我遇到了ValueError：检查目标时出错：期望density_1的形状为（10，），但数组的形状为（5，）

Question

我正在从事以下工作：

• 找到了5656个属于5类的图像。
• 找到3774张图像属于1类。 但我收到此错误：

  

ValueError：检查目标时出错：预期density_1的形状为（10，），但数组的形状为（5，）。

这是我的代码：

def conv_layer(x,filters,stride=1):
  x = Conv2D(filters,kernel_size=3,padding="same",strides=stride)(x)
  x = BatchNormalization()(x)
  x = Activation("relu")(x)
  return x

​
def SimpleNet(input_size=(224,224,3),num_classes=5):

  inputs = Input(shape=input_size)

  outputs = conv_layer(inputs,16,stride=2)
  outputs = conv_layer(outputs,32)
  outputs = conv_layer(outputs,32)

  outputs = conv_layer(outputs,32,stride=2)
  outputs = conv_layer(outputs,64)
  outputs = conv_layer(outputs,64)

  outputs = conv_layer(outputs,64,stride=2)
  outputs = conv_layer(outputs,128)
  outputs = conv_layer(outputs,128)
  outputs = Dropout(0.5)(outputs)

  outputs = GlobalAvgPool2D()(outputs)
  outputs = Dense(num_classes,activation="softmax")(outputs)

  return Model(inputs=inputs,outputs=outputs).
​
model = SimpleNet()
model.compile(loss="categorical_crossentropy",optimizer=Adam(lr=0.001),metrics=["accuracy"])
model.summary()






model_path = "my-model_{epoch:03d}.h5"
​checkpoint = ModelCheckpoint(filepath=model_path, monitor="val_acc", save_best_only=True,save_weights_only=True,verbose=1)
​model.fit_generator(train_data,
                    steps_per_epoch=int(9000/BATCH_SIZE),
                    epochs=100,
                    validation_data=test_data,
                    validation_steps=int(2000/BATCH_SIZE),
                    callbacks=[checkpoint])