Data

Tools

Indexes

Applications

Experiments

Open Source Science

Recent Releases of vak

vak - 1.0.4.post1

Full Changelog: https://github.com/vocalpy/vak/compare/1.0.4...1.0.4.post1

- Python
Published by NickleDave 11 months ago

vak - 1.0.4

What's Changed

  • docs: add @henricombrink as a contributor for bug by @allcontributors[bot] in https://github.com/vocalpy/vak/pull/782
  • docs: add @milaXT as a contributor for bug by @allcontributors[bot] in https://github.com/vocalpy/vak/pull/786
  • Added a configuration file for improved model performance along with supplemental parameter documentation by @Tingyan-Guo in https://github.com/vocalpy/vak/pull/788
  • docs: add milaXT as a contributor for doc by @allcontributors[bot] in https://github.com/vocalpy/vak/pull/789
  • DEV: Require Python >= 3.11, bump lower bounds on deps by @NickleDave in https://github.com/vocalpy/vak/pull/804

New Contributors

  • @Tingyan-Guo made their first contribution in https://github.com/vocalpy/vak/pull/788

Full Changelog: https://github.com/vocalpy/vak/compare/1.0.3...1.0.4

- Python
Published by NickleDave 11 months ago

vak - 1.0.3

What's Changed

  • BUG: avoid KeyError in train.frame_classification, fix #779 by @NickleDave in https://github.com/vocalpy/vak/pull/781

Full Changelog: https://github.com/vocalpy/vak/compare/1.0.2...1.0.3

- Python
Published by NickleDave over 1 year ago

vak - 1.0.2

What's Changed

  • DOC: Update autoannoate tutorial, fix #768 by @NickleDave in https://github.com/vocalpy/vak/pull/769
  • docs: add meriablue as a contributor for doc by @allcontributors in https://github.com/vocalpy/vak/pull/770
  • ENH: fix frame classification model to work with BioSoundSegBench by @NickleDave in https://github.com/vocalpy/vak/pull/774

Full Changelog: https://github.com/vocalpy/vak/compare/1.0.1...1.0.2

- Python
Published by NickleDave over 1 year ago

vak - 1.0.1

What's Changed

  • DEV: Require Python>=3.10, update other dependencies by @NickleDave in https://github.com/vocalpy/vak/pull/765
  • BUG: minor fixes to run with biosoundsegbench dataset by @NickleDave in https://github.com/vocalpy/vak/pull/766

