Donate to e Foundation | Murena handsets with /e/OS | Own a part of Murena! Learn more

Commit 0a9895d9 authored by Lev Proleev's avatar Lev Proleev Committed by Slava Shklyaev
Browse files

Fix docs: clarify usage of float16 scalars in operations 

Update the docs for ops:
- LOG_SOFTMAX
- LOCAL_RESPONSE_NORMALIZATION

The docs mentioned possibility to use float16 as an input type but
didn't specify that other inputs must be float16 as well in that case.

Fix: 123500722
Test: mma
Change-Id: I9028c4a109c80f0b8571fab45555818e9e4bc783
Merged-In: I9028c4a109c80f0b8571fab45555818e9e4bc783
(cherry picked from commit 6d13ba25)
parent 16a5cb19

current.txt

+1 −1
Original line number Diff line number Diff line
@@ -451,7 +451,7 @@ b83317b66721241887d2770b5ae95fd5af1e77c5daa7530ecb08fae8892f2b43 android.hardwar 
92714960d1a53fc2ec557302b41c7cc93d2636d8364a44bd0f85be0c92927ff8 android.hardware.neuralnetworks@1.2::IExecutionCallback

36e1064c869965dee533c537cefbe87e54db8bd8cd45be7e0e93e00e8a43863a android.hardware.neuralnetworks@1.2::IPreparedModel

e1c734d1545e1a4ae749ff1dd9704a8e594c59aea7c8363159dc258e93e0df3b android.hardware.neuralnetworks@1.2::IPreparedModelCallback

b47700929d91ad9c037fd26077d4008d4a04753f71f4f332aeedbd1de7bb91e1 android.hardware.neuralnetworks@1.2::types

73e995644b1bb2678ec3ab850feb7a1b4495501953951c22316cefd67b900b3e android.hardware.neuralnetworks@1.2::types

cf7a4ba516a638f9b82a249c91fb603042c2d9ca43fd5aad9cf6c0401ed2a5d7 android.hardware.nfc@1.2::INfc

abf98c2ae08bf765db54edc8068e36d52eb558cff6706b6fd7c18c65a1f3fc18 android.hardware.nfc@1.2::types

4cb252dc6372a874aef666b92a6e9529915aa187521a700f0789065c3c702ead android.hardware.power.stats@1.0::IPowerStats

neuralnetworks/1.2/types.hal

+21 −8
Original line number Diff line number Diff line
@@ -1005,12 +1005,21 @@ enum OperationType : int32_t { 
     *      the input.

     * * 1: An {@link OperandType::INT32} scalar, specifying the radius of

     *      the normalization window.

     * * 2: An {@link OperandType::FLOAT32} scalar, specifying the bias, must

     *      not be zero.

     * * 3: An {@link OperandType::FLOAT32} scalar, specifying the scale

     *      factor, alpha.

     * * 4: An {@link OperandType::FLOAT32} scalar, specifying the exponent,

     *      beta.

     * * 2: A scalar, specifying the bias, must not be zero.

     *      For input tensor of {@link OperandType::TENSOR_FLOAT16}, the bias

     *      value must be of {@link OperandType::FLOAT16}.

     *      For input tensor of {@link OperandType::TENSOR_FLOAT32}, the bias

     *      value must be of {@link OperandType::FLOAT32}.

     * * 3: A scalar, specifying the scale factor, alpha.

     *      For input tensor of {@link OperandType::TENSOR_FLOAT16}, the alpha

     *      value must be of {@link OperandType::FLOAT16}.

     *      For input tensor of {@link OperandType::TENSOR_FLOAT32}, the alpha

     *      value must be of {@link OperandType::FLOAT32}.

     * * 4: A scalar, specifying the exponent, beta.

     *      For input tensor of {@link OperandType::TENSOR_FLOAT16}, the beta

     *      value must be of {@link OperandType::FLOAT16}.

     *      For input tensor of {@link OperandType::TENSOR_FLOAT32}, the beta

     *      value must be of {@link OperandType::FLOAT32}.

     * * 5: An optional {@link OperandType::INT32} scalar, default to -1,

     *      specifying the dimension normalization would be performed on.

     *      Negative index is used to specify axis from the end (e.g. -1 for
@@ -3495,8 +3504,12 @@ enum OperationType : int32_t { 
     *

     * Inputs:

     * * 0: A tensor specifying the input logits.

     * * 1: An {@link OperandType::FLOAT32} scalar, specifying the positive

     *      scaling factor for the exponent, beta.

     * * 1: A scalar, specifying the positive scaling factor for the exponent,

     *      beta.

     *      For input tensor of {@link OperandType::TENSOR_FLOAT16}, the beta

     *      value must be of {@link OperandType::FLOAT16}.

     *      For input tensor of {@link OperandType::TENSOR_FLOAT32}, the beta

     *      value must be of {@link OperandType::FLOAT32}.

     * * 2: An {@link OperandType::INT32} scalar specifying the axis to

     *      reduce across. Negative index is used to specify axis from the

     *      end (e.g. -1 for the last axis). Must be in the range [-n, n).