Question

我不断收到此错误：

ValueError: Error when checking target: expected dense_3 to have 2 dimensions, but got array with shape (1, 10, 1)

但是我指定density_3为1维，这是我的代码：

X_train=X_train.reshape(1,10,200,200)
y_train=y_train.reshape(1,10,1)

model = Sequential()
model.add(Convolution2D(32, 3, 3, activation='relu', input_shape=(10,200,200)))
model.add(Convolution2D(32, 3, 3, activation='relu'))
model.add(MaxPooling2D(pool_size=(2,2)))
model.add(Dropout(0.25))

model.add(Flatten())
model.add(Dense(128, activation='relu'))
model.add(Dense(64, activation='relu'))
model.add(Dropout(0.5))
model.add(Dense(1, activation='sigmoid'))

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

model.fit(X_train, y_train, 
      batch_size=3, epochs=100, verbose=1)

即使将Y数据更改为2维，它也不起作用，我得到：

ValueError: Error when checking target: expected dense_3 to have 2 dimensions, but got array with shape (1, 10, 2)

我最不了解的事情是，在另一个项目中，我做了同样的事情并且奏效了。

Answer 1

您会看到model.summary()，除了输出的形状是(?,1)。但是您的y_train形状是(1,10,1)。

因此，您可以根据需要将y_train调整为(?,1)或调整模型以匹配输入。

print(model.summary())
_________________________________________________________________
Layer (type)                 Output Shape              Param #   
=================================================================
conv2d_1 (Conv2D)            (None, 8, 198, 32)        57632     
_________________________________________________________________
conv2d_2 (Conv2D)            (None, 6, 196, 32)        9248      
_________________________________________________________________
max_pooling2d_1 (MaxPooling2 (None, 3, 98, 32)         0         
_________________________________________________________________
dropout_1 (Dropout)          (None, 3, 98, 32)         0         
_________________________________________________________________
flatten_1 (Flatten)          (None, 9408)              0         
_________________________________________________________________
dense_1 (Dense)              (None, 128)               1204352   
_________________________________________________________________
dense_2 (Dense)              (None, 64)                8256      
_________________________________________________________________
dropout_2 (Dropout)          (None, 64)                0         
_________________________________________________________________
dense_3 (Dense)              (None, 1)                 65        
=================================================================
Total params: 1,279,553
Trainable params: 1,279,553
Non-trainable params: 0
_________________________________________________________________

修改

如果除2个尺寸外，应更改Flatten()层和模型结构。因为我不知道您需要什么网络结构，所以无法为您进行更正。当然，您也可以将y_train保留为(1,10,1)。尝试遵循它。

model.add(Dense(10, activation='sigmoid'))
model.add(Reshape((10,1)))

我建议您在原始结构下修改y_train。您可以将y_train完全更改为(?,10)。

# shape=(?,10)
y_train=y_train.reshape(1,10)
# change shape
model.add(Dense(10, activation='sigmoid'))

ValueError：检查目标时出错：预期density_3具有2维。但我指定density_3为1维

1 个答案: