简体繁体 English

使用 TENSORFLOW2 的 Kmeans 聚类

[英]Kmeans clustering using TENSORFLOW2

原文 2019-07-18 13:09:38 3 1 python/ tensorflow/ tensorflow2.0/ spherical-kmeans

How could I convert a pandas database that contains 47 columns and 99999 lines into a tensors in Tensorflow 2?如何将包含 47 列和 99999 行的 Pandas 数据库转换为 Tensorflow 2 中的张量？ is the Kmeans algorithm already implemented under TF 2? Kmeans 算法是否已经在 TF 2 下实现了？ because the command tf.contrib.factorization.KMeans does not work under TF2 since tf.contrib no longer exists on the second API Tensorflow因为命令tf.contrib.factorization.KMeans在 TF2 下不起作用，因为tf.contrib在第二个 API Tensorflow 上不再存在

List item项目清单

1 个解决方案

I got my TF2 example working with KMeans implementation from here tf.compat.v1.estimator.experimental.KMeans我从这里tf.compat.v1.estimator.experimental.KMeans得到了使用 KMeans 实现的 TF2 示例

Note: As of Nov 7, 2019 the code example has a problem.注意：截至 2019 年 11 月 7 日，代码示例存在问题。 Change tf.estimator.experimental.KMeans to tf.compat.v1.estimator.experimental.KMeans更改tf.estimator.experimental.KMeans到tf.compat.v1.estimator.experimental.KMeans

Also for anyone looking for TF 2 contrib, there's a quote on the r1.15 tf.contrib page:对于任何寻找 TF 2 contrib 的人，在 r1.15 tf.contrib页面上有一段引用：

Warning: The tf.contrib module will not be included in TensorFlow 2.0.警告： TensorFlow 2.0 中将不包含 tf.contrib 模块。 Many of its submodules have been integrated into TensorFlow core, or spun-off into other projects like tensorflow_io, or tensorflow_addons.它的许多子模块已集成到 TensorFlow 核心中，或分拆到其他项目中，如 tensorflow_io 或 tensorflow_addons。 For instructions on how to upgrade see the Migration guide.有关如何升级的说明，请参阅迁移指南。