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

Commit e4c8f5fe authored by Lev Proleev's avatar Lev Proleev Committed by Viet Dang
Browse files

Fix quantized LSTM doc 

The CL changes explicit prefixes for types in types.spec to a macro, so
that the prefixes of tensor types are correct both in NDK and HAL docs.

Bug: 144841609
Test: mma
Change-Id: I6d904bd3a858f555beed9270f141f080f96e429a
Merged-In: I6d904bd3a858f555beed9270f141f080f96e429a
(cherry picked from commit da5079c5)
parent 1fd6b723

current.txt

+1 −1
Original line number Diff line number Diff line
@@ -621,7 +621,7 @@ adb0efdf1462e9b2e742c0dcadd598666aac551f178be06e755bfcdf5797abd0 android.hardwar 
9e59fffceed0dd72a9799e04505db5f777bbbea1af0695ba4107ef6d967c6fda android.hardware.neuralnetworks@1.3::IDevice

258825966435b3ed08832055bb736d81516013e405f161d9ccde9a90cfcdde83 android.hardware.neuralnetworks@1.3::IPreparedModel

94e803236398bed1febb11cc21051bc42ec003700139b099d6c479e02a7ca3c3 android.hardware.neuralnetworks@1.3::IPreparedModelCallback

618a628f8c94d6f6e4cb401b69fa50ccb8b82191ea434e3a071252289b4f312c android.hardware.neuralnetworks@1.3::types

f3c1e7298da628a755b452cd3325e8d0fe867a2debb873069baab6a27434a72d android.hardware.neuralnetworks@1.3::types

3e01d4446cd69fd1c48f8572efd97487bc179564b32bd795800b97bbe10be37b android.hardware.wifi@1.4::IWifi

a64467bae843569f0d465c5be7f0c7a5b987985b55a3ef4794dd5afc68538650 android.hardware.wifi.supplicant@1.3::ISupplicant

44445b8a03d7b9e68b2fbd954672c18a8fce9e32851b0692f4f4ab3407f86ecb android.hardware.wifi.supplicant@1.3::ISupplicantStaIface

neuralnetworks/1.3/types.hal

+1 −1
Original line number Diff line number Diff line
@@ -4747,7 +4747,7 @@ enum OperationType : int32_t { 
    RESIZE_NEAREST_NEIGHBOR = @1.2::OperationType:RESIZE_NEAREST_NEIGHBOR,



    /**

     * Quantized version of {@link OperationType:LSTM}.

     * Quantized version of {@link OperationType::LSTM}.

     *

     * The input and the output use asymmetric quantized types, while the rest

     * use symmetric ones.

neuralnetworks/1.3/types.t

+2 −0
Original line number Diff line number Diff line
@@ -57,6 +57,8 @@ enum OperationType : int32_t { 


%insert Operation_1.2



%insert Operation_1.3



    /**

     * DEPRECATED. Since NNAPI 1.2, extensions are the preferred alternative to

     * OEM operation and data types.