Age | Commit message (Collapse) | Author |
|
When asked to reduce across all dimensions, reduce would produce a
zero-sized tensor without dimensions and cause segmentation fault in the
implementation.
The change fixes the bug by making the op output a tensor of size [1] in
this case.
Also, updated the bug to clarify this behaviour.
Bug: 155508675
Test: NNTest_static
Change-Id: Ie98d8fa2e508255fd50f6bd8184dc323ba90fac8
|
|
Test: mm
Test: atest NeuralNetworksTest_static
Fixes: 155942515
Fixes: 155942747
Fixes: 155942575
Fixes: 155942378
Fixes: 155942301
Fixes: 155942510
Fixes: 155942697
Fixes: 155942566
Change-Id: I940dda440c958fcef527d532d57b01586e070fb7
|
|
|
|
|
|
|
|
The test does not make sense when partitioning or CPU fallback is
disabled.
Bug: 155849908
Test: adb shell setprop debug.nn.partition 0 && \
NNT_static --gtest_filter=FailingDriverTest.FailAfterInterpretedWhile
Test: adb shell setprop debug.nn.partition 2 && \
NNT_static --gtest_filter=FailingDriverTest.FailAfterInterpretedWhile
Change-Id: Ie81eef414de3f767f4dfcf282d39ba63e366057f
|
|
1. Adds bias dimension count validation.
2. Does more validation in validate().
Bug: 155575142
Bug: 155261461
Test: NNT_static --gtest_filter="*while_fib*"
Test: NNT_static --gtest_filter=ValidationTestDimensionProductOverflow2.DynamicOutputShapeOverflow
Change-Id: I7b70a29e76fdf99e656ee6e3867cfd97675cfeec
|
|
Execute function in our tests among other things makes sure that the
models work with caching enabled. Caching token and directory are
constant and therefore the same for all tests. This is usually not a
problem since the tests check only one model with a set of different
configs but this was not the case for QuantizationCouplingTest suite.
This suite ran signed and unsigned models in one test making them share
the same caching token and directory which is an incorrect use of
caching API.
This CL solves this problem by removing the execution of an unsigned
model from the test. This is safe since the unsigned model is still
verified in GeneratedTests suite.
Bug: 155604227
Test: NNTest_static
Change-Id: I6aa2c8cd3fa41e37a5de53259d1fcc784f327093
|
|
|
|
|
|
|
|
Bug: 147925145
Test: mma
Test: NeuralNetworksTest_static
Change-Id: Ie636c7cdc84ff7a262925f8ff8ebbd4d4f45201b
|
|
|
|
* changes:
Create tests for VersionedInterfaces errors
Simplify IDevice reboot logic
|
|
This helps cover the code path of data copying between hidl memory and
IBuffer, as well as data copying between IBuffers. These code paths may
not be covered by CTS because of the lack of driver support.
This CL additionally extracts TestAshmem class from TestGenerated to a
common TestUtils.
Bug: 152209365
Test: NNT_static
Change-Id: I617bfbc391c7d0ada0c32b31ee2e6e493d5dc6a2
|
|
rvc-dev
|
|
The header lib is depended on by libneuralnetworks_common which is
available to platform. With b/153073816, we will be checking the
availability to the platform as well, i.e. platform-available module
depending on platform-unavailable module will cause a build error.
Prepare for the change by correctly marking that the header lib is also
available to the platform.
Bug: 153073816
Test: m
Exempt-From-Owner-Approval: cherry-pick from AOSP
Merged-In: I31a198068c98e7d6b01b7e2cd6f43e54769f28b1
(cherry picked from commit ddda33ec48ac01e042854c0a017a4ce276172488)
Change-Id: I31a198068c98e7d6b01b7e2cd6f43e54769f28b1
|
|
Fixes: 155195637
Test: NNT_static_fuzzing and inspect the dumped spec
Change-Id: I11b50433b17afeceedae954f2832c1c2193b2c7f
|
|
|
|
* changes:
Regenerate tests.
Re-enable tests that are previously disabled.
|
|
Squeeze, when used on a single-value tensor with 1s in
each dimension, will result in zero-sized tensor without dimensions.
This change fixes it, by making its output a tensor of size [1].
Bug: 155238914
Test: squeeze_b155238914.mod.py run on coral.
Change-Id: Ia5bf655c647084d9fa094ae8a2048917a8237b81
|
|
This CL fixes the ordering of sequences in the test. Specifically:
1) Causes the spin-loop in waitForExecutionToBegin to spin while the
execution has not yet started
2) Adds dummyExecution() to the driver implementations of FAIL_LAUNCH
3) Skips getDurationWhileRunning for all DriverKind::CPU test cases
Further, this CL adds dummyExecution() to
TestPreparedModelLatest::executeFenced to ensure the call to
executeFenced will not complete until after the test has called
getDuration. This brings executeFenced in line with the other execution
methods which call dummyExecution().
Finally, this CL has the following two minor changes:
1) code that was previously running from a detached thread in
executeFenced now instead runs synchronously
2) a for-loop that iterated by constant reference now instead iterates
by constant value
Fixes: 155215099
Test: mma
Test: NeuralNetworksTest_static --gtest_filter=Fenced/TimingTest*
Change-Id: I69a7448367ce8353791c9462d144122b6c913802
|
|
|
|
Bug: 140641425
Test: NNT_static
Change-Id: I3e037df067125b04efbd73f6d84da228d5e24f7a
|
|
Bug: 140641425
Bug: 151328024
Bug: 152446228
Bug: 152445711
Bug: 152446298
Fixes: 152446228
Test: NNT_static
Test: NNT_static_fuzzing
Change-Id: Ifd1f45a2b058fe9996dca817a067ce2ad6d47b46
|
|
This CL also re-enables TestUnspecifiedDimensions, which will trigger
the bug in validateRequest when sample driver is deployed.
