TensorFlow 1.6.0-rc0 发布，bug 修复和其他改进

TensorFlow 1.6.0-rc0 发布了，TensorFlow 是谷歌的第二代机器学习系统，按照谷歌所说，在某些基准测试中，TensorFlow 的表现比第一代的 DistBelief 快了 2 倍。

突破性变化：

• Prebuilt binaries are now built against CUDA 9.0 and cuDNN 7.
• Prebuilt binaries will use AVX instructions. This may break TF on older CPUs.

主要的特性和改进：

• tf.estimator.{FinalExporter,LatestExporter} now export stripped SavedModels. This improves forward compatibility of the SavedModel.
• FFT support added to XLA CPU/GPU.

Bug 修复：

• Documentation updates:
  • Added a second version of Getting Started, which is aimed at ML
    newcomers.
  • Clarified documentation on resize_images.align_corners parameter.
  • Additional documentation for TPUs.
• Google Cloud Storage (GCS):
  • Add client-side throttle.
  • Add a FlushCaches() method to the FileSystem interface, with an implementation for GcsFileSystem.

完整更新内容请查看发布主页。

下载地址：

•  Source code (zip)
•  Source code (tar.gz)

转自 http://www.oschina.net/news/93155/tensorflow-1-6-0-rc0-released