Age | Commit message (Collapse) | Author |
|
Bug: 155421116
Test: NeuralNetworksTest_static
Change-Id: I434d70e30b137a37febfab83127d79f9a6ecbae6
|
|
Change-Id: I0426ecb5a2d705a9f9c84214ea5c3712171c906b
|
|
e941d7c787 am: e8a7d0f6a9
Original change: https://googleplex-android-review.googlesource.com/c/platform/frameworks/ml/+/11867240
Change-Id: I0da07295387efb300957b8dbbce1d3d7fb3f9cb5
|
|
e941d7c787
Original change: https://googleplex-android-review.googlesource.com/c/platform/frameworks/ml/+/11867240
Change-Id: Ib55d105ba54c45b6b79a201829ae82fa65545267
|
|
Bug: 132458982
Bug: 154597673
Test: NNT_static --gtest_filter='*unknown_*'
Change-Id: I514b78ee3cf2efd86a47412e413a6873341a59d0
|
|
|
|
Original change: https://googleplex-android-review.googlesource.com/c/platform/frameworks/ml/+/11882615
Change-Id: Iffb46dd741e98ccf80b082b70b01ab1520181103
|
|
Original change: https://googleplex-android-review.googlesource.com/c/platform/frameworks/ml/+/11882615
Change-Id: I778f972749a52eff87872f80ba0507ad0c5500ea
|
|
Bug: 153876253
Test: mm
Change-Id: I4d36ed2aeaa7666fa349b50c93397792e34fad12
|
|
Fix: 159076604
Test: m
Change-Id: I44f31a004309594f03ef7eadf10c2ff51097e954
|
|
Change-Id: I6a03d021c58a0264ab9e609ed2fc35fb84c5a2ad
|
|
rvc-dev am: e19d742a8f am: dfa49a7ac6
Original change: https://googleplex-android-review.googlesource.com/c/platform/frameworks/ml/+/11815486
Change-Id: I1b9abbcb8b44ab7be0f1cb9ff475d82a7f84a53f
|
|
rvc-dev am: e19d742a8f
Original change: https://googleplex-android-review.googlesource.com/c/platform/frameworks/ml/+/11815486
Change-Id: Iad612cd6e715e034c0c056869c4c14e5a60a6db2
|
|
rvc-dev
|
|
This change restricts presubmit to only run a single pass of
NeuralNetworksTest_static ("pass 10"), corresponding to:
* useCpuOnly = 0
* computeMode = ComputeMode::ASYNC
* allowSyncExecHal = 1
Bug: 131770421
Test: mma
Test: atest
Change-Id: Ifd316ea87151ae80001208a38cb7af321f7cf9ec
|
|
Change-Id: I0666b757b0955967dd54948f25450563e7259491
|
|
Original change: https://googleplex-android-review.googlesource.com/c/platform/frameworks/ml/+/11680640
Change-Id: I43b1f4cf94266f1fcc6b6359d0f9996cbf7622c9
|
|
Original change: https://googleplex-android-review.googlesource.com/c/platform/frameworks/ml/+/11680640
Change-Id: I7c255211b7f9d161dfb4afbd52f082cb487a8988
|
|
* changes:
Support WHILE with growing output tensor in CpuExecutor
Relax control flow boundary operand dimension constraint
|
|
1. Adds a WHILE test that produces a tensor of dynamic size. The loop
body model has inputs and outputs of unknown rank.
2. Adds an IF test where the branch models have unkown input and output
ranks.
3. Modifies the partitioner to avoid trying to delegate referenced
models if an IF or WHILE or their associated referenced models have
unknown dimensions.
4. Adds dynamic loop output shape support to CpuExecutor by allocating
new temporaries on each iteration.
Bug: 132458982
Bug: 154597673
Test: NNT_static --gtest_filter='*_dynamic*'
Change-Id: I8da1aa92abf090adbdcbf647c113fe27f4c002d8
|
|
Also updates the NDK spec to mention the constraints and adds some
validation tests.
Bug: 132458982
Bug: 156918813
Test: NNT_static
Change-Id: Ia112e46da065a623a52ac1c402d28dcb963e5580
|
|
Change-Id: Ic5cf51adcdd15e52785bcafe3d94b241b541e8a7
|
|
am: fe603b440c am: bbd60fa020
Original change: https://googleplex-android-review.googlesource.com/c/platform/frameworks/ml/+/11620917
Change-Id: Ibaf84e7080d46cf9e8099aa98480778e5d680f6b
|
|
am: fe603b440c
Original change: https://googleplex-android-review.googlesource.com/c/platform/frameworks/ml/+/11620917
Change-Id: I42bebb34dafb55b58a7e329243a539fa15a60f2e
|
|
|
|
This change adds additional validation for non-optional tensors for the
following operations:
* EMBEDDING_LOOKUP
* HASHTABLE_LOOKUP
* LSH_PROJECTION
* BIDIRECTIONAL_SEQUENCE_LSTM
* LSTM
* RANDOM_MULTINOMIAL
* RNN
* SVDF
* SPLIT
Some operations such as SVDF unpack the scalar values without checking
if the value is present, leading to a failed CHECK. This CL adds
protections to use default values in these cases, and relies on a
corresponding Prepare method to cause these cases to fail validation.
