aboutsummaryrefslogtreecommitdiff
path: root/src
AgeCommit message (Collapse)Author
9 daysfeat: Enables augmentations via --optimization-profileNathan Bailey
- Enables user to specify augmentations via the --optimization-profile switch - Can specify from pre-given examples or can provide each parameter manually - Updates README Resolves: MLIA-1147 Signed-off-by: Nathan Bailey <nathan.bailey@arm.com> Change-Id: I9cbe71d85def6a8db9dc974adc4bcc8d90625505
10 daysfix: Fixes MAE discrepancies of rewritesNathan Bailey
- Adds model.evaluate stage to retrieve correct MAE - Sets augmentations to none by default - Enables MAE calculations using dequantized data (if needed) Resolves: MLIA-972 Signed-off-by: Nathan Bailey <nathan.bailey@arm.com> Change-Id: Ia838b2d86caf7b10ad6e4d87bf6aa9e27c80bb72
2024-04-16feat: Implement the clustering rewrite for int8Nathan Bailey
Implements a clustering rewrite for fully connected layers for int8 models Resolves: MLIA-1080 Signed-off-by: Nathan Bailey <nathan.bailey@arm.com> Change-Id: If48efb22764187a382e5b84bbb5c3b75a6e71b75
2024-04-16feat: Implement the clustering rewrite for fp32Nathan Bailey
Implements a clustering rewrite for fully connected layers for fp32 models Resolves: MLIA-1079 Signed-off-by: Nathan Bailey <nathan.bailey@arm.com> Change-Id: I4c12f0bf911219b4066f0760976e424ebe900a0b
2024-04-16feat: CLI and API changes for the clustering rewriteNathan Bailey
Adds API changes for a fully-connected-clustering rewrite Resolves: MLIA-1077 Signed-off-by: Nathan Bailey <nathan.bailey@arm.com> Change-Id: I845796a391c5020e66472456b97ecad5ee8139a8
2024-04-12fix: Change training_parameters to return empty list instead of list of None ↵Nathan Bailey
if needed. Extension to MLIA-1004 Signed-off-by: Nathan Bailey <nathan.bailey@arm.com> Change-Id: Ib40c2e5932c1210a1d141200815a76e33f5ab078
2024-04-04feat: Implement int8 sparsity 2:4 rewriteMadeleine Dunn
- Implement pruning-preserving quantisation aware training - Rework the training logic to avoid duplication - Remove the DynamicallyLoadedRewrite class as it is now unused Resolves: MLIA-1003 Signed-off-by: Madeleine Dunn <madeleine.dunn@arm.com> Change-Id: Ia7a4acf5f477a27963cffa88180cca085b32ffe4
2024-04-03feat: Implement fp32 sparsity 2:4 rewriteMadeleine Dunn
- Update the existing placeholder with code to prune the given model Resolves: MLIA-1002 Signed-off-by: Madeleine Dunn <madeleine.dunn@arm.com> Change-Id: I76b0e0bfe81be5e57d518cd7bb588eef76a11641
2024-04-03feat: Add placeholder rewrite_target for sparsity24Madeleine Dunn
- The placeholder currently duplicates the existing fc target Resolves: MLIA-1000 Signed-off-by: Madeleine Dunn <madeleine.dunn@arm.com> Change-Id: I0df5d47e61dafa567e212566bbcb0f1639fe7642
2024-04-03feat: Implement sparsityMadeleine Dunn
- Add a placeholder file and registry option for sparsity Resolves: MLIA-999 Signed-off-by: Madeleine Dunn <madeleine.dunn@arm.com> Change-Id: I273192ba6813309f5226e3d8e0b686ce87ee6b79
2024-03-28fix: Check that training checkpoint feature works as expectedNathan Bailey
Fixes the checkpoint feature in training and also completes unit tests for it Resolves: MLIA-1111 Signed-off-by: Nathan Bailey <nathan.bailey@arm.com> Change-Id: Ic2b84b4b045db5ba3cb299fcd137ae9d31df5298
2024-03-28feat: Update Vela versionNathan Bailey
Updates Vela Version to 3.11.0 and TensorFlow version to 2.15.1 Required keras import to change: from keras.api._v2 import keras needed instead of calling tf.keras Subsequently tf.keras.X needed to change to keras.X Resolves: MLIA-1107 Signed-off-by: Nathan Bailey <nathan.bailey@arm.com> Change-Id: I53bcaa9cdad58b0e6c311c8c6490393d33cb18bc
2024-03-27fix: Update rewrite target nameMadeleine Dunn
- Rename "fully_connected" to "fully-connected" - This will resolve issues with upstreaming rewrite library changes Signed-off-by: Madeleine Dunn <madeleine.dunn@arm.com> Change-Id: I2f24ae4917a556fd0bd44f0db6ee4e0f7a68cd24
2024-03-22refactor: Backend dependencies and moreBenjamin Klimczak
- Add backend dependencies: One backend can now depend on another backend. - Re-factor 'DownloadArtifact': - Rename 'DownloadArtifact' to 'DownloadConfig' - Remove attributes 'name' and 'version' not relevant for downloads - Add helper properties: - 'filename' parses the URL to extract the file name from the end - 'headers' calls the function to generate a HTML header for the download - Add OutputLogger helper class - Re-factor handling of backend configurations in the target profiles. Change-Id: Ifda6cf12c375d0c1747d7e4130a0370d22c3d33a Signed-off-by: Benjamin Klimczak <benjamin.klimczak@arm.com>
2024-03-21refactor: Refactored functions for Corstone installationsBenedetta Delfino
Signed-off-by: Benedetta Delfino <benedetta.delfino@arm.com> Change-Id: I51f845e9fc9f0a699a239c63c268565487be2aeb
2024-03-14feat: Enable rewrite parameterisationNathan Bailey
Enables user to provide a toml or default profile to change training settings for rewrite optimization Resolves: MLIA-1004 Signed-off-by: Nathan Bailey <nathan.bailey@arm.com> Change-Id: I3bf9f44b9a2062fb71ef36eb32c9a69edcc48061
2024-03-14feat: Update Corstone-300 version to 11.24_13Benedetta Delfino
Signed-off-by: Benedetta Delfino <benedetta.delfino@arm.com> Change-Id: I0918c0c323328348e8f605ce20b81840b5c65a81
2024-03-13fix: Relax filtering during archive installationBenjamin Klimczak
- Relax the filtering when unpacking an archive - Add unit tests for the filtering Resolves: MLIA-1042 Change-Id: I8acd6a1596bef1c624a8fc67cdfbac961e0b179d
2024-03-11feat: Add support for Arm Corstone-300 and Corstone-310 on AArch64Benedetta Delfino
- Add support for Corstone-300 download on AArch64 - Add support for Corstone-310 download on AArch64 - Add support for Corstone-310 download on x86 - Add e2e tests and unit tests - Edited README.md to reflect updates Resolves: MLIA-1017 Signed-off-by: Benedetta Delfino <benedetta.delfino@arm.com> Change-Id: I8d54a721f91d67123f65c076313cef12b7df92bd
2024-02-23refactor: Migrate from Vela's internal code to CSV summaryNathan Bailey
Removes vela defines from vela compiler.py and performance.py Replaces calls to vela code with data from vela summary csv Resolves: MLIA-1024 Signed-off-by: Nathan Bailey <nathan.bailey@arm.com> Change-Id: I569878f2936767f70c0255919ca40d1969275529
2024-02-09feat: Integrate Vela's per-layer performance estimatesNathan Bailey
Resolves: MLIA-1055, MLIA-1056, MLIA-1057 Signed-off-by: Nathan Bailey <nathan.bailey@arm.com> Change-Id: Id573cec94e4a69117051dcd5175f383c0955d890
2024-01-23fix: Improve error handling for invalid fileAnnie Tallund
If a file has the right extension, MLIA previously tried to load files with invalid content, resulting in confusing errors. This patch adds better reporting for that scenario Resolves: MLIA-1051 Signed-off-by: Annie Tallund <annie.tallund@arm.com> Change-Id: I3f1fd578906a73a58367428f78409866f5da7836
2023-12-07MLIA-835 Invalid JSON outputGergely Nagy
TFLiteConverter was producing log messages in the output that was not possible to capture and redirect to logging. The solution/workaround is to run it as a subprocess. This change required some refactoring around existing invocations of the converter. Change-Id: I394bd0d49d36e6686cfcb9d658e4aad05326cb87 Signed-off-by: Gergely Nagy <gergely.nagy@arm.com>
2023-12-04Update to Vela 3.10, TensorFlow 2.14, Python 3.9Benjamin Klimczak
Updating to Vela 3.10 which requires TensorFlow 2.14 which requires Python 3.9 (dropping support for Python 3.8). Resolves: MLIA-997 Change-Id: Id60bd08f7156a8efa204ef71ba81590edf0e3b28 Signed-off-by: Benjamin Klimczak <benjamin.klimczak@arm.com>
