推荐两个免费学习Tensorflow的网站

1. 该网站的教程从入门到深入，也会有代码片段

http://c.biancheng.net/view/1914.html

在教程的第十九章TensorFlow逻辑回归处理MNIST数据集，是用test数据计算了accuracy，但是教程里面的代码缺失一部分，偶在这儿给大家补全啦。

with tf.Session() as sess:
    sess.run(init)
    summary_writer = tf.summary.FileWriter('graphs', sess.graph)
    max_epochs = 100
    batch_size = 550
    for epoch in range(max_epochs):
        loss_avg = 0
        num_of_batch = int(mnist.train.num_examples/batch_size)
        for i in range(num_of_batch):
            batch_xs, batch_ys = mnist.train.next_batch(batch_size)
            _, l , summary_str = sess.run([optimizer, loss, merged_summary_op], feed_dict={x: batch_xs, y:batch_ys})
            loss_avg += l
            summary_writer.add_summary(summary_str, epoch*num_of_batch +i)
        loss_avg = loss_avg/num_of_batch
        print('epoch{0}:loss{1}'.format(epoch, loss_avg))
        y_v = sess.run(y_hat, feed_dict={x:mnist.test.images})
        correct_pre = tf.equal(tf.arg_max(y_v,1), tf.arg_max(mnist.test.labels,1))
        accuracy = tf.reduce_mean(tf.cast(correct_pre, tf.float32))
        print(sess.run(accuracy, feed_dict={x: mnist.test.images, y:mnist.test.labels}))
    summary_writer.close()
    print('done')

2. 这个是tensorflow官方文档的翻译

https://www.w3cschool.cn/tensorflow_python/