Keras:ValueError:从1减去5引起的负尺寸大小

Question

当我尝试定义我的模型时,我收到以下错误消息: ValueError: Negative dimension size caused by subtracting 5 from 1 for 'conv2d_19/convolution' (op: 'Conv2D') with input shapes: [?,1,1,32], [5,5,32,64].

以下是重现问题的代码段:

from keras.models import Sequential
from keras.layers import Dense, Dropout, Activation, Flatten
from keras.layers import Convolution2D, MaxPooling2D, AveragePooling2D
import numpy as np

nb_filters = 32
batch_size = 128
epochs = 5
nb_classes = 10

pool_size = (3, 3)
kernel_size = (5, 5)

img_rows = 32
img_cols = 32

input_shape = (img_rows, img_cols, 1)

model = Sequential()
model.add(Convolution2D(nb_filters, kernel_size,
                        input_shape=input_shape))
model.add(Activation('relu'))
model.add(MaxPooling2D(pool_size=pool_size))
model.add(Convolution2D(nb_filters, kernel_size))
model.add(Activation('relu'))
model.add(AveragePooling2D(pool_size=pool_size))
model.add(Convolution2D(nb_filters*2, kernel_size))
model.add(Activation('relu'))
model.add(AveragePooling2D(pool_size=pool_size))
model.add(Flatten())
model.add(Dense(nb_classes))
model.add(Activation('softmax'))

使用Python 2.7.11和Keras 2.1.1在MacOS上观察到了这个问题.

我构建模型的方式有问题吗？

这是我想要构建的架构:

1. 卷积层具有32个大小为5×5的过滤器,最大池化超过3×3区域,以及ReLU激活
2. 旋转层具有32个大小为5×5的过滤器,ReLU激活和3×3区域的平均池
3. 具有64个5×5过滤器,ReLU激活和3×3区域平均汇集的卷积层
4. 与softmax完全连接的层.

Answer 1

对于模型中应用的所有池,输入形状只是很小.

我们来看看你的模型:

model = Sequential()
model.add(Convolution2D(nb_filters, kernel_size, input_shape=input_shape))
model.add(Activation('relu'))
model.add(MaxPooling2D(pool_size=pool_size))
model.add(Convolution2D(nb_filters, kernel_size))
model.add(Activation('relu'))
model.add(AveragePooling2D(pool_size=pool_size))

直到这里一切都很好.AveragePooling2D图层的输出形状为(1,1,32).

_________________________________________________________________
Layer (type)                 Output Shape              Param #   
=================================================================
conv2d_1 (Conv2D)            (None, 28, 28, 32)        832       
_________________________________________________________________
activation_1 (Activation)    (None, 28, 28, 32)        0         
_________________________________________________________________
max_pooling2d_1 (MaxPooling2 (None, 9, 9, 32)          0         
_________________________________________________________________
conv2d_2 (Conv2D)            (None, 5, 5, 32)          25632     
_________________________________________________________________
activation_2 (Activation)    (None, 5, 5, 32)          0         
_________________________________________________________________
average_pooling2d_1 (Average (None, 1, 1, 32)          0         
=================================================================

现在你想要应用另一个内核大小为3的Convolution2D层,尽管最后一层的输出只是(1,1,32).所以你想要学习一个大小(3,3)的内核,它实际上比你想要学习它的数据要小.

现在,您可以增加数据的输入形状((79,79,？)是适用于您的模型的最小值),也可以更改模型.

• 减小池大小
• 通过添加padding='same'到卷积层来应用填充
• 削减你的模型

干杯