错误是神经网络中的输出层形状，无法弄清楚维度的错误

Question

我从神经网络开始。我已经建立了一个模型，并在我的训练数据集上对其进行了训练。但是当我尝试评估模型时，我得到一个尺寸不匹配错误：ValueError: Error when checking target: expected dense_16 to have shape (3,) but got array with shape (1,)。对于我的生活，似乎无法弄清楚它在模型定义中的来源。任何帮助表示赞赏。

型号定义：

培训：

评估（错误）：

代码：

# Building a model - build a simple feedforward neural network for this problem.

# Specify all the parameters we will be using in our network
input_num_units = (32, 32, 3)
hidden_num_units = 1000
output_num_units = 3

epochs = 10
batch_size = 128

from keras.models import Sequential
from keras.layers import Dense, Flatten, InputLayer



# Define the network/model
model = Sequential([
  InputLayer(input_shape=input_num_units),
  Flatten(),
  Dense(units=hidden_num_units, activation='relu'),
  Dense(units=output_num_units, activation='softmax'),
])



model.summary()


# Compile our network and let it train for a while, with cross validation

model.compile(optimizer='sgd', loss='categorical_crossentropy', metrics=['accuracy'])
model.fit(train_x, train_y, batch_size=batch_size,epochs=epochs,verbose=1, validation_split=0.2)


score = model.evaluate(test_x, test_y, verbose=0)
print('Test loss:', score[0])
print('Test accuracy:', score[1])

Answer 1

我可能是错的，但是您是否也在您的测试数据上使用了 to_categorical，您要使用它来进行评估？

y_test = to_categorical(y_test,num_classes)