relu'),
    MaxPooling2D(),
]

autoencoder = models.Sequential()
autoencoder.encoding_layers = encoding_layers

for l in autoencoder.encoding_layers:
    autoencoder.add(l)

decoding_layers = [
    UpSampling2D(),
    Conv2D(512, (kernel,kernel), padding='same'),
    BatchNormalization(),
    Activation('relu'),
    Conv2D(512, (kernel,kernel), padding='same'),
    BatchNormalization(),
    Activation('relu'),
    Conv2D(512, (kernel,kernel), padding='same'),
    BatchNormalization(),
    Activation('relu'),

    UpSampling2D(),
    Conv2D(512, (kernel,kernel), padding='same'),
    BatchNormalization(),
    Activation('relu'),
    Conv2D(512, (kernel,kernel), padding='same'),
    BatchNormalization(),
    Activation('relu'),
    Conv2D(256, (kernel,kernel), padding='same'),
    BatchNormalization(),
    Activation('relu'),

    UpSampling2D(),
    Conv2D(256, (kernel,kernel), padding='same'),
    BatchNormalization(),
    Activation('relu'),
    Conv2D(256, (kernel,kernel), padding='same'),
    BatchNormalization(),
    Activation('relu'),
    Conv2D(128, (kernel,kernel), padding='same'),
    BatchNormalization(),
    Activation('relu'),

    UpSampling2D(),
    Conv2D(128, (kernel,kernel), padding='same'),
    BatchNormalization(),
    Activation('relu'),
    Conv2D(64, (kernel,kernel), padding='same'),
    BatchNormalization(),
    Activation('relu'),

    UpSampling2D(),
    Conv2D(64, (kernel,kernel), padding='same'),
    BatchNormalization(),
    Activation('relu'),
    Conv2D(n_labels, (1, 1), padding='valid'),
    BatchNormalization(),
]
autoencoder.decoding_layers = decoding_layers
for l in autoencoder.decoding_layers:
    autoencoder.add(l)

autoencoder.add(Reshape((n_labels, img_h * img_w)))
autoencoder.add(Permute((2, 1)))
autoencoder.add(Activation('softmax'))

with open('model_5l.json', 'w') as outfile:
    outfile.write(json.dumps(json.loads(autoencoder.to_json()), indent=2))