我有一个用Keras(Theano后端)在Python中编写的简单NN模型,用于检测手写数字的28x28像素图像:
model0 = Sequential()
#number of epochs to train for
nb_epoch = 12
#amount of data each iteration in an epoch sees
batch_size = 128
model0.add(Flatten(input_shape=(1, img_rows, img_cols)))
model0.add(Dense(nb_classes))
model0.add(Activation('softmax'))
model0.compile(loss='categorical_crossentropy',
optimizer='sgd',
metrics=['accuracy'])
model0.fit(X_train, Y_train, batch_size=batch_size, nb_epoch=nb_epoch,
verbose=1, validation_data=(X_test, Y_test))
score = model0.evaluate(X_test, Y_test, verbose=0)
print('Test score:', score[0])
print('Test accuracy:', score[1])
这个工作很顺利,我获得了大约90%的准确率。然后我执行以下命令来获取我的网络结构的摘要信息,即 print(model0.summary())
。这将输出以下内容:
Layer (type) Output Shape Param # Connected to
=====================================================================
flatten_1 (Flatten) (None, 784) 0 flatten_input_1[0][0]
dense_1 (Dense) (None, 10) 7850 flatten_1[0][0]
activation_1 (None, 10) 0 dense_1[0][0]
======================================================================
Total params: 7850
我不明白他们是如何得出7850个总参数的,以及这实际上意味着什么?
nb_classes
应该是10(这是一个有10个类别的多类问题)。虽然在 OP 中没有提到,但在回答此问题的其他地方中多次提到。 - edesz