Python ValueError:检查目标时出错：预期激活_6具有形状（70），但获得具有形状（71）的数组

我正在使用CNN创建人脸识别。我在学习一个教程。我使用的是Tensorflow==1.15

该程序将拍摄70张用户的面部照片，并将其保存在“数据集”文件夹中

我不断得到错误：

ValueError:检查目标时出错：预期激活_6具有形状（70），但获得具有形状（71）的数组

输入形状-（32,32,1）

班级（n_班级）-70

输出

Model: "sequential_1"
_________________________________________________________________
Layer (type)                 Output Shape              Param #   
=================================================================
conv2d_1 (Conv2D)            (None, 30, 30, 32)        320       
_________________________________________________________________
activation_1 (Activation)    (None, 30, 30, 32)        0         
_________________________________________________________________
conv2d_2 (Conv2D)            (None, 28, 28, 64)        18496     
_________________________________________________________________
batch_normalization_1 (Batch (None, 28, 28, 64)        256       
_________________________________________________________________
activation_2 (Activation)    (None, 28, 28, 64)        0         
_________________________________________________________________
conv2d_3 (Conv2D)            (None, 28, 28, 64)        4160      
_________________________________________________________________
dropout_1 (Dropout)          (None, 28, 28, 64)        0         
_________________________________________________________________
batch_normalization_2 (Batch (None, 28, 28, 64)        256       
_________________________________________________________________
activation_3 (Activation)    (None, 28, 28, 64)        0         
_________________________________________________________________
conv2d_4 (Conv2D)            (None, 26, 26, 128)       73856     
_________________________________________________________________
dropout_2 (Dropout)          (None, 26, 26, 128)       0         
_________________________________________________________________
activation_4 (Activation)    (None, 26, 26, 128)       0         
_________________________________________________________________
max_pooling2d_1 (MaxPooling2 (None, 13, 13, 128)       0         
_________________________________________________________________
conv2d_5 (Conv2D)            (None, 13, 13, 64)        8256      
_________________________________________________________________
activation_5 (Activation)    (None, 13, 13, 64)        0         
_________________________________________________________________
flatten_1 (Flatten)          (None, 10816)             0         
_________________________________________________________________
dense_1 (Dense)              (None, 32)                346144    
_________________________________________________________________
dense_2 (Dense)              (None, 70)                2310      
_________________________________________________________________
activation_6 (Activation)    (None, 70)                0         
=================================================================
Total params: 454,054
Trainable params: 453,798
Non-trainable params: 256
_________________________________________________________________
Shape of Data: (70, 32, 32, 1)
Number of unique faces : 70

我正在计算x_列，x_测试，y_列，y_测试，如下所示

x_train, x_test, y_train, y_test = train_test_split(faces,ids, test_size = 0.2, random_state = 0)

输出

Model: "sequential_1"
_________________________________________________________________
Layer (type)                 Output Shape              Param #   
=================================================================
conv2d_1 (Conv2D)            (None, 30, 30, 32)        320       
_________________________________________________________________
activation_1 (Activation)    (None, 30, 30, 32)        0         
_________________________________________________________________
conv2d_2 (Conv2D)            (None, 28, 28, 64)        18496     
_________________________________________________________________
batch_normalization_1 (Batch (None, 28, 28, 64)        256       
_________________________________________________________________
activation_2 (Activation)    (None, 28, 28, 64)        0         
_________________________________________________________________
conv2d_3 (Conv2D)            (None, 28, 28, 64)        4160      
_________________________________________________________________
dropout_1 (Dropout)          (None, 28, 28, 64)        0         
_________________________________________________________________
batch_normalization_2 (Batch (None, 28, 28, 64)        256       
_________________________________________________________________
activation_3 (Activation)    (None, 28, 28, 64)        0         
_________________________________________________________________
conv2d_4 (Conv2D)            (None, 26, 26, 128)       73856     
_________________________________________________________________
dropout_2 (Dropout)          (None, 26, 26, 128)       0         
_________________________________________________________________
activation_4 (Activation)    (None, 26, 26, 128)       0         
_________________________________________________________________
max_pooling2d_1 (MaxPooling2 (None, 13, 13, 128)       0         
_________________________________________________________________
conv2d_5 (Conv2D)            (None, 13, 13, 64)        8256      
_________________________________________________________________
activation_5 (Activation)    (None, 13, 13, 64)        0         
_________________________________________________________________
flatten_1 (Flatten)          (None, 10816)             0         
_________________________________________________________________
dense_1 (Dense)              (None, 32)                346144    
_________________________________________________________________
dense_2 (Dense)              (None, 70)                2310      
_________________________________________________________________
activation_6 (Activation)    (None, 70)                0         
=================================================================
Total params: 454,054
Trainable params: 453,798
Non-trainable params: 256
_________________________________________________________________
Shape of Data: (70, 32, 32, 1)
Number of unique faces : 70

x_列车-（56,32,32,1）

y_列车-（56、71）

x_测试-（14,32,32,1）

y_试验-（14,71）

CNN层的尺寸有什么问题？ 请帮助

在您的model.summary（）输出中，您可以看到最终的致密层具有形状（无，70）。None代表当前未知的批次大小。70然后是每个图像的输出维度

从您的y_train和y_pred中，似乎您想要输出71个类，而不是70个，因此维度不匹配。您可以尝试将最后一个密集层更改为

model.add(Dense(num_classes+1))

这应该行得通。我不知道为什么y值的长度与类数不同。一个原因可能是，有一个类表示“nothing”，因此在其他类中不应选择的类是正确的。这可以解释为什么如果有70个类，就需要71维的输出

model.add(Dense(num_classes+1))