Tensorflow Relu误解

Question

我最近一直在做一个基于java.net.ConnectException: Connection timed out: connect 的Udacity深度学习课程。我有一个简单的TensorFlow程序，准确率约为92％：

MNIST

我的下一个作业是 from tensorflow.examples.tutorials.mnist import input_data import tensorflow as tf mnist = input_data.read_data_sets("MNIST_data/", one_hot=True) x = tf.placeholder(tf.float32, [None, 784]) W = tf.Variable(tf.zeros([784, 10])) b = tf.Variable(tf.zeros([10])) y = tf.nn.softmax(tf.matmul(x, W) + b) y_ = tf.placeholder(tf.float32, [None, 10]) cross_entropy = tf.reduce_mean(-tf.reduce_sum(y_ * tf.log(y), reduction_indices=[1])) train_step = tf.train.GradientDescentOptimizer(0.5).minimize(cross_entropy) init = tf.initialize_all_variables() sess = tf.Session() sess.run(init) for i in range(1000): batch_xs, batch_ys = mnist.train.next_batch(100) sess.run(train_step, feed_dict={x: batch_xs, y_: batch_ys}) correct_prediction = tf.equal(tf.argmax(y,1), tf.argmax(y_,1)) accuracy = tf.reduce_mean(tf.cast(correct_prediction, tf.float32)) print(sess.run(accuracy, feed_dict={x: mnist.test.images, y_: mnist.test.labels}))

我对此有心理障碍。目前我有一个784 x 10的权重矩阵和一个10元素的长偏置矢量。我不明白如何将生成的10个元素向量从Turn the logistic regression example with SGD into a 1-hidden layer neural network with rectified linear units nn.relu() and 1024 hidden nodes连接到1024 WX + Bias s。

如果有人能向我解释这一点，我将非常感激。

Answer 1

现在你有类似的东西

你需要这样的东西

（此图缺少ReLU层，后面是+ b1）