python import tensorflow as tf import numpy as np python learning_rate = 0.001 batch_size = 128 num_iterations = 10000 python train_data = np.loadtxt('train_data.txt') train_labels = np.loadtxt('train_labels.txt') python def neural_network(x): hidden_layer = tf.layers.dense(x, 256, activation=tf.nn.relu) output_layer = tf.layers.dense(hidden_layer, 1, activation=tf.nn.sigmoid) return output_layer python x = tf.placeholder(tf.float32, [None, 2]) y = tf.placeholder(tf.float32, [None, 1]) model_output = neural_network(x) loss = tf.reduce_mean(tf.nn.sigmoid_cross_entropy_with_logits(logits=model_output, labels=y)) optimizer = tf.train.AdamOptimizer(learning_rate).minimize(loss) python with tf.Session() as sess: sess.run(tf.global_variables_initializer()) for iteration in range(num_iterations): idx = np.random.randint(len(train_data), size=batch_size) batch_x = train_data[idx] batch_y = train_labels[idx] _, current_loss = sess.run([optimizer, loss], feed_dict={x: batch_x, y: batch_y}) if iteration % 1000 == 0: print("Iteration {}: Loss = {}".format(iteration, current_loss))