Full Changelog: https://github.com/vocalpy/vak/compare/1.0.0...1.0.1

- Python
Published by NickleDave almost 2 years ago

vak - 1.0.0

What's Changed

  • Version 1.0 by @NickleDave in https://github.com/vocalpy/vak/pull/639
  • DOC: Add version 1.0 announcement [skip ci] by @NickleDave in https://github.com/vocalpy/vak/pull/640
  • DOC: Add version 1.0 announcement to README [skip ci] by @NickleDave in https://github.com/vocalpy/vak/pull/642
  • DOC: Add API reference, fix #441 by @NickleDave in https://github.com/vocalpy/vak/pull/644
  • DOC: Revise reference/about.md [skip ci] by @NickleDave in https://github.com/vocalpy/vak/pull/646
  • CLN: Refactor window dataset, add tests by @NickleDave in https://github.com/vocalpy/vak/pull/654
  • ENH: Use crowsetta 5.0, fixes #526 by @NickleDave in https://github.com/vocalpy/vak/pull/657
  • Prep datasets as directories, fixes #649 #650 #651 by @NickleDave in https://github.com/vocalpy/vak/pull/658
  • BUG: Fix usage of crowsetta 5.0 by @NickleDave in https://github.com/vocalpy/vak/pull/659
  • BUG/CLN: Fixup prepare dataset as directory by @NickleDave in https://github.com/vocalpy/vak/pull/660
  • replace union to future syntax by @Ja-sonYun in https://github.com/vocalpy/vak/pull/661
  • docs: add Ja-sonYun as a contributor for code by @allcontributors in https://github.com/vocalpy/vak/pull/662
  • BUG: Change labelmap for validation step of FrameWindowClassificationModel only, fix #664 by @NickleDave in https://github.com/vocalpy/vak/pull/665
  • Refactor api, fixes #663 by @NickleDave in https://github.com/vocalpy/vak/pull/666
  • Refactor frame classification, add audio datasets + DAS model, fixes #630 #652 #667 by @NickleDave in https://github.com/vocalpy/vak/pull/670
  • Remove initial implementation of DAS model by @NickleDave in https://github.com/vocalpy/vak/pull/675
  • Add decorators to register models and model families, fix #623 by @NickleDave in https://github.com/vocalpy/vak/pull/676
  • ENH: Add ED-TCN model by @NickleDave in https://github.com/vocalpy/vak/pull/677
  • ENH: Determine network kwargs dynamically in vak.models.get by @NickleDave in https://github.com/vocalpy/vak/pull/680
  • BUG/CLN: Add/fix log statements in FrameClassificationModel by @NickleDave in https://github.com/vocalpy/vak/pull/681
  • Add parametric UMAP model family by @NickleDave in https://github.com/vocalpy/vak/pull/688
  • Fix and run linting by @NickleDave in https://github.com/vocalpy/vak/pull/690
  • TST/CLN: Fix unit tests by @NickleDave in https://github.com/vocalpy/vak/pull/693
  • docs: add JacquelineGoe as a contributor for bug by @allcontributors in https://github.com/vocalpy/vak/pull/695
  • BUG: Make distance metrics return tensors, fix #700 #701 by @NickleDave in https://github.com/vocalpy/vak/pull/702
  • docs: add VenetianRed as a contributor for bug by @allcontributors in https://github.com/vocalpy/vak/pull/703
  • docs: add zhileiz1992 as a contributor for bug by @allcontributors in https://github.com/vocalpy/vak/pull/705
  • DOC, Make minor doc fixes, fixes #704 by @NickleDave in https://github.com/vocalpy/vak/pull/706
  • docs: add zhileiz1992 as a contributor for code by @allcontributors in https://github.com/vocalpy/vak/pull/711
  • docs: add marisbasha as a contributor for ideas by @allcontributors in https://github.com/vocalpy/vak/pull/712
  • docs: add marisbasha as a contributor for code by @allcontributors in https://github.com/vocalpy/vak/pull/713
  • DOC: Add eval to autoannotate, fix #460 by @NickleDave in https://github.com/vocalpy/vak/pull/715
  • docs: add vivinastase as a contributor for ideas by @allcontributors in https://github.com/vocalpy/vak/pull/716
  • ENH: Minimize frame classification dataset size, fix #717 by @NickleDave in https://github.com/vocalpy/vak/pull/718
  • BUG: Fix models to log train loss on step, fixes #720 by @NickleDave in https://github.com/vocalpy/vak/pull/722
  • CLN: Rename "segment error rate" to "character error rate", fix #721 by @NickleDave in https://github.com/vocalpy/vak/pull/723
  • docs: add danielmk as a contributor for doc by @allcontributors in https://github.com/vocalpy/vak/pull/732
  • DOC: fix autoannotate tutorial configs, fixes #734 by @NickleDave in https://github.com/vocalpy/vak/pull/735
  • TST: Fix test in common.labels by @NickleDave in https://github.com/vocalpy/vak/pull/747
  • ENH: Switch to version 1.0 of config file format, fix #685 #345 #748 by @NickleDave in https://github.com/vocalpy/vak/pull/750
  • ENH: Add lightning.Trainer config, fix #691 #687 #742 #745 by @NickleDave in https://github.com/vocalpy/vak/pull/752
  • CLN: Refactor model abstraction, fix #737 #726 by @NickleDave in https://github.com/vocalpy/vak/pull/753
  • CLN/ENH: Rename and refactor datapipes, add datasets; fix #574 #724 #754 by @NickleDave in https://github.com/vocalpy/vak/pull/755

New Contributors

  • @Ja-sonYun made their first contribution in https://github.com/vocalpy/vak/pull/661

Full Changelog: https://github.com/vocalpy/vak/compare/0.8.2...1.0.0

- Python
Published by NickleDave about 2 years ago

vak - 0.8.2

What's Changed

  • BUG: fix default for posttfmkwargs, fixes Inconsistent syllable error by @zhileiz1992 in https://github.com/vocalpy/vak/pull/710

New Contributors

  • @zhileiz1992 made their first contribution in https://github.com/vocalpy/vak/pull/710

Full Changelog: https://github.com/vocalpy/vak/compare/0.8.1...0.8.2

- Python
Published by NickleDave over 2 years ago

vak - 0.8.1

What's Changed

  • BUG: Have to_segments return all Nones for no segments, fix #634 by @NickleDave in https://github.com/vocalpy/vak/pull/636
  • docs: add nhoglen as a contributor for bug by @allcontributors in https://github.com/vocalpy/vak/pull/637

Full Changelog: https://github.com/vocalpy/vak/compare/0.8.0...0.8.1

- Python
Published by NickleDave over 2 years ago

vak - 1.0.0a3

What's Changed

  • BUG: Make distance metrics return tensors, fix #700 #701 by @NickleDave in https://github.com/vocalpy/vak/pull/702
  • docs: add VenetianRed as a contributor for bug by @allcontributors in https://github.com/vocalpy/vak/pull/703

Full Changelog: https://github.com/vocalpy/vak/compare/1.0.0a2...1.0.0a3

- Python
Published by NickleDave over 2 years ago

vak - 1.0.0a2

What's Changed

  • BUG: Have to_segments return all Nones for no segments, fix #634 by @NickleDave in https://github.com/vocalpy/vak/pull/636
  • docs: add nhoglen as a contributor for bug by @allcontributors in https://github.com/vocalpy/vak/pull/637
  • Version 1.0 by @NickleDave in https://github.com/vocalpy/vak/pull/639
  • DOC: Add version 1.0 announcement [skip ci] by @NickleDave in https://github.com/vocalpy/vak/pull/640
  • DOC: Add version 1.0 announcement to README [skip ci] by @NickleDave in https://github.com/vocalpy/vak/pull/642
  • DOC: Add API reference, fix #441 by @NickleDave in https://github.com/vocalpy/vak/pull/644
  • DOC: Revise reference/about.md [skip ci] by @NickleDave in https://github.com/vocalpy/vak/pull/646
  • CLN: Refactor window dataset, add tests by @NickleDave in https://github.com/vocalpy/vak/pull/654
  • ENH: Use crowsetta 5.0, fixes #526 by @NickleDave in https://github.com/vocalpy/vak/pull/657
  • Prep datasets as directories, fixes #649 #650 #651 by @NickleDave in https://github.com/vocalpy/vak/pull/658
  • BUG: Fix usage of crowsetta 5.0 by @NickleDave in https://github.com/vocalpy/vak/pull/659
  • BUG/CLN: Fixup prepare dataset as directory by @NickleDave in https://github.com/vocalpy/vak/pull/660
  • replace union to future syntax by @Ja-sonYun in https://github.com/vocalpy/vak/pull/661
  • docs: add Ja-sonYun as a contributor for code by @allcontributors in https://github.com/vocalpy/vak/pull/662
  • BUG: Change labelmap for validation step of FrameWindowClassificationModel only, fix #664 by @NickleDave in https://github.com/vocalpy/vak/pull/665
  • Refactor api, fixes #663 by @NickleDave in https://github.com/vocalpy/vak/pull/666
  • Refactor frame classification, add audio datasets + DAS model, fixes #630 #652 #667 by @NickleDave in https://github.com/vocalpy/vak/pull/670
  • Remove initial implementation of DAS model by @NickleDave in https://github.com/vocalpy/vak/pull/675
  • Add decorators to register models and model families, fix #623 by @NickleDave in https://github.com/vocalpy/vak/pull/676
  • ENH: Add ED-TCN model by @NickleDave in https://github.com/vocalpy/vak/pull/677
  • ENH: Determine network kwargs dynamically in vak.models.get by @NickleDave in https://github.com/vocalpy/vak/pull/680
  • BUG/CLN: Add/fix log statements in FrameClassificationModel by @NickleDave in https://github.com/vocalpy/vak/pull/681
  • Add parametric UMAP model family by @NickleDave in https://github.com/vocalpy/vak/pull/688
  • Fix and run linting by @NickleDave in https://github.com/vocalpy/vak/pull/690
  • TST/CLN: Fix unit tests by @NickleDave in https://github.com/vocalpy/vak/pull/693
  • docs: add JacquelineGoe as a contributor for bug by @allcontributors in https://github.com/vocalpy/vak/pull/695

New Contributors

  • @Ja-sonYun made their first contribution in https://github.com/vocalpy/vak/pull/661

Full Changelog: https://github.com/vocalpy/vak/compare/0.8.0...1.0.0a2

- Python
Published by NickleDave over 2 years ago

vak - 1.0.0a1

What's Changed

  • BUG: Have to_segments return all Nones for no segments, fix #634 by @NickleDave in https://github.com/vocalpy/vak/pull/636
  • docs: add nhoglen as a contributor for bug by @allcontributors in https://github.com/vocalpy/vak/pull/637
  • Version 1.0 by @NickleDave in https://github.com/vocalpy/vak/pull/639

Full Changelog: https://github.com/vocalpy/vak/compare/0.8.0...1.0.0a1

- Python
Published by NickleDave almost 3 years ago

vak -

0.8.0 release notes

2023-02-09

Added

  • Add options for how audio.to_spect calls dask.bag, to help with memory issues when processing large files #611. Fixes #580.
  • Add ability to run evaluation of models with and without post-processing transforms. This is done by specifying an option post_tfm_kwargs in the [EVAL] or [LEARNCURVE] sections of a .toml configuration file. If the option is not specified, then models are evaluated as they were previously, by converting the predicted label for each time bin to a label for each continuous segment, represented as a string. If the option is specified, then the post-processing is applied to the model predictions before converting to strings. Metrics are computed for outputs with and without post-processing, to be able to compare the two. #621. Fixes #472.
  • vak.core.eval now logs computed evaluation metrics so they can be quickly inspected in the terminal or log files before full analysis #621. Fixes #471.

Changed

  • Rewrite post-processing transforms applied to network outputs as transforms, with functional and class implementations, to make it possible to compose these transforms, and more easily evaluate model performance with and without them #621. Fixes #537.

- Python
Published by NickleDave over 3 years ago

vak -

vak 0.7.0 release notes

vak 0.7.0 is a maintenance release, but it does include some new features and bug fixes. Highlights: - For annotation formats that have one annotation file per annotated file, vak can now recognize when the annotation files are named by removing the annotated file extension (e.g., .wav or .npz) and replacing it with the annotation format extension, e.g. .txt or .csv. (Other ways of relating annotations and annotated files are still valid, e.g. by including the original source audio file in both filenames.) - The transform that normalizes spectrograms is now fit only to the training set; previously no split was specified and in some cases the entire dataset was used, which could potentially reduce the error on the test set because of dataset leakage (the model "knows" about the distribution of the test set because the parameters used to normalize the spectrograms take it into account). For training sets large enough to achieve good performance with current models, there is probably not a big enough difference between their distribution and that of the test set for this to seriously impact evaluation, but we have not tested this extensively. - Several other clean ups, additional unit tests, and minor bug fixes that should not have impacted performance but do make the library more efficient and robust.

Added

  • Add unit tests for csv.has_unlabled #541. Fixes #102.
  • Add unit tests for __main__ #542. Fixes #337.
  • Add validation of labels argument to vak.split.algorithms.brute_force, to prevent conditions where algorithm can fail to converge because of bad input #562. Fixes #288.
  • Add a "Frequently Asked Questions" page to the documentation, and a page to the "Reference" section on file naming conventions #564. Fixes #524 and #424.
  • Add a new way for vak to map annotation files to annotated files when preparing datasets, e.g. for training models. For annotation formats that have one annotation file per annotated file, vak can now recognize when the annotation files are named by removing the annotated file extension (e.g., .wav or .npz) and replacing it with the annotation format extension, e.g. .txt or .csv. (Other ways of relating annotations and annotated files are still valid, e.g. by including the original source audio file in both filenames.) #572. Fixes #563.
  • Have runs from command-line interface log version to logfile #587. Fixes #216.

Changed

  • Rewrite unit tests in tests/test_cli/ to use mocks for vak.core functions #544. Fixes #543.
  • It is now possible to load configuration files and work with them programmatically even if the paths they point to do not exist. The core functions handle validation instead. E.g., the PrepConfig class does not check whether output_dir exist is a directory, but vak.core.prep does. #550. Fixes #459.
  • Refactor and speed up logic for determining whether a dataset with sequence annotations has unlabeled segments that should be assigned a "background" label #559. Fixes #243.
    • Adds a new sub-sub-package, datasets.seq with a validators module, which is where the re-written has_unlabeled function now lives. Replaces the vak.csv module which was not well named.
    • Also adds a has_unlabeled function to vak.annotation that is used by vak.datasets.seq.validators.has_unlabeled; this function handles edge cases outlined in #243.
  • Rename and refactor functions in vak.annotation that map annotations to the files that they annotate, so that the purpose of the functions is clearer, and add clearer error messages with links to documentation about file naming conventions #566. Fixes #525.
  • Revise "autoannotate" tutorial to use .wav audio and .csv annotation files from new release of Bengalese Finch Song Repository, and to suggest that Windows users unpack archives with tar, not other programs such as WinZip #578. Fixes #560 and #576.
  • Change vak.files.find_fname and vak.files.spect.find_audio_fname so they work when spaces are in filename and/or path #594. Fixes #589.

Fixed

  • Fix how vak.core.prep handles labelset parameter. Add pre-condition that raises a ValueError when labelset is None but the .toml config is one of {'train', 'learncurve', 'eval'} #545. Avoids running computationally expensive step of generating and validating spectrograms before crashing when trying to split the dataset using labelset. Also avoids silent failures for datasets that do not require splitting, e.g., an 'eval' set that could contain labels not in the training set. Fixes #468.
  • Fix how cli and core functions that have the csv_path parameter handles it. The parameter points to a dataset .csv generated by vak prep that other core/cli function use: train, learncurve, eval, predict. They now validate that it exists, and if it doesn't, the cli functions politely suggest running vak prep first; the core functions raise a FileNotFoundError. #546. Fixes #469.
  • Fix bug where labelmap_path parameter was ignored by core.train. Change function so that either labelmap_path or labelset must be passed in, both passing in both will raise an error. Also change cli.train to only pass in one of those and set the other to None. #552. Fixes #547.
  • Fix vak.annotation.has_unlabeled to handle the edge case where an annotation file has no annotated segments #583. Fixes #378.
  • Fix StandardizeSpect method fit_df so that it computes parameters for standardization from a specific split of the dataset--the training split, by default--instead of using the entire dataset, which could technically give rise to data leakage #584. Fixes #575.
  • Fix error message in vak.core.eval #589. Fixes #588.

- Python
Published by NickleDave over 3 years ago

vak -

0.4.0 -- 2021-12-29

Added

  • add a CITATION.cff file #407.
  • add an all-contributors table to README, using their bot to adopt the spec. E.g., #395. Fixes #387.
  • add description of command-line interface to reference section of documentation. #417. Fixes #270.
  • add how-to on using an annotation format that's not built in #421. Fixes #397.
  • add how-to on using custom spectrograms #421. Fixes #413.

Changed

  • updated the .toml configuration files in the tutorial to match what was used for TweetyNet paper. #416. Fixes #414.
  • move tutorial into "getting started" section of docs, and revise landing page of docs #419.
  • revise the documentation for the configuration file format. Show valid options for each section by including docstrings from the classes that represents the different sections #428. Fixes #271.

Fixed

  • make further fixes + add unit tests for handling predictions where all timebins are the background "unlabeled" class #409. Fixes bug in remove_short_segments #403. Related to #393 and #386.
  • fix docs so entries appear in navbar #427. Fixes #426.

- Python
Published by NickleDave over 3 years ago

vak -

0.6.0 -- 2022-07-07

Added

  • better document conda install #528. Fixes #527.
  • Add tests for console script, i.e., the command-line interface #533. Fixes #369.

Changed

  • switch from using make to nox for running tasks #532. Fixes #440.
  • Refactor logging so that it can be configured by cli functions when running vak through command-line interface, and by users that are working with the API directly #535.

Fixed

  • Fix bug that prevented creating spectrogram files with non-default keys (e.g. 'spect' instead of the default 's'). Needed to pass keys from spect_params into spect.to_dataframe inside vak.io.dataframe.from_files. #531. Fixes #412.
  • Fix logging so a single message is not logged multiple times. #535. Fixes #258.

- Python
Published by NickleDave almost 4 years ago

vak -

- Python
Published by NickleDave almost 4 years ago

vak -

- Python
Published by NickleDave almost 4 years ago

vak -

- Python
Published by NickleDave about 4 years ago

vak -

- Python
Published by NickleDave over 4 years ago

vak -

- Python
Published by NickleDave over 4 years ago

vak -

- Python
Published by NickleDave over 4 years ago

vak -

- Python
Published by NickleDave about 5 years ago

vak -

- Python
Published by NickleDave about 5 years ago

vak -

- Python
Published by NickleDave about 5 years ago

vak -

- Python
Published by NickleDave about 5 years ago

vak -

- Python
Published by NickleDave over 5 years ago

vak -

- Python
Published by NickleDave over 5 years ago

vak -

- Python
Published by NickleDave over 5 years ago

vak -

- Python
Published by NickleDave almost 6 years ago

vak -

- Python
Published by NickleDave almost 6 years ago

vak -

- Python
Published by NickleDave almost 6 years ago

vak -

- Python
Published by NickleDave over 6 years ago

vak -

- Python
Published by NickleDave over 6 years ago

vak -

- Python
Published by NickleDave over 6 years ago

vak -

- Python
Published by NickleDave over 6 years ago

vak -

- Python
Published by NickleDave over 6 years ago

vak - bullfinches-blathering

- Python
Published by NickleDave over 6 years ago

vak - bullfinches-bettering

- Python
Published by NickleDave over 6 years ago

vak - bullfinches-bellowing

- Python
Published by NickleDave over 6 years ago

vak - sparrows-gathering

Added

  • add helper function to TestLearncurve that multiple unit tests can use to assert all outputs were generated. Now being used to make sure bug fixed in 0.1.0a8 stays fixed.
  • error checking in cli that raises ValueError when cli command is learncurve and the option 'resultsdirmadebymain_script' is already defined in [OUTPUT] section, since running 'learncurve' would overwrite it.
  • dataset subpackage that houses VocalizationDataset and related classes that facilitate creating data sets for training neural networks from heterogeneous data: audio files, files of arrays containing spectrograms, different annotation types, etc.
    • also includes modules for handling each data source
    • e.g. audio.to_spect creates spectrograms from audio files
    • spect.from_files creates a VocalizationDataset from spectrogram files
  • core sub-package that contains / will contain functions that do heavy lifting: learning_curve, train, predict
    • learning_curve is a sub-sub-module that does both train and test of models, instead of having a separate learncurve and summary function (i.e. train and test). Still will confuse some ML/AI people that this "learning curve" has a test data step but whatevs
    • cli sub-package calls / will call these functions and handle any command-line-interface specific logic (e.g. making changes to config.ini files)

Changed

  • change name of vak.cli.make_data to vak.cli.prep
  • structure of config.ini file
    • now specify either audio_format or spect_format in [DATA] section
    • and annot_format for annotations
  • refactor utils sub-package
    • move several functions from data and general into a labels module

Removed

  • remove unused options from command-line interface: --glob, --txt, --dataset
  • skip_files_with_labels_not_in_labelset option
    • now happens whenever labelset is specified; if no labelset is given then no filtering is done
  • summary command-line option, since learncurve now runs trains models and also tests them on separate data set
  • silent_label_gap option, because VocalizationDataset class determines if a label for unlabeled segments between other segments is needed, and if so automatically assigns this a label of 0 when mapping user labels to consecutive integers
    • this way user does not have to think about it
    • and program doesn't have to keep track of a labels_mapping file that saves what user specified

- Python
Published by NickleDave almost 7 years ago

vak -

Fixed

  • Fix how main loop in learncurve re-loads indices for grabbing subsets of training data after generating them, and do so in a way that still allows for re-using subsets from previous runs

- Python
Published by NickleDave about 7 years ago

vak -

Added

  • vak.cli.summary has save_transformed_data parameter and vak.cli passed value from config.data.save_transformed_data as the argument when calling vak.cli.summary

Changed

  • vak.cli.summary only saves transformed train/test data if save_transformed_data is True
  • move a test from tests/unittests/testutils.py into tests/unittests/testutils/test_data.py

Removed

  • vak.cli.summary no longer saves copy of test data in results directory

- Python
Published by NickleDave about 7 years ago

vak -

Added

  • add test for utils.data.getindsfor_dur

Changed

  • learncurve gets indices for all train data subsets before starting training

- Python
Published by NickleDave about 7 years ago

vak -

Fixed

  • add missing 'savetransformeddata' option to Data config parsing

- Python
Published by NickleDave about 7 years ago

vak -

Added

  • Use attrs-based classes to represent sections of config.ini files

Changed

  • rewrite vak.cli so it can deal with state of config.ini files
    • e.g. doesn't throw an error if train_data_path not declared as an option in [TRAIN] when running vak prep (since training data won't exist yet, doesn't make sense to throw an error).

Removed

  • remove code about freq_bins in a couple of places, since the number of frequency bins in spectrograms is now just determined programmatically
    • vak.config.data no longer has freq_bins field in DataConfig namedtuple
    • make_data no longer adds freq_bins option to [DATA] section after making data sets

- Python
Published by NickleDave about 7 years ago

vak -

Changed

  • checkpoints saved in individual directories by learncurve so they are more cleanly segregated, e.g. if user wants to point to a specific checkpoint when calling predict
  • calling vak prep config.ini will run vak.cli.make_data function
    • so to generate a learning curve, the three steps now are: bash vak prep config.ini vak learncurve config.ini vak summary config.ini

Fixed

  • vak.cli.train runs all the way through, passes basic "does not crash" test
  • vak.cli.predict runs all the way through, passes basic "does not crash" test

- Python
Published by NickleDave about 7 years ago