Age | Commit message (Collapse) | Author |
|
- add version extraction function in compat.py
- create Metadata, MLIAMetadata, TOSAMetadata and MetadataDisplay classes
- update the reporting functions so tosa and mlia version will be displayed in output json
- update unit test test_configure_and_get_tosa_advisor to mock the get_events function
- update the copyright information of all changed/added files
- handle exception and report to json when program crashes
- write new context managers for capturing stderr and stdout
- support reporting stderr to json output
- support reporting model checksum and model name to json output
- made changes in test_e2e.py handling {model_name} replacement in --output
- add unit tests
Change-Id: I6629fd1c5754378e6accd488217c83d87c7eb6f1
|
|
Breaking change in the CLI and API: Sub-commands "optimization",
"operators", and "performance" were replaced by "check", which
incorporates compatibility and performance checks, and "optimize" which
is used for optimization. "get_advice" API was adapted to these CLI
changes.
API changes:
* Remove previous advice category "all" that would perform all three
operations (when possible). Replace them with the ability to pass a
set of the advice categories.
* Update api.get_advice method docstring to reflect new changes.
* Set default advice category to COMPATIBILITY
* Update core.common.AdviceCategory by changing the "OPERATORS" advice
category to "COMPATIBILITY" and removing "ALL" enum type.
Update all subsequent methods that previously used "OPERATORS" to use
"COMPATIBILITY".
* Update core.context.ExecutionContext to have "COMPATIBILITY" as
default advice_category instead of "ALL".
* Remove api.generate_supported_operators_report and all related
functions from cli.commands, cli.helpers, cli.main, cli.options,
core.helpers
* Update tests to reflect new API changes.
CLI changes:
* Update README.md to contain information on the new CLI
* Remove the ability to generate supported operators support from MLIA
CLI
* Replace `mlia ops` and `mlia perf` with the new `mlia check` command
that can be used to perform both operations.
* Replace `mlia opt` with the new `mlia optimize` command.
* Replace `--evaluate-on` flag with `--backend` flag
* Replace `--verbose` flag with `--debug` flag (no behaviour change).
* Remove the ability for the user to select MLIA working directory.
Create and use a temporary directory in /temp instead.
* Change behaviour of `--output` flag to not format the content
automatically based on file extension anymore. Instead it will simply
redirect to a file.
* Add the `--json` flag to specfy that the format of the output should
be json.
* Add command validators that are used to validate inter-dependent
flags (e.g. backend validation based on target_profile).
* Add support for selecting built-in backends for both `check` and
`optimize` commands.
* Add new unit tests and update old ones to test the new CLI changes.
* Update RELEASES.md
* Update copyright notice
Change-Id: Ia6340797c7bee3acbbd26601950e5a16ad5602db
|
|
Change-Id: Ieeaa9188ea1e29e2ccaad7475d457bce71e3140d
|
|
- Provide command for backend installation in case
if backend is not available
- Fix issue with connection timeout during downloading
- Show installation tools output only in verbose mode
Change-Id: Ic0e495ba19879cc2cda4fd0bce20b57ba896cfeb
|
|
With Vela 3.6 we are able to remove the special treatment of aarch64
in our dependencies, i.e.
- upgrade Vela to version 3.6 that resolves a compatibility issue for
aarch64 in 3.4 and 3.5.
- upgrade to TensorFlow 2.10 which now supports aarch64 (therefore
making it obsolete to use 'tensorflow-aarch64').
Change-Id: I86508b667b5ccb55bfd11dcae9defc54e5ef74de
|
|
- Rename module "mlia.devices" into "mlia.target"
- Rename module "mlia.target.ethosu" into "mlia.target.ethos_u"
- Rename module "mlia.target.cortexa" into "mlia.target.cortex_a"
- Rename and update tests
Change-Id: I6dca7c8646d881f739fb6b5914d1cc7e45e63dc2
|
|
- Create module "compat" for tosa_checker backend
- Move TOSA checker functions into new module
- Update tests
Change-Id: Ia07034515fe43b2061b8892535067d21315cc721
|
|
- Move backend management/executor code into module backend_core
- Create separate module for each backend in "backend" module
- Move each backend into corresponding module
- Split Vela wrapper into several submodules
Change-Id: If01b6774aab6501951212541cc5d7f5aa7c97e95
|
|
Resolves: MLIA-719, MLIA-720
Change-Id: Ib697046f5090260437f3b1ab5fe8c5b4975abae2
|
|
- Add new type of the backend based on python packages
- Add installation class for TOSA checker
- Update documentation
- Extend support of the parameter "force" in the
"install" command
Change-Id: I95567b75e1cfe85daa1f1c3d359975bb67b2504e
|
|
* add entry point for mlia-backend in setup.cfg and main.py
* add --force option for install from path: uninstall existing backend
in ML Inference Advisor and install from given path
* add uninstall and list program parameters: uninstall has
backend_name as input arg, install has backend_name as a mandatory argument
* add unit tests in test_cli_commands.py, test_cli_main.py,
test_tools_metadata_common.py, test_tools_metadata_corstone.py
* updated README.md
* remove --download option for installing backend
* add new lines for the display section when we do mlia-backen list
* add case insensitive support for backend names in command line argument
Change-Id: Icb89d8957fa6be4b767710e24fa074f26472674b
|
|
- Add new error types for the TensorFlow Lite compatibility
check
- Try to detect custom operators in SavedModel/Keras models
- Add warning to the advice about models with custom operators
Change-Id: I2f65474eecf2788110acc43585fa300eda80e21b
|
|
- Update TensorFlow dependencies for x86_64
- Adapt unit tests to new TensorFlow version
- Update linters (including pre-commit hooks) and fix issues
- Use conditional import to fix tflite compat code for aarch64
Change-Id: I1a9b080b900ab65e38f7f2552562822bbfdcd259
|
|
Check input model for Arm NN TensorFlow Lite Delegate 22.08 support.
