Evolution-x/hardware_interfaces
1
0
Fork 0
mirror of https://github.com/Evolution-X/hardware_interfaces synced 2026-02-01 15:58:43 +00:00
Code Issues Packages Projects Releases Wiki Activity

Merge "Fix docs: clarify usage of float16 scalars in operations" into qt-dev

Browse Source
This commit is contained in:
Slava Shklyaev
2019-04-23 14:26:21 +00:00
committed by Android (Google) Code Review
parent f22bc9099e 6d13ba258b
commit 34e718703d
2 changed files with 22 additions and 9 deletions
Download Patch File Download Diff File Expand all files Collapse all files

2
current.txt
View File

@@ -515,7 +515,7 @@ b83317b66721241887d2770b5ae95fd5af1e77c5daa7530ecb08fae8892f2b43 android.hardwar
92714960d1a53fc2ec557302b41c7cc93d2636d8364a44bd0f85be0c92927ff8 android.hardware.neuralnetworks@1.2::IExecutionCallback 92714960d1a53fc2ec557302b41c7cc93d2636d8364a44bd0f85be0c92927ff8 android.hardware.neuralnetworks@1.2::IExecutionCallback
36e1064c869965dee533c537cefbe87e54db8bd8cd45be7e0e93e00e8a43863a android.hardware.neuralnetworks@1.2::IPreparedModel 36e1064c869965dee533c537cefbe87e54db8bd8cd45be7e0e93e00e8a43863a android.hardware.neuralnetworks@1.2::IPreparedModel
e1c734d1545e1a4ae749ff1dd9704a8e594c59aea7c8363159dc258e93e0df3b android.hardware.neuralnetworks@1.2::IPreparedModelCallback 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 cf7a4ba516a638f9b82a249c91fb603042c2d9ca43fd5aad9cf6c0401ed2a5d7 android.hardware.nfc@1.2::INfc
abf98c2ae08bf765db54edc8068e36d52eb558cff6706b6fd7c18c65a1f3fc18 android.hardware.nfc@1.2::types abf98c2ae08bf765db54edc8068e36d52eb558cff6706b6fd7c18c65a1f3fc18 android.hardware.nfc@1.2::types
4cb252dc6372a874aef666b92a6e9529915aa187521a700f0789065c3c702ead android.hardware.power.stats@1.0::IPowerStats 4cb252dc6372a874aef666b92a6e9529915aa187521a700f0789065c3c702ead android.hardware.power.stats@1.0::IPowerStats

29
neuralnetworks/1.2/types.hal
View File

@@ -1005,12 +1005,21 @@ enum OperationType : int32_t {
* the input. * the input.
* * 1: An {@link OperandType::INT32} scalar, specifying the radius of * * 1: An {@link OperandType::INT32} scalar, specifying the radius of
* the normalization window. * the normalization window.
* * 2: An {@link OperandType::FLOAT32} scalar, specifying the bias, must * * 2: A scalar, specifying the bias, must not be zero.
* not be zero. * For input tensor of {@link OperandType::TENSOR_FLOAT16}, the bias
* * 3: An {@link OperandType::FLOAT32} scalar, specifying the scale * value must be of {@link OperandType::FLOAT16}.
* factor, alpha. * For input tensor of {@link OperandType::TENSOR_FLOAT32}, the bias
* * 4: An {@link OperandType::FLOAT32} scalar, specifying the exponent, * value must be of {@link OperandType::FLOAT32}.
* beta. * * 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, * * 5: An optional {@link OperandType::INT32} scalar, default to -1,
* specifying the dimension normalization would be performed on. * specifying the dimension normalization would be performed on.
* Negative index is used to specify axis from the end (e.g. -1 for * Negative index is used to specify axis from the end (e.g. -1 for
@@ -3495,8 +3504,12 @@ enum OperationType : int32_t {
* *
* Inputs: * Inputs:
* * 0: A tensor specifying the input logits. * * 0: A tensor specifying the input logits.
* * 1: An {@link OperandType::FLOAT32} scalar, specifying the positive * * 1: A scalar, specifying the positive scaling factor for the exponent,
* scaling factor for the exponent, beta. * 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 * * 2: An {@link OperandType::INT32} scalar specifying the axis to
* reduce across. Negative index is used to specify axis from the * 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). * end (e.g. -1 for the last axis). Must be in the range [-n, n).