Question

我是Tensorflow的新手，请耐心等待我，我正在关注this教程并遇到一个我不知道如何解决的错误。有人可以帮我吗？提前谢谢。

这是我尝试执行的代码：

def train():
    model = Model()

    with tf.Graph().as_default():
        images, val_images, labels, val_labels = load_training_data()

        x = tf.placeholder(shape=[FLAGS.batch_size, IMAGE_SIZE, IMAGE_SIZE, 1], dtype=tf.float32, name='x')
        y = tf.placeholder(shape=[FLAGS.batch_size, NUM_LABELS], dtype=tf.float32, name='y')
        keep_prob = tf.placeholder(tf.float32, name='dropout_prob')
        global_step = tf.contrib.framework.get_or_create_global_step()

        logits = model.inference(x, keep_prob=keep_prob)
        loss = model.loss(logits=logits, labels=y)

        accuracy = model.accuracy(logits, y)
        summary_op = tf.summary.merge_all()
        train_op = model.train(loss, global_step=global_step)

        init = tf.global_variables_initializer()
        saver = tf.train.Saver()

        with tf.Session(config=tf.ConfigProto(log_device_placement=True)) as sess:
            writer = tf.summary.FileWriter(FLAGS.summary_dir, sess.graph)
            print(writer)
            sess.run(init)
            for i in range(FLAGS.num_iter):

                offset = (i * FLAGS.batch_size) % (len(images) - FLAGS.batch_size)
                batch_x, batch_y = images[offset:(offset + FLAGS.batch_size), :], labels[
                                                                                  offset:(offset + FLAGS.batch_size), :]

                _, cur_loss, summary = sess.run([train_op, 
                                                 loss, 
                                                 summary_op],
                                                feed_dict={
                                                    x: batch_x, 
                                                    y: batch_y, 
                                                    keep_prob: 0.5
                                                })

                writer.add_summary(summary, i)

                print(i, cur_loss)
                if i % 1000 == 0:
                    validation_accuracy = accuracy.eval(feed_dict={x: val_images, y: val_labels, keep_prob: 1.0})
                    print('Iter {} Accuracy: {}'.format(i, validation_accuracy))

                if i == FLAGS.num_iter - 1:
                    saver.save(sess, FLAGS.checkpoint_file_path, global_step)

这是错误日志：

TypeError                                 Traceback (most recent call last)
<ipython-input-72-8d21e7b24473> in <module>()
     49                     saver.save(sess, FLAGS.checkpoint_file_path, global_step)
     50 
---> 51 train()

<ipython-input-72-8d21e7b24473> in train()
     36                                                     x: batch_x,
     37                                                     y: batch_y,
---> 38                                                     keep_prob: 0.5
     39                                                 })
     40

我还需要补充一点，我目前正在使用Kaggle笔记本电脑，所以如果这影响了一些事情，请告诉我。

Answer 1

看起来其中一个train_op，loss或summary_op为无。

您没有提供完整的代码，所以我不能多说。检查Model班级的相应功能。

此外，如果在Notebook环境中工作，请确保在进行一些更改后执行了所有相关单元格。例如，您可以尝试从头开始执行所有单元格。

Fetch参数None具有无效类型<class'nonetype'=“”>

1 个答案: