手动将 tf.contrib.slim 升级到 tf 2.0

问题描述

我的 Python 代码使用了 tf.contrib.slim 功能，并且在升级到 tensorflow 到 2.0 后不再起作用.

I have a problem with my python code that uses tf.contrib.slim functionalities and no longer works after upgrading to tensorflow to 2.0.

如何将以下内容升级到 tf 2.0:

How can I upgrade the following to tf 2.0:

import tensorflow.contrib.slim as slim
import tensorflow.contrib.slim.nets

# ...

net = slim.conv2d(
    inp,
    dim,
    [3, 3],
    rate=1,
    normalizer_fn=slim.layer_norm,
    activation_fn=lrelu,
    scope='g_' + str(width) + '_conv1')

谢谢.

推荐答案

您可以使用 tf_slim 包代替 (https://github.com/google-research/tf-slim)

You can use tf_slim package instead (https://github.com/google-research/tf-slim)

但是，将包更新到 TF2 的推送请求仍然未决.所以你应该从分支安装pip install git+https://github.com/adrianc-a/tf-slim.git@remove_contrib

However, the push request updating the package to TF2 is still pending. So you should install from the branchpip install git+https://github.com/adrianc-a/tf-slim.git@remove_contrib

这篇关于手动将 tf.contrib.slim 升级到 tf 2.0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！