TensorFlow

Question

我正在尝试解决 Titanic Problem on Kaggle 但我不确定如何获取给定测试数据的输出。

我成功地训练了网络并调用了方法make_prediction(x, test_x)

x = tf.placeholder('float', [None, ip_features])
...
def make_prediction(x, test_data):
  with tf.Session() as sess :
    sess.run(tf.global_variables_initializer())
    prediction = sess.run(y, feed_dict={x: test_data})
    return prediction

我不确定如何在这种情况下传递 np.array test_data 以取回包含预测 0/1

的 np.array

Link to Full Code

Answer 1

我将您的 train_neural_network 和 make_prediction 函数合并为一个函数。将tf.nn.softmax应用到模型函数会使值范围从0~1（解释为概率），然后tf.argmax提取概率较高的列号。请注意，在这种情况下，y 的 placeholder 需要进行单热编码。（如果你不是在这里对 y 进行单热编码，那么 pred_y=tf.round(tf.nn.softmax(model)) 会将 softmax 的输出转换为 0 或 1）

def train_neural_network_and_make_prediction(train_X, test_X):

    model = neural_network_model(x)
    cost = tf.reduce_mean( tf.nn.softmax_cross_entropy_with_logits(model, y) )
    optimizer = tf.train.AdamOptimizer().minimize(cost)
    pred_y=tf.argmax(tf.nn.softmax(model),1)

    ephocs = 10

    with tf.Session() as sess :
        tf.initialize_all_variables().run()
        for epoch in range(ephocs):
            epoch_cost = 0

            i = 0
            while i< len(titanic_train) :
                start = i
                end = i+batch_size
                batch_x = np.array( train_x[start:end] )
                batch_y = np.array( train_y[start:end] )

                _, c = sess.run( [optimizer, cost], feed_dict={x: batch_x, y: batch_y} )
                epoch_cost += c
                i+=batch_size
            print("Epoch",epoch+1,"completed with a cost of", epoch_cost)
        # make predictions on test data
        predictions = pred_y.eval(feed_dict={x : test_X})
    return predictions

TensorFlow - 无法获得预测

TensorFlow - Unable to get Prediction

python

neural-network

kaggle