Zamba Versions Save

Bug fixes for docs

• Adds experimental image support (PR #314)
• Clarifies installation instructions for Linux and Windows operating systems (PR #299)

• Pin Pydantic to less than v2.0 (PR #277)

• Code updates for PyTorch Lightning v2.0.0 (PR #266, PR #272)
• Switch to pyproject.toml-based build and other requirement updates (PR #254, PR #255, PR #260, PR #262, PR #268)

Model release

• Adds a depth estimation module for predicting the distance between animals and the camera (PR #247). This model comes from one of the winning solutions in the Deep Chimpact: Depth Estimation for Wildlife Conservation machine learning challenge hosted by DrivenData.

• Do not cache videos if the VIDEO_CACHE_DIR environment variable is an empty string or zero (PR #245)

• Fixes Lightning deprecation of DDPPlugin (PR #244)

• Adds a page to the docs summarizing the performance of the African species classification model on a holdout set (PR #235)

• Turn off showing local variables in Typer's exception and error handling (PR #237)
• Fixes bug where the column order was incorrect for training models when the provided labels are a subset of the model's default labels (PR #236)

Model releases and new features

• The default time_distributed model (African species classification) has been retrained on over 250,000 videos. This 16x increase in training data significantly improves accuracy. This new version replaces the previous one. (PR #226, PR #232)
• A new default model option is added: blank_nonblank. This model only does blank detection. This binary model can be trained and finetuned in the same way as the species classification models. This model was trained on both African and European data, totaling over 263,000 training videos. (PR #228)
• Detect if a user is training in a binary model and preprocess the labels accordingly (PR #215)

Bug fixes and improvements

• Add a validator to ensure that using a model’s default labels is only possible when the species in the provided labels file are a subset of those (PR #229)
• Refactor the logic in instantiate_model for clarity (PR #229)
• Use pqdm to check for missing files in parallel (PR #224)
• Set model_name based on the provided checkpoint so that user-trained models use the appropriate video loader config (PR #221)
• Leave data_dir as a relative path (PR #219)
• Ensure hparams yaml files get included in the source distribution (PR #210)
• Hold back setuptools so mkdocstrings works (PR #207)
• Factor out get_cached_array_path (PR #202)