WildlifeDatasets - v1.0.6

New functionality

• Added support for the AnimalCLEF2025 re-identification competition.

• Added support for a new version of the WildlifeReID-10k dataset. This included adding timestamps to BirdIndividualID, CowDataset, Giraffes and SeaStarReID2023 datasets.

• Two new datasets were added: MultiCamCows2024 and PrimFace.

• SeaTurtleID2022 allows loading images of whole turtles and flippers now.

• Internal changes, making it easier to work with the package as a developer.

  • Function prepare_data is much more flexible, enabling additional outputs such as splits.
  • Added TimeProportionOpenSetSplit.
  • Many other minor changes.

Biosphere - Terrestrial Wildlife - Jupyter Notebook
Published by sadda 13 days ago

WildlifeDatasets - v1.0.5

New functionality

• Six new datasets were added: AmvrakikosTurtles, ReunionTurtles, SouthernProvinceTurtles, ZakynthosTurtles (sea turtles), ELPephants (elephants) and Chicks4FreeID (chickens).
• The WildlifeDataset (formerly DatasetFactory) class was restructed and multiple methods were added from wildlife-tools. This brings the benefits of:
  • Simple way of adding datasets in other formats - example for the parquet format.
  • Easier access to images via dataset[0] or automatically loading cropped images via instantiating dataset(root, img_load='bbox').
  • Significantly improved readability.
• We added links to original publications whenever we were able to find them.

Biosphere - Terrestrial Wildlife - Jupyter Notebook
Published by sadda 6 months ago

WildlifeDatasets - v1.0.4

WildlifeReID-10k

• We released a new dataset WildlifeReID-10k depicting 214k images of 10k individuals.
• It is a collection of 30 existing re-identification datasets with permissible licenses.
• We incorporated default splits, retrained MegaDescriptor and included baseline performance.
• All scripts to create and analyze WildlifeReID-10k are publicly available.
• This dataset can now be accessed as datasets.WildlifeReID10k.

New functionality

• Added the newly released testing set for BelugaID. This dataset can now be accessed as datasets.BelugaIDv2.
• Updated links for several datasets hosted at LILA BC.
• To evaluate WildlifeReID-10k, we included new metrics metrics.BAKS and metrics.BAUS.
• To evaluate the difference between the random and similarity-aware splits, we added method resplit_by_features into splits.BalancedSplit.

Biosphere - Terrestrial Wildlife - Jupyter Notebook
Published by sadda 11 months ago

WildlifeDatasets - v1.0.3

New functionality

• Three new datasets were added: CatIndividualImages (cats), CowDataset (cows) and DogFaceNet (dogs).
• The license file is shown upon download.

Other changes

• Added orientation (left, right, ...) to SeaTurtleID2022.
• Fixed two segmentations in NDD20 which may have caused problems during loading.
• Metadata including licenses and citations were updated or corrected in some cases.

Biosphere - Terrestrial Wildlife - Jupyter Notebook
Published by sadda 12 months ago

WildlifeDatasets - v1.0.2

New functionality

• Three new datasets were added: MPDD (dogs), PolarBearVidID (polar bears) and SeaStarReID2023 (sea stars).
• Labels were fixed for Cows2021 and FriesianCattle2015. These classes appear now as Cows2021v2 and FriesianCattle2015v2 to keep backward compability. A full list of changes is in documentation.
• Visual overhaul including new logos.

Breaking functionality

• Splits were removed from the dataframes. They may be added manually.

Other changes

• SeaTurtleID was updated by SeaTurtleID2022.
• File names of images must contain only ASCII characters. Some files in IPanda50 were renamed while keeping backward compability.
• Some functions were refactored and plot_grid was updated.

Biosphere - Terrestrial Wildlife - Jupyter Notebook
Published by sadda about 1 year ago

WildlifeDatasets - v1.0.0

Initial release

We are happy to introduce the first release of the wildlife-datasets library. Currently, the library can process 31 wildlife re-identification datasets. Its main feature is an interface for downloading and extracting datasets and converting them into a unified format. For full functionality see documentation.

Biosphere - Terrestrial Wildlife - Jupyter Notebook
Published by sadda about 1 year ago