Bug: 141294076
Fixes: 155228680
Test: NNT_static with sample driver
Change-Id: I268eb67bda8933be180bd58b604ee76b72577697
|
|
rvc-dev
|
|
Fixes: 154639297
Test: NNT_static
Test: NNT_static_fuzzing
Change-Id: I2b37dd7fe07f3239682b5bc7f7cef0ae76134ad0
|
|
- The tests require mTestDevice being valid to perform the tests, while
useCpuOnly will only allow CPU fallback path.
Fixes: 155229031
Test: mm
Test: NeuralNetworksTest_static
Change-Id: Ic866d14de39d0c8f52648ad319bac14bc8fdd666
|
|
* changes:
Remove unused utility functions
Add tests for multiplier quantization functions
|
|
This CL introduces the following kinds of tests:
* device creation and initialization errors
* "normal" functional positive and negative tests
* HIDL transport error tests
* mock service crash tests
Fixes: 139189546
Bug: 129572750
Test: mma
Test: atest NeuralNetworksTest_static
Change-Id: I3e1eb5433732695572044a74f1529ffc9c3a1982
|
|
Test: Build NeuralNetworksTest_static both normally and with
#define VERBOSE uncommented in TestPartitioningRandom.cpp
Bug: 136735929
Change-Id: I79e33239b63885b050d77b5a819b7be82a80528e
|
|
HIDL allows a service to be retrieved with two functions:
* <Interface>::getService — blocks until service is retrieved
* <Interface>::tryGetService — immediately returns service or nullptr
Currently, the NN runtime retrieves the service in three different
places:
1) When the runtime first starts, <Interface>::getService is used to
acquire all services
2) When the object is dead, <Interface>::tryGetService is used to
attempt to reacquire the service, but will quickly resume if the
service is still rebooting
3) When the client calls ANNDevice_wait, <Interface>::getService is used
to block until the service is active again
This CL simplifies the IDevice reboot logic by changing these static
class functions to dependency injection. Specifically, VersionedIDevice
now retrieves a handle to the IDevice object through a DeviceFactory
function that is passed in when the VersionedIDevice object is created.
This function can either operate as blocking or nonblocking to support
all use-cases described above, and makes it easier to test the
VersionedIDevice recovery code.
Bug: 139189546
Test: mma
Test: NeuralNetworksTest_static
Test: CtsNNAPITestCases
Change-Id: I012eb4df6f09f98bdfbd0835457ba98bc22d906e
|
|
|
|
* changes:
Add STRIDED_SLICE with shrinkMask in RGG tests.
Increase the fp precision in dumped spec.
|
|
Fixes: 132322549
Test: NNT_static_fuzzing
Change-Id: I85577481125e131741992e9d896d12320af67e1a
|
|
By default, C++ will output 6 fractional digits of floating point
values. This is insufficient for some of the RGG tests that requires
precision < 1e-6.
This CL uses hex representation for fp values in the generated spec
file, while human-readable values are also dumped as a comment.
Fixes: 144788409
Test: NNT_static_fuzzing and inspected the dumped spec
Change-Id: I43ed11e9f73cb387ed8894713fe79361322315ba
|
|
|
|
In this test, the RGG produces a non-sensible graph with extreme large
output gain and highly clamped output range.
Fixes: 153690038
Test: NNT_static_fuzzing
Change-Id: I7063730e04ea8a18aecd20029eb6e726ac780c2a
|
|
Bug: 129569821
Test: atest NeuralNetworksTest{_static,_utils}
Change-Id: I3178c22e4570a4afb927eb42d275ae00e533c397
|
|
The tests are based on TF Lite's quantization_util_test.cc.
Fix: 129569821
Test: atest NeuralNetworkTest_utils
Change-Id: I9715e0a5f36d431f9d0bb2fbbf34e221996b6208
|
|
These tests use a customized IDevice to test the device memory
allocation and fallback logic.
This CL also allows the runtime to dispatch device memory allocation
with dynamic shape to drivers.
Additionally, this CL fixes a bug that a failed device memory allocation
will return BAD_DATA -- it should return OP_FAILED instead.
Bug: 152209365
Test: NNT_static
Change-Id: I1facb2dad345958c3b9b1bab4a9564085c382c4a
|
|
|
|
|
|
Fix sporadic failures in CtsNNAPITestCases.TensorRankConstraint tests.
Improves description of expectation failures when comparing
OperandTypeWithExtraParams instances.
Test: CtsNNAPITestCases
Bug: 154093710
Change-Id: Ia2b8bc914892f2ff7908d247fa26743fa242f783
|
|
Fix: 148208229
Test: NNT_static
Change-Id: I853f1f294cedacb0cbb810042ef2a3466a072ffe
|
|
Bug: 149199424
Test: NNT_static
Test: VTS 1.3
Change-Id: I887be1b8530aad4568db9e75d3260b6b78884d23
|
|
|
|
|
|
Bug: 153540930
Test: atest+presubmit
Change-Id: I8e3de182114503fd519b42393b36308145d125b8
|