TensorFlow 索引无效(越界) [英] TensorFlow Indices are not valid (out of bounds)

问题描述

我目前正在尝试使用自己的图像数据运行 TensorFlow.但是当我尝试运行这些函数时它崩溃了:它来自 mnist.py

Hi i'am currently trying to run TensorFlow with own image data. But it crashes when i'am trying to run these function: its from mnist.py

def loss_fn(logits, labels):
    batch_size = tf.size(labels)
    labels = tf.expand_dims(labels, 1)
    indices = tf.expand_dims(tf.range(0, batch_size, 1), 1)
    concated = tf.concat(1, [indices, labels])
    onehot_labels = tf.sparse_to_dense(
             concated, tf.pack([batch_size, NUM_CLASSES]), 1.0, 0.0)
    cross_entropy = tf.nn.softmax_cross_entropy_with_logits(logits,
                     onehot_labels,name='xentropy')
    loss = tf.reduce_mean(cross_entropy, name='xentropy_mean')
    return loss

出现此错误:

Compute status: Invalid argument: Indices are not valid (out of bounds).  Shape: dim { size: 100 } dim { size: 447 }

数字 100 是我的批次大小，447 是我的类数.

the number 100 is my batch_size and 447 is my number of classes.

我也尝试像这里一样解决这个问题https://github.com/tensorflow/tensorflow/issues/194将 indeces 行更改为此行:

i also try to solve that issue like here https://github.com/tensorflow/tensorflow/issues/194 changing the indeces line into this line:

indices = tf.expand_dims(tf.range(0, batch_size, 1), 1)

没有解决我的问题.有人有想法吗?

didn't solve my problem. Does anybody have an idea?

推荐答案

我也遇到了这个错误.我意识到了我的错误.如果您有 10 个类，则您的标签值应介于 0-9 之间，包括 0-9.该错误在 TensorFlow CIFAR10 示例中重现，与 SVHN 数据集一起使用.请参阅下面的问答.

I had this error as well. And I realized my mistake. If you have 10 classes, your label values should range between 0-9, inclusive. The error was reproduced on the TensorFlow CIFAR10 example, used with SVHN dataset. Refer to question and answer below.

TensorFlow CIFAR10 示例

这篇关于TensorFlow 索引无效(越界)的文章就介绍到这了，希望我们推荐的答案对大家有所帮助，也希望大家多多支持IT屋！