Tags give the ability to mark specific points in history as being important
- Sort by
- Name
- Oldest updated
- Last updated
-
v3.0.0Release v3.0.0
-
!73 Merged bob.bio: Moved
bob.bio.base,bob.bio.face,bob.bio.gmm, andbob.bio.videoto this packae. They were respectively renamed to:bob.bio.base_legacy,bob.bio.face_legacy,bob.bio.gmm_legacy,bob.bio.video_legacyMissing to port the docs. Fixes #34 - !74 Added spear as part of the temporary legacy: Addressing this issue https://gitlab.idiap.ch/bob/bob.bio.spear/-/issues
- !76 Cleaning up dependencies
- !75 WIP: Port to dask pipelines
- !77 Remove deprecated code
- !80 [vanilla-pad] Improve the dask client option and delayed annotations
- !78 Dask pipelines Improvements: This MR improves the dask pipelines port.
-
!81 [dask] Make vanilla-pad work properlly with dask: In this MR, I'm. 1. Wrapping the pipeline with DaskWrapper, because it wasn't. I think that's why things were not working for you with SGE @ydayer.
vanilla-padwas creating SGE jobs AND running everything locally. 2. Added the options "--dask-partition-size" and "--dask-n-workers", so the user has some freedom to set these parameters if the heuristics in place are unpleasant. I'll merge this one right away because of the workshop. Feel free to open issues if any - !79 new documentation incl. vanilla-pad: The goal is to update the documentation of bob.pad.base with the latest changes. ping @amohammadi @tiago.pereira
-
!82 New database interface for PAD: Hi @amohammadi, @ydayer Follow the proposition for a new DB interface for PAD. It follows the same guide lines used in
bob.bio.base. Follow below the features implemented: 1. Uses CSV files instead of LSTs; with that, you can ship metadata. However, it uses the same file structure as before, so no stress in porting stuff. 2. The CSVPADDataset can transparently read the current LST files we have (I've created a sample loader that handles that). 3. The CSVPADDataset is able to read either files inside of a file structure or files inside of a tarball. Follow an example on how to use it, by reading from a file structure and from a tarballpython def run(path): dataset = CSVPADDataset(path, "protocol1") bob/bob.pad.base# Train assert len(dataset.fit_samples()) == 5 bob/bob.pad.base# 2 out of 5 are bonafides assert sum([s.is_bonafide for s in dataset.fit_samples()]) == 2 bob/bob.pad.base# DEV assert len(dataset.predict_samples()) == 5 bob/bob.pad.base# 2 out of 5 are bonafides assert sum([s.is_bonafide for s in dataset.predict_samples()]) == 2 bob/bob.pad.base# EVAL assert len(dataset.predict_samples(group="eval")) == 7 bob/bob.pad.base# 3 out of 5 are bonafides assert sum([s.is_bonafide for s in dataset.predict_samples(group="eval")]) == 3 csv_example_dir = os.path.realpath( bob.io.base.test_utils.datafile(".", __name__, "data/csv_dataset") ) csv_example_tarball = os.path.realpath( bob.io.base.test_utils.datafile(".", __name__, "data/csv_dataset.tar.gz") ) run(csv_example_dir) run(csv_example_tarball) - !84 Remove vulnerability analysis commands: Moved to bob.bio.base Fixes #27
-
!85 Allow to specify the pipeline decision function in vanilla_pad script: This changes makes it easier to use the
vanilla_padscript with classifiers that have different names for their decision functions (eg "predict_proba", "predict", etc...) This also allows passing "transform" as a decision_function in case the pipeline does not contain a classifier.
-
!73 Merged bob.bio: Moved
-
v2.3.2b0 First beta [skip-ci]
-
v2.3.0Release v2.3.0
- !65 Separate semilogx and TPR options in ROC plots: Depends on bob.measure!98
- !66 Fix the wrong total number reported in metrics: Fixes bob.measure#61
- !69 Small fixes
- !68 Add a GMM Algorithm (moved from bob.pad.voice)
- !70 Improve the metrics command with AUC and relaxed threshold criteria
-
v2.2.0Release v2.2.0
- !54 Use the GridSubplot base class for epsc: Depends on bob.measure!89
- !55 Use the version of scikit-learn that we use for testing:
- !56 Use the builtin method for converting frame containers to arrays:
- !57 Correcting bug when using split_training_data_by_client flag in extractor
-
!53 Cross database testing evaluation: Adds a new command
bob pad crossto evaluate PAD systems in cross database settings - !58 Fixes #8 Algorithm.read_toscore_object should not exist
- !59 fix for wrong Axis label with -nG option: fix for wrong Axis label with -nG option, fixes #28
- !60 Correct apcer calculation
- !61 Bpcer threshold criteria: Added criteria for threshold selection based on desired BPCER criteria
- !62 Add a new one class GMM based on bob's GMMs
-
v2.1.0Release v2.1.0
- Significant changes:
- Added new plotting and evaluation scripts. Refer to docs.
- Detailed Changes:
- !52 Change assert to assert_click_runner_result
- !50 Add new classification algorithms: As mentioned here !33 here is the new branch
- !51 Fix broken commands cref bob.extension!86
- !48 Various fix: Requires bob.measure!82 Similar to bob.measure!82 for PAD
- !45 Allow PAD filelist database to be used in vulnerability experiments
- !47 Remove bob vuln metrics and evaluate commands: since they were not well defined and we do not know what should be in there. rename --hlines-at to --fnmr in bob vuln roc,det commands small nit-pick fixes overall
- !43 Finalization of plots: Fixes #22. Requires merge bob.measure!65. Requires bob.measure!67
- !46 Add a command for multi protocol (N-fold cross validation) analysis: Depends on bob.measure!79
- !44 Remove the grid_search.py entrypoint: Fixes #23
- !41 Set of click commands for pad: Provide commands: bob pad metrics bob pad epc bob pad epsc bob pad gen
- !42 Set of click commands for pad: Provide commands: bob pad metrics bob pad epc bob pad epsc bob pad gen
- added MLP and LDA classifiers for PAD
-
v2.0.0Release v2.0.0
- Migrate to conda based CI
- Added --allow-missing-files option
- Improved documentation
- Moved from bob.pad.face SVM (bob implementation), one class GMM (scikit-learn) and logistic regression (scikit-learn) algorithms
- Cleaned up and improved code. Added tests.
- Replace the old PAD ISO metrics class with a script
- Added clients option to FileListDB driver
- Avoids feature blow-up when std==0.
- Added predictions algorithm and padfile to label.