我刚开始学习机器学习和TensorFlow。我尝试训练一个简单的模型来识别性别。我使用了身高、体重和鞋码的小数据集。然而，我在评估模型准确性时遇到了问题。以下是完整的代码：
import tflearnimport tensorflow as tfimport numpy as np# [height, weight, shoe_size]X = [[181, 80, 44], [177, 70, 43], [160, 60, 38], [154, 54, 37], [166, 65, 40], [190, 90, 47], [175, 64, 39], [177, 70, 40], [159, 55, 37], [171, 75, 42], [181, 85, 43], [170, 52, 39]]# 0 - for female, 1 - for maleY = [1, 1, 0, 0, 1, 1, 0, 0, 0, 1, 1, 0]data = np.column_stack((X, Y))np.random.shuffle(data)# Split into train and test setX_train, Y_train = data[:8, :3], data[:8, 3:]X_test, Y_test = data[8:, :3], data[8:, 3:]# Build neural networknet = tflearn.input_data(shape=[None, 3])net = tflearn.fully_connected(net, 32)net = tflearn.fully_connected(net, 32)net = tflearn.fully_connected(net, 1, activation='linear')net = tflearn.regression(net, loss='mean_square')# fix for tflearn with TensorFlow 12:col = tf.get_collection(tf.GraphKeys.TRAINABLE_VARIABLES)for x in col: tf.add_to_collection(tf.GraphKeys.VARIABLES, x)# Define modelmodel = tflearn.DNN(net)# Start training (apply gradient descent algorithm)model.fit(X_train, Y_train, n_epoch=100, show_metric=True)score = model.evaluate(X_test, Y_test)print('Training test score', score)test_male = [176, 78, 42]test_female = [170, 52, 38]print('Test male: ', model.predict([test_male])[0])print('Test female:', model.predict([test_female])[0])尽管模型的预测并不是很准确
Test male: [0.7158362865447998]Test female: [0.4076206684112549]model.evaluate(X_test, Y_test)总是返回1.0。如何使用TFLearn计算测试数据集上的真实准确率？
回答：
在这种情况下，你想要进行二元分类。你的网络被设置为执行线性回归。
首先，将标签（性别）转换为分类特征：
from tflearn.data_utils import to_categoricalY_train = to_categorical(Y_train, nb_classes=2)Y_test = to_categorical(Y_test, nb_classes=2)你的网络的输出层需要两个输出单元来预测你想要的两个类别。此外，激活函数需要是softmax以进行分类。tf.learn的默认损失是交叉熵，默认度量是准确率，因此这是正确的设置。
# Build neural networknet = tflearn.input_data(shape=[None, 3])net = tflearn.fully_connected(net, 32)net = tflearn.fully_connected(net, 32)net = tflearn.fully_connected(net, 2, activation='softmax')net = tflearn.regression(net)输出现在将是一个包含每个性别概率的向量。例如：
[0.991, 0.009] #female请注意，使用你这么小的数据集，网络会严重过拟合。这意味着在训练过程中准确率会接近1，而在测试集上的准确率会相当差。
