Eager
Eager execution
动态图的执行
Eager execution is a feature that makes TensorFlow execute operations immediately: concrete values are returned, instead of creating a computational graph that is executed later:
动态图特性使Tensorflow可以立刻执行运算:并返回具体值,替换(之前)建立计算图(它)过一会才执行。
A user guide is available: https://www.tensorflow.org/programmers_guide/eager (source file)
使用指南:https://www.tensorflow.org/programmers_guide/eager (source file)
We welcome feedback through GitHub issues.
欢迎通过反馈:GitHub issues.
Sample code is available, including benchmarks for some:
可用的实例,包含如下实例:
- Linear Regression 线性回归
- MNIST handwritten digit classifier 基于MINIST数据集的手写数字分类
- ResNet50 image classification 使用ResNet50网络分类图像
- RNN to generate colors 使用RNN(循环神经网络)生成演示
- RNN language model RNN(循环神经网络)语言模型
扫描二维码关注公众号,回复:
1642498 查看本文章
完整项目下载
方便没积分童鞋,请加企鹅452205574,共享文件夹。
包括:代码、数据集合(图片)、已生成model、安装库文件等。