TensorFlow is a software library for designing and deploying numerical computations, with a key focus on applications in machine learning. The library allows algorithms to be described as a graph of connected operations that can be executed on various GPU-enabled platforms ranging from portable devices to desktops to high-end servers.
TensorFlow runs up to 50% faster on the latest Pascal GPUs and scales well across GPUs. Now you can train the models in hours instead of days.
The GPU-enabled version of TensorFlow has the following requirements:
64-bit Linux
Python 2.7
CUDA 7.5 (CUDA 8.0 required for Pascal GPUs)
cuDNN v5.1 (cuDNN v6 if on TF v1.3)
附 详细安装参考:
https://www.nvidia.com/en-us/data-center/gpu-accelerated-applications/tensorflow/
最新版的官方文档,相比原中文版社区文档,还是丰富实用了很多很多,有你意想不到。
www.tensorflow.org/
这是最快入门 TensorFlow 的最完整的 PPT,包括最主要的几乎所有知识点,从图模型构建,Session创建,Constants, Variables, TensorBoard,CheckPoints, Save等等,入门最快捷。
直接在 算法channel 后台回复 dl 下载完整的TensorFlow 入门PPT
这是 TensorFlow 的框架,底层是核心,往上依次提供低、中、高的三层接口,官方建议使用中、高接口,其中高层接口是预置的预测器,直接可以拿来训练模型,评估,预测。
当然,你也可以学习自己感兴趣的部分,比如底层接口,这样,可以定制自己的功能,实现扩展底层接口。
https://github.com/tensorflow/tensorflow
tensorflow/models
这个项目是基于 TensorFlow 的各种模型实例,是非常好的快速提升应用 TF 解决实际问题能力的最好方法之一。