Question

我正在学习卷积自动编码器，并且正在使用keras来构建图像降噪器。以下代码可用于构建模型：

denoiser.add(Conv2D(32, (3,3), input_shape=(28,28,1), padding='same')) 
denoiser.add(Activation('relu'))
denoiser.add(MaxPooling2D(pool_size=(2,2)))

denoiser.add(Conv2D(16, (3,3), padding='same'))
denoiser.add(Activation('relu'))
denoiser.add(MaxPooling2D(pool_size=(2,2)))

denoiser.add(Conv2D(8, (3,3), padding='same'))
denoiser.add(Activation('relu'))

################## HEY WHAT NO MAXPOOLING?

denoiser.add(Conv2D(8, (3,3), padding='same'))
denoiser.add(Activation('relu'))
denoiser.add(UpSampling2D((2,2)))

denoiser.add(Conv2D(16, (3,3), padding='same'))
denoiser.add(Activation('relu'))
denoiser.add(UpSampling2D((2,2)))

denoiser.add(Conv2D(1, (3,3), padding='same'))

denoiser.compile(optimizer='adam', loss='mean_squared_error', metrics=['accuracy'])
denoiser.summary()

并给出以下摘要：

_________________________________________________________________
Layer (type)                 Output Shape              Param #   
=================================================================
conv2d_155 (Conv2D)          (None, 28, 28, 32)        320       
_________________________________________________________________
activation_162 (Activation)  (None, 28, 28, 32)        0         
_________________________________________________________________
max_pooling2d_99 (MaxPooling (None, 14, 14, 32)        0         
_________________________________________________________________
conv2d_156 (Conv2D)          (None, 14, 14, 16)        4624      
_________________________________________________________________
activation_163 (Activation)  (None, 14, 14, 16)        0         
_________________________________________________________________
max_pooling2d_100 (MaxPoolin (None, 7, 7, 16)          0         
_________________________________________________________________
conv2d_157 (Conv2D)          (None, 7, 7, 8)           1160      
_________________________________________________________________
activation_164 (Activation)  (None, 7, 7, 8)           0         
_________________________________________________________________
conv2d_158 (Conv2D)          (None, 7, 7, 8)           584       
_________________________________________________________________
activation_165 (Activation)  (None, 7, 7, 8)           0         
_________________________________________________________________
up_sampling2d_25 (UpSampling (None, 14, 14, 8)         0         
_________________________________________________________________
conv2d_159 (Conv2D)          (None, 14, 14, 16)        1168      
_________________________________________________________________
activation_166 (Activation)  (None, 14, 14, 16)        0         
_________________________________________________________________
up_sampling2d_26 (UpSampling (None, 28, 28, 16)        0         
_________________________________________________________________
conv2d_160 (Conv2D)          (None, 28, 28, 1)         145       
=================================================================
Total params: 8,001
Trainable params: 8,001
Non-trainable params: 0
_________________________________________________________________

我不确定如何计算MaxPooling2D，Conv2D，UpSampling2D输出大小。我已经阅读了keras文档，但仍然感到困惑。有许多参数会影响输出形状，例如Conv2D图层的stride或padding，但我不知道它如何精确影响输出形状。

我不明白为什么在注释行之前没有MaxPooling2D层。编辑代码以在注释上方包含convmodel3.add(MaxPooling2D(pool_size=(2,2)))层，它将最终输出形状变为（None，12，12，1）

编辑代码以在注释之前包含convmodel3.add(MaxPooling2D(pool_size=(2,2)))层，然后convmodel3.add(UpSampling2D((2,2)))将最终输出更改为（None，24，24，1）。这不是（None，28，28，1）吗？代码和摘要：

convmodel3 = Sequential()
convmodel3.add(Conv2D(32, (3,3), input_shape=(28,28,1), padding='same')) 
convmodel3.add(Activation('relu'))
convmodel3.add(MaxPooling2D(pool_size=(2,2)))

convmodel3.add(Conv2D(16, (3,3), padding='same'))
convmodel3.add(Activation('relu'))
convmodel3.add(MaxPooling2D(pool_size=(2,2)))

convmodel3.add(Conv2D(8, (3,3), padding='same'))
convmodel3.add(Activation('relu'))
convmodel3.add(MaxPooling2D(pool_size=(2,2))) # ADDED MAXPOOL

################## HEY WHAT NO MAXPOOLING?

