TensorFlow 入門進階
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.
TensorFlow GPU加速安裝
INSTALLATION SYSTEM REQUIREMENTS
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 詳細安裝參考:
https://www.nvidia.com/en-us/data-center/gpu-accelerated-applications/tensorflow/
2 TensorFlow 最新版官方文檔
最新版的官方文檔,相比原中文版社區文檔,還是豐富實用了很多很多,有你意想不到。
3 TensorFlow from Stanford Uni
這是最快入門 TensorFlow 的最完整的 PPT,包括最主要的幾乎所有知識點,從圖模型構建,Session創建,Constants, Variables, TensorBoard,CheckPoints, Save等等,入門最快捷。
4 TensorFlow GitHub源碼學習
這是 TensorFlow 的框架,底層是核心,往上依次提供低、中、高的三層介面,官方建議使用中、高介面,其中高層介面是預置的預測器,直接可以拿來訓練模型,評估,預測。
當然,你也可以學習自己感興趣的部分,比如底層介面,這樣,可以定製自己的功能,實現擴展底層介面。
https://github.com/tensorflow/tensorflow
5 基於 TensorFlow 的模型實例
tensorflow/models
這個項目是基於 TensorFlow 的各種模型實例,是非常好的快速提升應用 TF 解決實際問題能力的最好方法之一。
關於演算法channel
TAG:演算法channel |