2023-11-24MLIA-1037 Fix default backend validationBenjamin Klimczak
Add a check to see if the default backends are installed when no backend is provided via CLI. Change-Id: I27dd9f35cfeec187f44cba06915d1be5a3a052b5 Signed-off-by: Benjamin Klimczak <benjamin.klimczak@arm.com>
2023-11-22MLIA-963: Capture and handle Vela warningMichiel Olieslagers
Signed-off-by: Gergely Nagy <gergely.nagy@arm.com> Change-Id: I6c8b0b74d6d35261eb0ff1a37b9577f9033be8f9
2023-11-15Add linters/checkers for TOML files to pre-commitsBenjamin Klimczak
Change-Id: I8a228cbab405b4d4112e5e38856b3cb92304cba7 Signed-off-by: Benjamin Klimczak <benjamin.klimczak@arm.com>
2023-10-31MLIA-1019 Fix rebase artifactGergely Nagy
Fixed an artifact that crept in during the upstream rebase process, change a6ae703b6e41c73 was being taken out, but 3cd84481fa25 reintroduced the first part of a try/except block which caused a syntax error. Change-Id: I7fc2e18a227a30ebaaee0763450ee68646611add Signed-off-by: Benjamin Klimczak <benjamin.klimczak@arm.com>
2023-10-11Enable rewrites for quantized input modelsBenjamin Klimczak
If the input model for rewriting is quantized: - Record de-quantized TFRecords - enable writing de-quantized calibration data for the training - re-generate augmented training data, if needed - Use quantization-aware training (QAT) to train the replacement models - Check if replacement model is quantized: If source model is quantized, we make sure rewrite's output model is quantized too. Right now, only int8 is supported so raising an error if any other datatype is present in the output. Resolves: MLIA-907, MLIA-908, MLIA-927 Signed-off-by: Benjamin Klimczak <benjamin.klimczak@arm.com> Change-Id: Icb4070a9e6f1fdb5ce36120d73823986e89ac955
2023-10-11Re-factoring of rewrite management & added metricsGergely Nagy
- List available rewrites - Refactor/rename 'Rewrite' class to 'RewritingOptimizer' - Introduce a registry for rewrite functions - Refactor 'Rewriter' to use the registry to look up rewrite functions - Remove mentions of hardcoded "fully_connected" from CLI help and error messages, using the registry instead - Add unit tests - Enable rewrites for all targets: Extract optimization (including rewrite specific code) from the Ethos-U-specific data collector into OptimizingDataCollector. This is reused in other targets' collectors, such as TOSA and Cortex-A. - Add more logging for rewrite - add display of MAE and NRMSE values for the trained result - add total model MAE and NRMSE metric Resolves: MLIA-891, MLIA-899, MLIA-906 Change-Id: Ie798749e1ed60cab14fdb6d9c2271c833960e93f Signed-off-by: Benjamin Klimczak <benjamin.klimczak@arm.com>
2023-10-11Bug-fixes and re-factoring for the rewrite moduleBenjamin Klimczak
- Fix input shape of rewrite replacement: During and after training of the replacement model for a rewrite the Keras model is converted and saved in TensorFlow Lite format. If the input shape does not match the teacher model exactly, e.g. if the batch size is undefined, the TFLiteConverter adds extra operators during conversion. - Fix rewritten model output - Save the model output with the rewritten operator in the output dir - Log MAE and NRMSE of the rewrite - Remove 'verbose' flag from rewrite module and rely on the logging mechanism to control verbose output. - Re-factor utility classes for rewrites - Merge the two TFLiteModel classes - Move functionality to load/save TensorFlow Lite flatbuffers to nn/tensorflow/tflite_graph - Fix issue with unknown shape in datasets After upgrading to TensorFlow 2.12 the unknown shape of the TFRecordDataset is causing problems when training the replacement models for rewrites. By explicitly setting the right shape of the tensors we can work around the issue. - Adapt default parameters for rewrites. The training steps especially had to be increased significantly to be effective. Resolves: MLIA-895, MLIA-907, MLIA-946, MLIA-979 Signed-off-by: Benjamin Klimczak <benjamin.klimczak@arm.com> Change-Id: I887ad165aed0f2c6e5a0041f64cec5e6c5ab5c5c
2023-10-11Implement first rewrite (proof of concept)Ruomei Yan
* Define replacement function fully_connected layer * Define RewriteConfiguration and Rewriter to integrate rewrite module into mlia optimize command * Fix a bug in the ethos_u/data_collection.py file * Fix a bug in join.py * Remove diff_stats and use diff instead, added related changes around this to ensure e2e tests passing * Add unit tests for all changes * Fix bug in diff_stats function * The bug was caused by a dividing by numpy array of all zeros. The previous way of handling it did not consider the all zeros case but only dealt with partially zeros * unit tests added. * Fix the bug in rewrite/core/graph_edit/join.py * Remove the possibility of passing None to append_relabel function because it is immutable * The bug happened when empty dictionary was passed in the append_relabel function and the function overwrites the reference of operator_map which caused the dictionary was not updated after the function call Resolves: MLIA-749, MLIA-864, MLIA-866 Change-Id: I1ab426996232f182345e6e98033d5dcb32aea08c Signed-off-by: Benjamin Klimczak <benjamin.klimczak@arm.com>
2023-10-11Adapt rewrite module to MLIA coding standardsAnnie Tallund
- Fix imports - Update variable names - Refactor helper functions - Add licence headers - Add docstrings - Use f-strings rather than % notation - Create type annotations in rewrite module - Migrate from tqdm to rich progress bar - Use logging module in rewrite module: All print statements are replaced with logging module Resolves: MLIA-831, MLIA-842, MLIA-844, MLIA-846 Signed-off-by: Benjamin Klimczak <benjamin.klimczak@arm.com> Change-Id: Idee37538d72b9f01128a894281a8d10155f7c17c
2023-10-11MLIA-843 Add unit tests for module mlia.nn.rewriteBenjamin Klimczak
Note: The unit tests mostly call the main functions from the respective modules only. Change-Id: Ib2ce5c53d0c3eb222b8b8be42fba33ac8e007574 Signed-off-by: Benjamin Klimczak <benjamin.klimczak@arm.com>
2023-10-11Add a CLI component to enable rewritesRuomei Yan
* Add flags for rewrite (--rewrite, --rewrite-start, --rewrite-end, --rewrite-target) * Refactor CLI interfaces to accept tflite models with optimize for rewrite, keras models with optimize for clustering and pruning * Refactor and move common.py and select.py out of the folder nn/tensorflow/optimizations * Add file nn/rewrite/core/rewrite.py as placeholder * Update/add unit tests * Refactor OptimizeModel in ethos_u/data_collection.py for accepting tflite model case * Extend the logic so that if "--rewrite" is specified, we don't add pruning to also accept TFLite models. * Update README.md Resolves: MLIA-750, MLIA-854, MLIA-865 Signed-off-by: Benjamin Klimczak <benjamin.klimczak@arm.com> Change-Id: I67d85f71fa253d2bad4efe304ad8225970b9622c
2023-10-11MLIA-845 Migrate rewrite codeAnnie Tallund
- Add required files for rewriting of TensorFlow Lite graphs - Adapt rewrite dependency paths and project name - Add license headers Change-Id: I19c5f63215fe2af2fa7d7d44af08144c6c5f911c Signed-off-by: Benjamin Klimczak <benjamin.klimczak@arm.com>
2023-09-26MLIA-469 Support batch size > 1 for optimizationsAnnie Tallund
- Add a PruningPolicy to skip layers that are not supported by the Keras pruning API - Make dataset generation more generic to support use-cases beyond classification Signed-off-by: Annie Tallund <annie.tallund@arm.com> Change-Id: I198dae2b53860f449f2fdbc71575babceed1ffcf
2023-09-08MLIA-961 Update pre-commit hook versionsBenjamin Klimczak
- Update dependencies in .pre-commit.yaml - Fix code issues with new linters Change-Id: I36964ecf1a405dd8faac01b4470b56122a7cad17 Signed-off-by: Benjamin Klimczak <benjamin.klimczak@arm.com>
2023-09-05MLIA-961 Update tox dependenciesBenjamin Klimczak
- Update version dependencies in the tox.ini - Fix linter issues Change-Id: I04c3a841ee2646a865dab037701d66c28792f2a4 Signed-off-by: Benjamin Klimczak <benjamin.klimczak@arm.com>
2023-08-22MLIA-757: Update Vela and TensorFlow dependenciesJoseph Tummon
Ignoring new 'Conv_hwcn_Weights' layer that is named in TensorFlow 2.11.1 and used as buffer for float32 only. Signed-off-by: Joseph Tummon <Joseph.Tummon@arm.com> Change-Id: Iaa579c76013b1e0dc505466c46f5864a96af8c6d
2023-08-21MLIA-881 Update compatible operators for Cortex-ABenjamin Klimczak
Update the compatibility information of the backend for ArmNN TensorFlow Lite Delegate (classic) to version 23.05. Change-Id: I84693842d1a883f7083a6faf7d5ddcd5ecc34e5d Signed-off-by: Benjamin Klimczak <benjamin.klimczak@arm.com>
2023-05-15MLIA-755 Remove TOSA Extra DependencyDhruv Chauhan
- Removed TOSA Checker dependency from setup.cfg - Installation process calls directly the installation of TOSA Checker instead of the extra dependency Change-Id: I21e309b9316671959483bd2ef1ecaf644936a4cb
2023-04-12MLIA-849 Update mypy version and fix associated issuesAnnie Tallund
- Remove unused silencing of typing - Amend None type hints where it is default Change-Id: Id972b56dcdce865bf6c9d6aea88bc76baf39133e
2023-04-11MLIA-825 Make backend installation more genericBenjamin Klimczak
Use the backend registry to manage installation routines for different backends as well. This makes the process more generic and allows us to move towards plug & play for backends (i.e. there should be no code changes needed in the general MLIA code to add/support new backends). Change-Id: Ib7c772ec52b2f4d857c2c9871e44dfff97e9d970
2023-04-04MLIA-816 Correctly name TOSA Checker attributeDhruv Chauhan
- JSON output now reports tosa_checker as attribute name, which accurately represents its value as the version of TOSA Checker Change-Id: I8ac5032fea5dae65382db76091d295595a644816
2023-03-24MLIA-711 Extend TensorFlow Lite Compatibility CheckDhruv Chauhan
- Unify the TensorFlow Lite compatibility check across Cortex-A, TOSA and Ethos-U targets - Display tables/messages with parsed information - Do not display raw TensorFlow Lite errors, and return with exit code 0 Change-Id: I9333fdb6cbe592f1ed7395d392412168492a1479
2023-02-21MLIA-813 Change default output directory0.6.0-rc.30.6.0Dmitrii Agibov
- Use directory mlia-output as output directory for MLIA - If parameter --output-dir provided then place directory mlia-output under specified path or otherwise create it in the current working directory Change-Id: I298088c4aa8dbe9f35dee69ecb9ff6e9ea3cac0a
2023-02-16MLIA-812 Show error message for unsupported functionality0.6.0-rc.2Dmitrii Agibov
Change-Id: I68fb8c4e51046e9fc2d91ad8338718ba545209cd
2023-02-15MLIA-813 Change default output directoryDmitrii Agibov
- If no output directory provided then create one in the current working directory - Update documentation and tests Change-Id: Id1f2acef14e1bd2edffbfa6139a961a5c5018211
2023-02-13MLIA-709 Update compatibility data for Cortex-A0.6.0-rc.1Annie Tallund
- Add operator compatibility data for Cortex-A via for ArmNN TensorFlow Lite delegate 22.11 - Extend the Cortex-A target profile to include the version of the ArmNN TensorFlow Lite delegate to be used. - Some re-factoring work to support multiple versions and the new target profile parameter. Change-Id: Iae91bb0757ea3909be975af68b34d0ca2be47c43
generated by cgit v1.2.1 (git 2.23.0) at 2024-05-17 21:36:28 +0000