Geek Answers Handbook

Tensor error: minimum tensor rank: 1, but received: 1

I get the following error trying to evaluate my model.

tensorflow.python.framework.errors.InvalidArgumentError: Minimum tensor rank: 1 but got: 1 [[Node: ArgMax_1 = ArgMax[T=DT_INT64, _device="/job:localhost/replica:0/task:0/cpu:0"](_recv_Placeholder_1_0, ArgMax_1/dimension/_40)]]

Here is the relevant code

        # Predictions for the current training minibatch.
        train_prediction = tf.nn.softmax(logits)
        correct_prediction = tf.equal(tf.argmax(train_prediction, 1), tf.argmax(train_labels, 1))
        accuracy = tf.reduce_mean(tf.cast(correct_prediction, tf.float32))

        sess.run(tf.initialize_all_variables())
        for i in range(1000000):
            start_time = time()

            images, labels = get_batch(fifo_queue, FLAGS.batch_size)

            feed_dict = {
                train_images: images,
                train_labels: labels
            }

            _, loss_value, learn_rate, predictions = sess.run(
                [train_step, cross_entropy, learning_rate, train_prediction],
                feed_dict=feed_dict)

            duration = time() - start_time
              if i % 1 == 0:
                # Print status to stdout.
                 print('Step %d: loss = %.3f (%.3f sec)' % (i, loss_value, duration))

                 train_accuracy = accuracy.eval(feed_dict={
                     train_images: images, train_labels: labels, keep_prob: 1.0})
                 print("step %d, training accuracy %g"%(i, train_accuracy))
                 train_step.run(feed_dict={train_images: images[0], train_labels: labels[1], keep_prob: 0.5})

`

I have not been able to try a lot yet, because I just get my first assessment model, and this error (indicating expectations 1 and 1) is not very useful.

+4
source share
1 answer

The error message is not very large, but looking at the code may explain what is happening.

The problem arises from what train_labelsis (presumably) a one-dimensional vector. Dimensions are numbered from 0, so the vector has only a 0-dimensional dimension, but your call is tf.argmax(train_labels, 1)trying to take argmax in the first dimension, which does not exist.

argmax . :

correct_prediction = tf.equal(tf.argmax(train_prediction, 1), train_labels)
+8

More articles:


All Articles