Change-Id: I1253c4c0b294c5283e08f0a39561b922ef0f62e6
|
|
Change-Id: I212c9cad5f2ac28b75b1d9e2fb8f1f8b444b8397
|
|
* Add `api.generate_supported_operators_report` that calls
a report generator based on given target profile.
* Update `--supported-ops-report` cli flag help section and README.md
info by specifying that it is currently only supported for Ethos-U.
* Add tests for `generate_supported_operators_report` method.
* Add stub methods `report` for Cortex-A
and Tosa operators.py module that throw a "Not supported" exception.
Change-Id: Iaf373fe48299d807e48fd6a0e6c029ce32203f4f
|
|
- Add ability to intercept low level TensorFlow output
- Produce advice for the models that could not be
converted to the TensorFlow Lite format
- Refactor utility functions for TensorFlow Lite
conversion
- Add TensorFlow Lite compatibility checker
Change-Id: I47d120d2619ced7b143bc92c5184515b81c0220d
|
|
Due to the new version of Corstone-310, the generic inference runner
has been updated to 22.08:
* The inference runner 22.08 doesn't have timing adapters because
incompatible with new version of Corstone-310
* Remove some memory mode logic which is not needed anymore
* Corstone-310 allows to run Ethos-U65 simulation hence adding the
binary for enabling this case
* Delete the inference runner 22.05
* Fix codebase and tests to cope with changes above
Change-Id: I3dc894d7cb49b09102a19b0d7f588694a0f3b99f
|
|
* Add Cortex-A device skeleton
* Add unit tests for the Cortex-A device skeleton
* Update profiles.json by adding the new "cortex-a" profile
* Add new cortex-a factory to the get_advisor method in api.py
* Disable performance and optimization commands for the cortex-a
profile.
* Update trademarks section in README.md
* Update pyproject.toml to not run similarity check in imports
Change-Id: I2e228aaada1e2d3c5cc329d70572b51962ff517f
|
|
Use "TensorFlow Lite" instead of "TFLite" in
documentation and comments
Change-Id: Ie4450d72fb2e5261d152d72ab8bd94c3da914c46
|
|
Change-Id: I2ce8ccebf8a9972d9936164ae52912044c682633
|
|
- Update configuration for inclusive language linter
- Fix reported issues
Change-Id: If0f8b6e20c17d8ee1c6179c61040fc351437f036
|
|
- Remove the extra 's' character which broke the path detection
mechanism when installed from /opt/VHT location on AVH instances
- Add unit tests to make sure we fixed the problem
Change-Id: Ic33a3c6c4d2b33181268d0efbc0324962e741dd4
|
|
- added the target profile for ethos-u65-256
- modified the unit tests regarding target profiles
- updated the README.md
Change-Id: I0f6b50199e735a18f0b436d291c871e1fa0460dd
|
|
- Use pyupgrade tool for the syntax upgrade
Change-Id: I3b9ae6cc5da193329e37028cde967ae049388361
|
|
- Enable deferred annotations evaluation
- Use builtin types for type hints whenever possible
- Use | syntax for union types
- Rename mlia.core._typing into mlia.core.typing
Change-Id: I3f6ffc02fa069c589bdd9e8bddbccd504285427a
|
|
Apply the same formatting rules for each section in the
output of the command "backend status"
Change-Id: I253c513f99826ef1eb916285ca4c2cc1840633ac
|
|
- mypy issue: to make the comment #type: ignore platform specific,
flags like platform.machine() cannot be recognized by mypy, so we
cannot isolate the specific lines of code that fail mypy tests
- numpy issue: for numpy version < 1.20, the function np.unique
has not been type annotated, which caused mypy throwing the error
when we run our unit tests in aarch64
- because of the above two reasons, we use function decorator to
turn off type checking for entire functions to remove all
annotations so that the mypy error for certain lines can be silented
Change-Id: Id91e65ef7677b78b4c9c85b8412229e3672e3a66
|
|
Change-Id: I9dfa9f17a93ac24be0aa9ad68e4a72b79aecfb9d
|
|
- Add new module for TOSA
- Add advisor workflow components
- Use TOSA checker for getting operators compatibility
information
Change-Id: I769e5e2a84e15779658f0895b4a347384def63bf
|
|
- Move target specific details out of API module
- Move common logic for workflow event handler into a
separate class
Change-Id: Ic4a22657b722af1c1fead1d478f606ac57325788
|
|
Add bandit to pre-commit and fix some bandit errors.
