platform_hardware_interfaces/neuralnetworks/1.2
David Gross 48544cc38a "successful preparation means successful execution" guarantee neglects bad operation inputs
Under certain circumstances, we guarantee that a prepared model can be
executed successfully.  In describing those circumstances, we
neglected to specify that operation input operands must have legal
values for the guarantee to hold.  For example, the guarantee doesn't
hold if an ADD operation has an activation input that is not one of
the defined values; or if a RESHAPE operation has a shape input in
which two or more components are -1.

This change modifies the guarantee to apply only when operation input
operands have legal values.  It also documents this guarantee for
burst execution.

Note that if an operation has an input operand that can be proven to
have an illegal value at preparation time (e.g., a constant value that
is illegal), model preparation might (but is not required to) fail for
that reason.

Bug: 135933040

Test: $ cd neuralnetworks ; mma
Change-Id: I8b421550dd89e4bbbdae899e7cb5e9e88a46d2fb
2019-09-09 14:35:49 -07:00
..
vts Consolidate NNAPI VTS utility code 2019-08-30 14:01:38 -07:00
Android.bp Update hidl makefiles for bpfmt 2019-04-17 09:38:50 -07:00
IBurstCallback.hal Fix IBurstCallback.hal typo 2019-04-17 17:37:30 +00:00
IBurstContext.hal NNAPI Burst -- HAL interface 2019-01-24 14:04:35 -08:00
IDevice.hal Fix V1_2::IDevice::getType documentation: was @param instead of @return 2019-08-27 12:22:01 -07:00
IExecutionCallback.hal Update neuralnetworks HAL to allow collecting execution duration. 2019-01-24 16:07:03 -08:00
IPreparedModel.hal "successful preparation means successful execution" guarantee neglects bad operation inputs 2019-09-09 14:35:49 -07:00
IPreparedModelCallback.hal Add 1.2 NN HAL: IPreparedModel & callbacks. 2018-12-13 13:56:51 -08:00
types.hal Fix LSTM documentation 2019-05-15 14:57:34 +01:00