reference_model.git - [no description]

Age	Commit message (Collapse)	Author
2021-10-18	More ERROR_IF supports	Kevin Cheng
	- Also delay tensor allocation after operator being validated ERROR_IF can be caught first before 0 or negative dimension set the graph_status to UNPREDICTABLE - Rescale, Argmax, FullyConnected, Matmul, Pad, Reshape, Slice, Transpose, Clamp, Concat, Equal, Greater, GreaterEqual, Table Signed-off-by: Kevin Cheng <kevin.cheng@arm.com> Change-Id: I4e1b3e5794fe195ce1a37e28443ae584645a3b91
2021-10-05	Couple of reference model fixes	Kevin Cheng
	- comparison ops could have different type of input/output - add SUBGRAPH_ERROR_IF() when operator doesn't have any output tensor Signed-off-by: Kevin Cheng <kevin.cheng@arm.com> Change-Id: I10f2c10f92de1c7a979221a421fa8e86b26fcc72
2021-09-30	Fixes to pass NEGATE op test.	Kevin Cheng
	- Elementwise unary op input/output type should match. - TOSA_UNPREDICTABLE should ONLY be sent when a tensor with negative dimension is read/written Signed-off-by: Kevin Cheng <kevin.cheng@arm.com> Change-Id: I689518933a2b56cd62793e3f28ea66a6e57b057c
2021-09-30	Add SUBGRAPH_ERROR_IF() to catch graph-level error.	Kevin Cheng
	- Also replace SIMPLE_FATAL_ERROR() with FATAL_ERROR() since they're duplicate - Replace FATAL_ERROR()/ASSERT_MSG() with ERROR_IF_SUBGRAPH() if the condition is a graph error FATAL_ERROR()/ASSERT() should only be used by model internal/runtime error like file reading. Signed-off-by: Kevin Cheng <kevin.cheng@arm.com> Change-Id: If1e1e2488054a0ecd800fb0f2ea6487019282500
2021-09-16	Implement Conv3D kernel.	Kevin Cheng
	Signed-off-by: Kevin Cheng <kevin.cheng@arm.com> Change-Id: Ic16e918b1a2423ad563684e29ce70d9efdbf9c02
2021-08-20	Replace node level check ASSERT_MSG_NODE()/FATAL_ERROR_NODE() with REQUIRE() ↵	Kevin Cheng
	or ERROR_IF() - Adding return code enum class: {VALID, UNPREDICTABLE, ERROR} - Runtime errors (e.g. memory allocation failure) will abort immediately, or will return one of the three return codes Part of the codes are re-written to pass REQUIRE() to the top-level (e.g. apply_scale_32/16()) - Update setExpectedFailure() to setExpectedReturnCode() on test generation script - Update test regression script to interface with reference model change Signed-off-by: Kevin Cheng <kevin.cheng@arm.com> Change-Id: Ia063c936bcb2a54d6e379a5bb6801aa72d1186f1
2021-08-12	Support int4 weights read. Added conv2d int8xint4 in test generation.	Kevin Cheng
	Signed-off-by: Kevin Cheng <kevin.cheng@arm.com> Change-Id: I61620f160c7dad6aac5fcc3da0a6e97f3bae5b40
2021-06-24	Update to use new serialization_lib API.	Kevin Cheng
	- Constant tensors are now initialized from embedded u8 array instead from numpy. - Python unit test generator and built-in test hasn't been updated. Signed-off-by: Kevin Cheng <kevin.cheng@arm.com> Change-Id: I5cb86f8e5ec8f23fee5dcbf257874a0f204ede04
2021-06-04	Rewrite model frontend to be json-driven.	Kevin Cheng
	Change-Id: Iac786eff96183938d2fd11cde9313c6e8e1270a5
2021-05-12	Update to v0.22.0	Kevin Cheng
	- remove identityN and placeholder - add div - update serialization_lib hash - update apply_scale_16() assertion - regenerate examples/ due to serialization_lib change Change-Id: I7183d92bec33697c65adfc07cb8eb89c6882675a
2021-04-27	Replace serialization/ and verif/ with MLPlatform's serialization_lib submodule	Kevin Cheng
	- Remove Usage and Format - Run black on verif/*.py scripts Signed-off-by: Kevin Cheng <kevin.cheng@arm.com> Change-Id: Ie81515891eb0039540f614894f4b6b0e0e78ba74
2021-02-22	Fix operator initialization bug when rank/dtype fails to initialize with ↵	Kevin Cheng
	Usage arrays Signed-off-by: Kevin Cheng <kevin.cheng@arm.com> Change-Id: Iefa2959996871d06b766dadbc4cba601e2e739fe
2020-10-14	Initial checkin of TOSA reference_model and tests	Eric Kunze
	Change-Id: I2f8e7fa63e2ae40203e57d2cc8814bde3b312cb6 Signed-off-by: Eric Kunze <eric.kunze@arm.com>