machine-learning - TFlearn 准确率

Question

使用 TFlearn 构建 DNN 后，我想计算网络的准确性。

这是代码:

def create_model(self):
    x = tf.placeholder(dtype= tf.float32, shape=[None, 6], name='x')
    # Build neural network
    input_layer = tflearn.input_data(shape=[None, 6])
    net = input_layer
    net = tflearn.fully_connected(net, 128, activation='relu')
    net = tflearn.fully_connected(net, 64, activation='relu')
    net = tflearn.fully_connected(net, 16, activation='relu')
    net = tflearn.fully_connected(net, 2, activation='sigmoid')
    net = tflearn.regression(net, optimizer='adam', loss='mean_square', metric='R2')

    w = tf.Variable(tf.truncated_normal([2, 2], stddev=0.1))
    b = tf.Variable(tf.constant(1.0, shape=[2]))
    y = tf.nn.softmax(tf.matmul(net, w) + b, name='y')

    model = tflearn.DNN(net, tensorboard_verbose=3)
    return model

这是训练部分:

train_data, train_goal, test_data, test_goal = self.normalize_data()
        model = self.create_model()

        # train model with train sets & evaluate on test sets
        model.fit(train_data, train_goal, validation_set=0.2, n_epoch=10, show_metric=True, snapshot_epoch=True)
        result = model.evaluate(test_data, test_goal)

如何计算准确度？另外，我应该改变什么来分类？谢谢

Answer 1

你可以这样做:

def create_model(self):
    x = tf.placeholder(dtype= tf.float32, shape=[None, 6], name='x')
    # Build neural network
    input_layer = tflearn.input_data(shape=[None, 6])
    net = input_layer
    net = tflearn.fully_connected(net, 128, activation='relu')
    net = tflearn.fully_connected(net, 64, activation='relu')
    net = tflearn.fully_connected(net, 16, activation='relu')
    net = tflearn.fully_connected(net, 2, activation='sigmoid')
    net = tflearn.regression(net, optimizer='adam', loss='mean_square', metric='R2')

    w = tf.Variable(tf.truncated_normal([2, 2], stddev=0.1))
    b = tf.Variable(tf.constant(1.0, shape=[2]))
    y = tf.nn.softmax(tf.matmul(net, w) + b, name='y')

    return y

network = create_model()
net = tflearn.regression(network, optimizer='RMSprop', metric='accuracy', loss='categorical_crossentropy')

model = tflearn.DNN(net, show_metric=True, tensorboard_verbose=3)