Bug: 157516274
Test: mma
Test: CtsNNAPITestCases
Test: NeuralNetworksTest_static
Test: libneuralnetworks_fuzzer
Change-Id: I6bb804ec40205c9741b04231022894c714ad28ec
|
|
Change-Id: I0285a6d5b4a40655c54c1a0d709b5def5afbf8c8
|
|
54688b80e2 am: 7e13bcdcb7
Original change: https://googleplex-android-review.googlesource.com/c/platform/frameworks/ml/+/11707952
Change-Id: Ib8a2e230655ad9c7e3839d79d6a2c3dff6c7f0b5
|
|
54688b80e2
Original change: https://googleplex-android-review.googlesource.com/c/platform/frameworks/ml/+/11707952
Change-Id: I2bed8eabb3110a69fabf6a44a67197af9207bc9e
|
|
LSH_PROJECTION is very sensitive to the value of the hash tensor. Prior
to this CL, AllInputsAsInternalCoverter will convert the hash tensor to
internal by introducing a dummy ADD operation. Under relaxed execution
mode, the small precision loss in ADD will result in a significant
difference in the final result. This CL prevents the hash tensor from
being converted to internal in relaxed precision tests.
Additionally, this CL removes a redundant variation in
lsh_projection_float16.
Fixes: 155962587
Test: NNT_static
Change-Id: Id5522b4949a4e3ab4801537e8eb747a25f0cd0e8
|
|
Change-Id: Iaaab2d04a5c29c0ddb77949d1ca5e439f45f5329
|
|
c7e4e604b2 am: 1a13ed68b3
Change-Id: I574d4545659691bf74623ea2247dd65bbf15339a
|
|
Change-Id: Ia595deeb58fb6d72e9516082b2c101034a9bde2a
|
|
|
|
Change-Id: Id34f07d30e78e2a22c1ccb78a1ba7bb7a6998643
|
|
rvc-dev am: 2299d26439 am: 469128d85b
Change-Id: Idebe9766f3d5c2ce2eac60bdae2c0910e67b0a78
|
|
rvc-dev am: 2299d26439
Change-Id: I34b0045f0578d6bcca09a72642dfbeed51b74e79
|
|
rvc-dev
|
|
a71f6b8f21
Change-Id: Ib77fd4834e5882fa19c6d8c613a6e2a447aef868
|
|
Change-Id: Ic205bc7f63a7d45fe277480d4b09c3cbeb21285b
|
|
|
|
Change-Id: I2607408d3ca618a684ccdaec1c6bcfb4257e1a67
|
|
Bug: 157268934
Test: mma
Test: libneuralnetworks_fuzzer
Change-Id: I5d78db36b110eaec2230478c4759f94f386d59c3
|
|
Change-Id: Ia6227cb2d15782de915081cdd1e144ee7c938dda
|
|
Change-Id: Ieb84523dbc03cd79cbaf44710e38c2e917d4b96d
|
|
* changes:
Fix FULLY_CONNECTED issue with unknown num_units.
Fix CAST issue with outputs of unknown rank.
|
|
The generated test is added only to CTS since VTS would fail on some 1.2
drivers.
Fix: 156284111
Test: NeuralNetworksTest_static
Change-Id: I4f3c6cdb9f546501e4ca375d7900431c384d6885
|
|
Change-Id: I066342232903e34667b03d501433d9823d452570
|
|
The scale in NNAPI is always a fp32 data type. As there are accelerators
that only support fp16 data type, there is precision loss when
executing a casting operation that converts a fp16 buffer to/from a
quantized buffer. In the worst case, the precision loss in scale could
be up to 0.5 ULP, and results in 0.5 * 255 = 127.5 ULP difference in the
final result. This is much larger than the tolerance of these operations
in RGG. This CL sets the scale of such operations to be always representable
in fp16 to avoid potential precission loss.
Additionally, relax the MSE requirement on DEQUANTIZE.
Bug: 155842363
Test: NNT_static_fuzzing
Change-Id: I511ddb6753be1dabac36e1423820a03a4f28641e
|
|
Fixes: 156748888
Test: NNT_static
Test: 1.3 VTS with ag/11509996
Change-Id: Ib3b191ccefdfd0d03f8c69772976ef0f2421a9d7
|