Tensorflow.strided_slice 缺少参数“步幅"? [英] Tensorflow.strided_slice missing argument 'strides'?

问题描述

我正在尝试根据教程运行 cifar10_train.py，但我得到了

I am trying to run cifar10_train.py according to tutorials, but I got

"cifar10_input.py", line 87, in read_cifar10
tf.strided_slice(record_bytes, [0], [label_bytes]), tf.int32)
TypeError: strided_slice() missing 1 required positional argument: 'strides'

文档说strides是可选的，之前在Ubuntu上也能正常工作.

The document says that strides is optional, and it did work properly on Ubuntu before.

我的 tensorflow 版本是 0.12.0rc1-cp35-cp35m-win_amd64.我已经安装了最新版本.

My tensorflow version is 0.12.0rc1-cp35-cp35m-win_amd64. I have already installed the newest release.

我可以通过这个论点吗?我不知道它...

May I have to pass this argument? I have no idea about it...

更新:我用 slice 替换了 strided_slice，它有效.根据问题#754，strides 在 1.0 版本中将是可选的.(也许?)

UPDATE: I replaced strided_slice with slice, and it works. According to issue#754, strides will be optional at 1.0 release. (maybe?)

推荐答案

替换一行

tf.strided_slice(record_bytes, [0], [label_bytes]), tf.int32)

到线:

tf.strided_slice(record_bytes, [0], [label_bytes], [1]), tf.int32)

和下一个运算符中的一行

and a line in the next operator

[label_bytes + image_bytes]),

到线

[label_bytes + image_bytes], [1]),

它对我有用.

这篇关于Tensorflow.strided_slice 缺少参数“步幅"?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！