Question

这个keras是一个简单的keras模型，我使用relu来实现简单性和学习能力也将mean_square视为损失，但模型不适合我认为输出是数字[0-9]，我没有使用to_categorical，这就是为什么只有输出神经元

from keras.datasets import mnist
(data, labels),(x_test,y_test) = mnist.load_data()

from keras.layers import Input, Dense, Flatten
from keras.models import Model
from keras.losses import mean_squared_error

# This returns a tensor
inputs = Input(shape=(28, 28,))
x = Flatten()(inputs)

x = Dense(64, activation='relu')(x)
x = Dense(64, activation='relu')(x)
predictions = Dense(1, activation='relu')(x)

model = Model(inputs=inputs, outputs=predictions)

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

model.fit(data, labels, batch_size=10, epochs=10 ,
              validation_data=(x_test, y_test))  # starts training

如何适应这种简单的mnist分类

0 个答案: