tensorflow的contrib的基本用法和自定义模型

最新推荐文章于 2024-01-25 21:12:12 发布

忧郁一休

最新推荐文章于 2024-01-25 21:12:12 发布

阅读量8.3k

点赞数 1

分类专栏： tensorflow 文章标签： tensorflow contrib模块 optimizers estimator numpy

本文链接：https://blog.csdn.net/youyuyixiu/article/details/71252356

版权

本文介绍了TensorFlow的contrib模块，特别是contrib.learn的基本用法，并详细讲解了如何在contrib中进行自定义模型的构建，涵盖了optimizer和estimator的使用，同时结合numpy数据进行实战演示。

摘要由CSDN通过智能技术生成

tensorflow的contrib.learn的基本用法

import tensorflow as tf
# NumPy is often used to load, manipulate and preprocess data.
import numpy as np

# Declare list of features. We only have one real-valued feature. There are many
# other types of columns that are more complicated and useful.
features = [tf.contrib.layers.real_valued_column("x", dimension=1)]

# An estimator is the front end to invoke training (fitting) and evaluation
# (inference). There are many predefined types like linear regression,
# logistic regression, linear classification, logistic classification, and
# many neural network classifiers and regressors.