Age | Commit message (Collapse) | Author |
|
Dynamic shape model cannot directly run on the refenence model as
the concrete size of tensor is unknown therefore the volume of tensor
is not able to be allocated. Furthemore, the operators also expect
the input model is static-shaped.
This change turns dynamic model to static model prior to execution.
- Add `ifm_dynamic` field into json description to indicate whether
the model has dynamic shape or not.
- Add the shape inference pass into the compilation pipeline, firstly
legalize the dynamic tf/tfl model to dynamic tosa model with unknown
shapes, and then run the shape inference pass with static shapes
input argument to resolve unknown dimensions.
Change-Id: I5d2ffd452becc562dc30546789705bd01dd7a0b0
Signed-off-by: TatWai Chong <tatwai.chong@arm.com>
|
|
Name of the test can now come from the json description
rather than inferred from the directory. Old method remains to
keep functionality with older tests
Change-Id: I79f872103ae6a101b5cc799af91c933839f28dfb
|
|
And fixes in tosa_verif_run_tests:
* support for no-color printing
* stop double printing of error messages on verbose
* differentiate result code pass from results check
Change-Id: I26e957013a8d18f7d3d3691067dfb778008a1eea
Signed-off-by: Jeremy Johnson <jeremy.johnson@arm.com>
|