Fixed bugs:
- Fix feature while looping by moving feof to after read_image.
- Fix issue #2 use hashed string for log filename and result filename to avoid file names getting too long.
New features:
- Add SsimFeatureExtractor and MsSsimFeatureExtractor with intermediate features (luminence, contrast, structure).
New features:
- Refactor feature code to expose ssim/ms-ssim, speed up ssim/ms-ssim.
New features:
- Add base class NorefFeatureExtractor for any feature extractor that do not use a reference video.
- Add MomentNorefFeatureExtractor subclassing NorefFeatureExtractor as an example implementation.
Fixed bugs:
- Fix a series of numerical issues in VMAF features, increment VmafFeatureExtractor version number.
- Retrain VmafQualityRunner after feature update, increment version number.
New features:
- Add LocalExplainer class.
- Add show_local_explanation option to run_vmaf script.
New features:
- Add DisYUVRawVideoExtractor and related classes.
- Add NeuralNetworkTrainTestModel base class that integrates TensorFlow.
- Add example class ToddNoiseClassifierTrainTestModel.
New features:
- Update VmafFeatureExtractor to 0.2.2b with scaled ADM features exposed (adm_scale0-3).
New features:
- Generalize read_dataset to allow specifying width, height and resampling method on which to calculate quality.
- Add bicubic to SUPPORTED_RESAMPLING_TYPES for Asset.
- Update Asset rule with resampling_type in str to avoid duplicates in data store.
Fixed bugs:
- Move VmafQualityRunnerWithLocalExplainer to quality_runner_adhoc to resolve multiple instances of VMAF found when calling QualityRunner.find_subclass.
New features:
- Add custom_clip_0to1 to TrainTestModel.
New features:
- Update wrapper/vmafossexec: 1) it now takes pkl model file as input, so that slopes/intercepts are no longer hard-coded; 2) it now takes multiple YUV input formats; 3) add flag to enable/disable VMAF score clipping at 0/100; 4) allow customly running PSNR/SSIM/MS-SSIM; 5) allow customly outputing XML/JSON
- Add SSIM/MS-SSIM option in run_testing.
New features:
- Update command lines run_vmaf, run_psnr, run_vmaf_in_batch, run_cleaning_cache, run_vmaf_training and run_testing.
Fixed bugs:
- Make ptools work under Mac OS.
- Update SklearnRandomForestTrainTestModel test with sklearn 0.18.
New features:
- Generalize dataset format to allow per-content YUV format.
Fixed bugs:
- Issue #29: Make ptools build under Fedora.
New features:
- Add support for docker usage (#30).
New features:
- Add Xcode project support.
- Add more pooling options (median, percx) to CLIs.
Fixed bugs:
- Issue #36: SSIM and MS-SSIM sometimes get negative values.
New features:
- Add quality runners for each individual VMAF elementary metrics.
New features:
- Add DatasetReader and subclasses; add SubjectiveModel and subclasses.
New features:
- Add options to use custom subjective models in run_vmaf_training and run_testing commands.
New features:
- Add implementation of KFLK - quality metric evaluation method based on AUC. Refer to: L. Krasula, K. Fliegel, P. Le Callet, M.Klima, "On the accuracy of objective image and video quality models: New methodology for performance evaluation", QoMEX 2016.
New features:
- Add Travis continuous integration.
Fixed bug:
- Fix a bug in DatasetReader.to_aggregated_dataset_file.
New features:
- Add enable_transform_score option to VmafQualityRunner, VmafossExecQualityRunner.
Fixed bug:
- Fix vmafossexec memory leakage.