Search Options

Results per page
Sort
Preferred Languages
Advance

Results 1 - 1 of 1 for hard_sigmoid (0.05 sec)

  2. github.com/tensorflow/tensorflow

    RELEASE.md 

    *   Add `UnifiedGRU` as the new GRU implementation for tf2.0. Change the default
    recurrent activation function for GRU from `hard_sigmoid` to `sigmoid`, and
    `reset_after` to True in 2.0. Historically recurrent activation is
    `hard_sigmoid` since it is fast than 'sigmoid'. With new unified backend
    between CPU and GPU mode, since the CuDNN kernel is using sigmoid, we change
    Registered: Tue Dec 30 12:39:10 UTC 2025
    - Last Modified: Tue Oct 28 22:27:41 UTC 2025
    - 740.4K bytes
    - Viewed (3)
Back to top