We use the default security level (low) with few exceptions:
* B101 assert_use: apart of tests, we use assert in our codebase
hence we globally ignore error B101.
* B404/B603: these are errors related to subprocesse and they are
being ignored locally when used.
* B604 Test for any function with shell equals true: we have disabled
this locally because of its safe use in the tests.
Change-Id: If654e5e92285f7c86ac210a6f1373dbab6be17c9
|
|
Re-factoring the code base to further merge the old AIET code into MLIA.
- Remove last traces of the backend type 'tool'
- Controlled systems removed, including SSH protocol, controller,
RunningCommand, locks etc.
- Build command / build dir and deploy functionality removed from
Applications and Systems
- Moving working_dir()
- Replace module 'output_parser' with new module 'output_consumer' and
merge Base64 parsing into it
- Change the output consumption to optionally remove (i.e. actually
consume) lines
- Use Base64 parsing in GenericInferenceOutputParser, replacing the
regex-based parsing and remove the now unused regex parsing
- Remove AIET reporting
- Pre-install applications by moving them to src/mlia/resources/backends
- Rename aiet-config.json to backend-config.json
- Move tests from tests/mlia/ to tests/
- Adapt unit tests to code changes
- Dependencies removed: paramiko, filelock, psutil
- Fix bug in corstone.py: The wrong resource directory was used which
broke the functionality to download backends.
- Use f-string formatting.
- Use logging instead of print.
Change-Id: I768bc3bb6b2eda57d219ad01be4a8e0a74167d76
|
|
- Update TensorFlow to version 2.8 (now supported by Vela 3.4)
- Adapt existing codebase to preserve intermediary tensors in the interpreter in order to avoid errors when trying to print all of them in the future.
- Ignore types for numpy methods that do not have typing annotations in their definitions. This is needed because otherwise mypy would consider the calling function to also be untyped.
Change-Id: I943ac196fd4e378f5238949b15c23a2d628c8b5e
|
|
Upgrade Vela version from 3.3.0 to 3.4.0.
- Adapt code to use new typing notation by replacing `numpy.array` with `numpy.ndarray` where necessary.
Change-Id: I035e9564d448652aa09a52d79c71ef09663ea776
|
|
Merge the deprecated AIET interface for backend execution into MLIA:
- Execute backends directly (without subprocess and the aiet CLI)
- Fix issues with the unit tests
- Remove src/aiet and tests/aiet
- Re-factor code to replace 'aiet' with 'backend'
- Adapt and improve unit tests after re-factoring
- Remove dependencies that are not needed anymore (click and cloup)
Change-Id: I450734c6a3f705ba9afde41862b29e797e511f7c
|
|
When running the e2e test of Wav2Letter, the tensor allocation failed.
To resolve this, we changed the arena cache size to 2096768. This is
due to the requirement in Vela. We need to make it aware of the memory
limitation on the target we are deploying for.
Change-Id: I192790033954058fa5db249452d998764df52663
|
|
Fix the issue that no performance information is shown for TFLite files
when the mode 'all_tests' is used.
Change-Id: I8b4df4ab84ba9783b582ad449a34bf6177037e14
|
|
Use TFLITE_BUILTINS instead of TFLITE_BUILTINS_INT8 to make the
quantization non-strict.
Note: De facto this does not change the behavior of MLIA because the
TFLITE_BUILTINS_INT8 is not correctly applied with the new quantizer.
See: https://github.com/tensorflow/tensorflow/issues/56535
Change-Id: Ia0782ba22c5e9223fa10fec71c16aee60b79bb57
|
|
Add MLIA codebase including sources and tests.
Change-Id: Id41707559bd721edd114793618d12ccd188d8dbd
|