convmodel3.add(UpSampling2D((2,2))) # ADDED UPSAMPLING
convmodel3.add(Conv2D(16, (3,3), padding='same'))
convmodel3.add(Activation('relu'))
convmodel3.add(UpSampling2D((2,2)))

convmodel3.add(Conv2D(32, (3,3), padding='same'))
convmodel3.add(Activation('relu'))
convmodel3.add(UpSampling2D((2,2)))

convmodel3.add(Conv2D(1, (3,3), padding='same'))

convmodel3.compile(optimizer='adam', loss='mean_squared_error', metrics=['accuracy'])
convmodel3.summary()

_________________________________________________________________
Layer (type)                 Output Shape              Param #   
=================================================================
conv2d_247 (Conv2D)          (None, 28, 28, 32)        320       
_________________________________________________________________
activation_238 (Activation)  (None, 28, 28, 32)        0         
_________________________________________________________________
max_pooling2d_141 (MaxPoolin (None, 14, 14, 32)        0         
_________________________________________________________________
conv2d_248 (Conv2D)          (None, 14, 14, 16)        4624      
_________________________________________________________________
activation_239 (Activation)  (None, 14, 14, 16)        0         
_________________________________________________________________
max_pooling2d_142 (MaxPoolin (None, 7, 7, 16)          0         
_________________________________________________________________
conv2d_249 (Conv2D)          (None, 7, 7, 8)           1160      
_________________________________________________________________
activation_240 (Activation)  (None, 7, 7, 8)           0         
_________________________________________________________________
max_pooling2d_143 (MaxPoolin (None, 3, 3, 8)           0         
_________________________________________________________________
up_sampling2d_60 (UpSampling (None, 6, 6, 8)           0         
_________________________________________________________________
conv2d_250 (Conv2D)          (None, 6, 6, 16)          1168      
_________________________________________________________________
activation_241 (Activation)  (None, 6, 6, 16)          0         
_________________________________________________________________
up_sampling2d_61 (UpSampling (None, 12, 12, 16)        0         
_________________________________________________________________
conv2d_251 (Conv2D)          (None, 12, 12, 32)        4640      
_________________________________________________________________
activation_242 (Activation)  (None, 12, 12, 32)        0         
_________________________________________________________________
up_sampling2d_62 (UpSampling (None, 24, 24, 32)        0         
_________________________________________________________________
conv2d_252 (Conv2D)          (None, 24, 24, 1)         289       
=================================================================
Total params: 12,201
Trainable params: 12,201
Non-trainable params: 0
_________________________________________________________________

None在输出形状中的意义是什么？

此外，将Conv2D图层编辑为不包含填充，则会引发错误：

ValueError: Negative dimension size caused by subtracting 3 from 2 for 'conv2d_240/convolution' (op: 'Conv2D') with input shapes: [?,2,2,16], [3,3,16,32].

为什么？

Answer 1

对于卷积（此处为2D）图层，要考虑的重点是图像的体积（宽度x高度x深度）以及您提供的四个参数。这些参数是

过滤器数量K
过滤器大小（空间）F
滤波器在S处移动的步幅
零填充P

输出形状的公式为

Wnew =（W-F + 2 * P）/ S +1
Hnew =（H-F + 2 * P）/ S +1
Dnew = K

这是从what is the effect of tf.nn.conv2d() on an input tensor shape?线程中获取的，有关零填充等的更多信息可以在此处找到。

对于最大池化和上采样，其大小仅受池大小和跨度的影响。在您的示例中，池大小为（2,2），并且未定义步幅（因此默认为池大小，请参见此处https://keras.io/layers/pooling/）。上采样的工作原理相同。池大小仅占用一个2x2像素的池，找到它们的总和并将它们放到一个像素中。因此将2x2像素转换为1x1像素，对其进行编码。上采样是一回事，只是在池上重复这些值，而不是对像素值求和。

之所以没有maxpooling图层以及图像尺寸混乱的原因是由于该阶段的图像尺寸。观察网络，图像尺寸已经为[7,7,8]。池大小和步幅分别为（2,2）和2时，会将图像的分辨率降低到[3,3,8]。在上采样层之后，维数将从3-> 6-> 12-> 24开始，您在每一行和每一列中损失了4个像素。

无（None）的意义（如果我错了，我不确定100％肯定，请纠正我）是由于网络期望卷积层上通常有多个图像。通常，预期尺寸为

[Number of images, Width, Height, Depth]

因此，第一个元素为“ no”的原因是您的网络一次只期待一个图像，因此它被指定为“ None”（同样，我对此不太确定）。

如何计算MaxPooling2D，Conv2D，UpSampling2D图层的输出大小？

1 个答案: