aboutsummaryrefslogtreecommitdiff
AgeCommit message (Collapse)Author
2022-07-22MLIA-569 Update TensorFlow to version 2.8Raul Farkas
- 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
2022-07-22MLIA-507 Upgrade Vela versionRaul Farkas
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
2022-07-20MLIA-529 Add pre-commit configurationRaul Farkas
- Add pre-commit configuration file that is used to run a series of hooks on the codebase. - Update setup.cfg to include required pre-commit library when installing MLIA with the [dev] extra require. Change-Id: I8e88cd2bae98c03c20a70a320e82d2eb38ce127c
2022-07-08MLIA-546 Merge AIET into MLIABenjamin Klimczak
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
2022-07-04MLIA-316 Specify cache arena size in the Vela memory profilesRuomei Yan
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
2022-06-27MLIA-522 No 'perf' in mode 'all' for TFLite filesBenjamin Klimczak
Fix the issue that no performance information is shown for TFLite files when the mode 'all_tests' is used. Change-Id: I8b4df4ab84ba9783b582ad449a34bf6177037e14
2022-06-23MLIA-545 Make quantization non-strictBenjamin Klimczak
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
2022-06-09Update readme with new contents of --outputRuomei Yan
Change-Id: I00669320303020b1953b3ba505d108b87cb89327
2022-05-30MLIA-509 Update README.md0.3.0Benjamin Klimczak
Address the feedback from the review during out-of-box testing. Change-Id: Ib70fce58240284ca39392988e2321743c5c02600
2022-05-30Specify long_description_content_type in setup.cfgDiego Russo
The content type of the long description needs to be specified to avoid publishing errors on pypi.org. Change-Id: Ibf40cab77599d5c04fb996f884eed9d56c5a5ce7
2022-05-30Add MLIA codebase0.3.0-rc.1Diego Russo
Add MLIA codebase including sources and tests. Change-Id: Id41707559bd721edd114793618d12ccd188d8dbd
2022-05-30Empty commitDiego Russo
Change-Id: Ie6194f62fede2c093b3471779f6f816d716ce639
generated by cgit v1.2.1 (git 2.23.0) at 2024-07-09 23:14:53 +0000