machine-learning - 词向量上的 CNN 会引发输入维度错误

Question

我有一个包含大约 14560 个维度为 400 的字向量的数据框。我已将每个向量 reshape 为 20*20 并使用 1 个 channel 来应用 CNN，因此维度已变为 (14560,20,20,1) 。当我尝试拟合 CNN 模型时，它会抛出错误。

代码:

from keras.models import Sequential
from keras.layers.core import Dense, Dropout, Activation, Flatten
from keras.layers.convolutional import Convolution2D, MaxPooling2D
from keras.layers import BatchNormalization
from keras.utils import np_utils
from keras import backend as K

model_cnn=Sequential()
model_cnn.add(Convolution2D(filters = 16, kernel_size = (3, 3), 
activation='relu',input_shape = (20, 20,1)))

model_cnn.compile(loss='categorical_crossentropy', optimizer = 'adadelta', 
metrics=["accuracy"])

model_cnn.fit(x_tr_,y_tr_,validation_data=(x_te_,y_te))

错误:

Error when checking target: expected conv2d_6 to have 4 dimensions, but got array with shape (14560, 1). When I reshape train data to (14560,1,20,20) still it gives error as model receives input =(1,20,20) and required is (20,20,1).

我该如何修复它？

Answer 1

问题

问题不仅仅在于 x_tr 形状，正如另一个答案中正确指出的那样，它应该是 (-1,20,20,1) 。这也是网络架构本身。如果您执行model_cnn.summary()，您将看到以下内容:

Layer (type)                 Output Shape              Param #   
=================================================================
conv2d_1 (Conv2D)            (None, 18, 18, 16)        160       
=================================================================
Total params: 160
Trainable params: 160
Non-trainable params: 0

模型的输出排名为 4:(batch_size, 18, 18, 16)。当标签为 (batch_size, 1) 时，它无法计算损失。

解决方案

正确的架构必须将卷积输出张量 (batch_size, 18, 18, 16) reshape 为 (batch_size, 1)。有很多方法可以做到这一点，这里是一种:

model_cnn = Sequential()
model_cnn.add(Convolution2D(filters=16, kernel_size=(3, 3), activation='relu', input_shape=(20, 20, 1)))
model_cnn.add(MaxPool2D(pool_size=18))
model_cnn.add(Flatten())
model_cnn.add(Dense(units=1))
model_cnn.compile(loss='sparse_categorical_crossentropy', optimizer='adadelta', metrics=["accuracy"])

总结:

Layer (type)                 Output Shape              Param #   
=================================================================
conv2d_1 (Conv2D)            (None, 18, 18, 16)        160       
_________________________________________________________________
max_pooling2d_1 (MaxPooling2 (None, 1, 1, 16)          0         
_________________________________________________________________
flatten_1 (Flatten)          (None, 16)                0         
_________________________________________________________________
dense_1 (Dense)              (None, 1)                 17        
=================================================================
Total params: 177
Trainable params: 177
Non-trainable params: 0

请注意，我添加了最大池化以将 18x18 特征映射减少为 1x1，然后展平图层以将张量压缩为 (无，16) 最后是密集层输出单个值。另请注意损失函数:它是 sparse_categorical_crossentropy。如果您希望进行分类交叉熵，则必须进行 one-hot 编码，并且输出的不是单个数字，而是类别上的概率分布:(无，类)。

顺便说一句，还要检查您的验证数组是否具有有效的形状。