Search Options

Results per page
Sort
Preferred Languages
Advance

Results 1 - 3 of 3 for Softplus (0.21 sec)

  1. tensorflow/compiler/mlir/tf2xla/transforms/legalize_tf.cc

      // repeated floating point additions.
      return (ty.isF16() || ty.isBF16()) ? FloatType::getF32(ty.getContext()) : ty;
    }
    
    //===----------------------------------------------------------------------===//
    // Softplus op utilities.
    //===----------------------------------------------------------------------===//
    
    static DenseElementsAttr GetEpsilonValue(Type ty) {
      auto element_ty = mlir::cast<TensorType>(ty).getElementType();
    Registered: Sun Jun 16 05:45:23 UTC 2024
    - Last Modified: Tue Jun 11 20:00:43 UTC 2024
    - 291.8K bytes
    - Viewed (0)
  2. tensorflow/compiler/mlir/tensorflow/ir/tf_generated_ops.td

      let summary = "Computes softplus gradients for a softplus operation.";
    
      let arguments = (ins
        Arg<TF_FloatTensor, [{The backpropagated gradients to the corresponding softplus operation.}]>:$gradients,
        Arg<TF_FloatTensor, [{The features passed as input to the corresponding softplus operation.}]>:$features
      );
    
      let results = (outs
    Registered: Sun Jun 16 05:45:23 UTC 2024
    - Last Modified: Tue Jun 11 23:24:08 UTC 2024
    - 793K bytes
    - Viewed (0)
  3. RELEASE.md

    *   Other:
        *   Instead of jemalloc, revert back to using system malloc since it
            simplifies build and has comparable performance.
        *   Remove integer types from `tf.nn.softplus` and `tf.nn.softsign` OpDefs.
            This is a bugfix; these ops were never meant to support integers.
        *   Allow subslicing Tensors with a single dimension.
    Registered: Sun Jun 16 05:45:23 UTC 2024
    - Last Modified: Tue Jun 11 23:24:08 UTC 2024
    - 730.3K bytes
    - Viewed (0)
Back to top