| Age | Commit message (Collapse) | Author |
|---|
|
Update example applications to support new core_driver inference
timeout feature.
Change-Id: Ib7283421aa8db9a3b5f1dd6d1bd44803491f0399
Signed-off-by: Jonny Svärd <jonny.svaerd@arm.com>
|
|
Change-Id: I47fdf29a50440c82fd9ccf111a846bf87e8a9e29
|
|
Adapt to Ethos-U driver changes
Change-Id: I5a10f9166f4d9ac32a1502409e1708ea62844944
|
|
Also override new/delete operators to call in FreeRTOS malloc/free in
the freeRTOS example app.
Change-Id: I08c0780c907e5fe90ccb1679869d3f41c87c2731
|
|
Changed mutex lock/unlock and semaphore take/give functions to return
an int value instead of void. In addition changed FreeRTOS and
message_handler applications (also FreeRTOS-based) to ignore failure
of xSemaphoreGive on binary semaphores, as it does not affect the
correctness of such applications.
Change-Id: I023c62dc8971488107679f6dd7a5967dec0380a8
|
|
Update sample applications to use an external context for the PMU
configuration. The external context stored in the InferenceJob will
be set as TFLu external context and will be returned in the
ethosu_inference_begin() and ethosu_inference_end() callbacks.
Change-Id: Ief1f0943e322c2b50e8b964017af59161f67de6b
|
|
Adjusting toolchain files which compiler warnings to enable.
Fixing compiler warnings reported by Arm Clang and Arm GCC.
Change-Id: I715e875904ffd7ecfe994d3093cdf066373981b1
|
|
Change-Id: Ic0a900c29f0ff24a7505ff952f326643c1bff5c0
|
|
This reverts commit 43834ab8967d1e8f063533c8c8cbf84be8ccc1b0.
Reason for revert: Temporarily backing out change to fix compilation issue for Cortex-M4.
Change-Id: I98a4ba8ce44e0ca396b7eb052cec4adecb9fe0ad
|
|
Change-Id: Ia5970925db31805a693e0c0dfc081375767a9b82
|
|
Change-Id: Ib1e59fda457edc90ceb324f35252c3def451c751
|
|
Tensorflow lite micro has increased the size of the MicroProfiler.
As a consequence the FreeRTOS application needs to increase the stack
size allocate from the heap.
Change-Id: I8e4df44767edaecee27d9571319ef72da5937a3b
|
|
Modified freertos.cpp to the support multi NPUs API.
Spawn NUM_INFERENCE_TASKS inference processing tasks (Reserves, locks,
and runs inference on an available NPU driver. Usually 1 per NPU, but
not required)
Spawn NUM_JOB_TASKS job creating/recieving tasks (Creates
NUM_JOBS_PER_TASK jobs, sends
them to inference job queue, and recieves response once finished)
Added: Mutex & Semaphore interfaces. Overrides weakly linked symbols in
driver.
Change-Id: Id187c6c9b43b988b1fdd560fdf3d57bd4b30b79c
|
|
Change-Id: I660cd5d2bc73eaf589598c4f0570f5e9293de28d
|
|
Adding script to run CTest on the Corstone-300 FVP. The script will
detect which version of the FVP that is used and pass the correct
command line arguments.
Updating README with instructions how to run tests, either using
CTest or calling the FVP directly.
Update FreeRTOS example to exit with the status of the inference.
Minor adjustments are needed to the output vectors.
Change-Id: I8a1a740b0dec2ce35d95e5c5d91f4b57a2c8e1fa
|
|
Replace the CPU-only network with mobilenet_v2_1.0_224.
The header files in this commit are the same as the model data in the
trustzone application, see the README.md in
applications/trustzone_inference for details on how to generate them
from source on Arm ML-Zoo repository on github.
Change-Id: I8d3cfd6313fd5d98880cf1b24511208ca12faa05
|
|
The FreeRTOS port resets the stack when the scheduler starts. Move the
queue to global memory for it to not be overwritten.
Change-Id: I98f2360a14a0f74a65353694c6e2f60d37461ecf
|
|
Moved the initialisation of the TensorArena from inference_process.cpp in core_software to application level.
Change-Id: Id2f8361b19241b4251e2ce90b4f330d32734e801
|
|
The source tree is configured for a specific target as defined in the
targets directory.
The common target components are defined in targets/common. Targets
for real platform should include this directory to get the default
target libraries setup.
Change-Id: I7fced4bfacec97432cbbd4125bd5b4cdd21122e3
|
