Ctlearn

Major Features
- Replaced `DataLoader`, `DataProcessor`, and `ImageMapper` with `DL1DataReader` from the `DL1-Data-Handler` package (115, 82, 46, 73).
- Greatly revised configuration format to use DL1DH parameter names and inputs and simplify all sections.

Minor Improvements
- Simplified `input_fn` in `run_model` to remove unnecessary required parameters (41).
- Added option to list data files directly in configuration file (40).
- Added explicit dictionary of label names to list of class names to configuration file.
- Added `load_only` mode in `run_model` to load the data and print info without running a model.
- Simplified `predict` mode in `run_model` to iterate through the data only once.

Bug Fixes and Other Changes
- Added kludge when loading data to manually convert unsigned dtypes to the next-higher signed dtype, as TensorFlow cannot automatically perform this conversion.
- Removed scripts specific to processing and image mapping (`plot_camera_image` and `visualize_bounding_boxes`).
- Removed scripts made obsolete by `load_only` mode (`print_dataset_metadata` and `print_run_metadata`).
- Moved `test_image_mapper` notebook to DL1DH.
- Replaced direct dependencies on Astropy, OpenCV, Pillow, PyTables, and SciPy with a dependency on DL1-Data-Handler installed using pip.

Major Features

Minor Improvements
- Upgraded Python version to 3.7.3.
- Upgraded TensorFlow version to 1.13.1.

Bug Fixes and Other Changes
- Fixed typo in image mapper.

Major Features
- Added FACT, H.E.S.S.-I, H.E.S.S.-II, and MAGIC cameras to `ImageMapper`.
- Added bilinear interpolation, bicubic interpolation, nearest neighbor interpolation, rebinning, image shifting, and axial addressing image mapping methods in `ImageMapper`.
- Added support for running models using data of multiple telescope types.
- Added `use_peak_times` data loading option to load peak arrival times from data files.

Minor Improvements
- Added `auto_configuration.py` script to automatically change the paths in benchmark configuration files.
- Added argument in `run_multiple_configurations.py` to resume from a particular run.
- Added `summarize_results.py` to summarize the results of a set of runs.
- Rationalized the metadata variables returned by `DataLoader`.
- Added `test_image_mapper.ipynb` for testing the image mapping methods of `ImageMapper`.
- Changed telescope names for compatibility with [ctapipe](https://github.com/cta-observatory/ctapipe) camera names.
- Refactored `ImageMapper` to implement all image mapping methods as matrix operations, so that more expensive calculations are performed only during initialization.

Bug Fixes and Other Changes
- Fixed `DivisionByZeroError` in `apply_cuts` during `HDF5DataLoader` initialization.
- Renamed internal variables in and generally cleaned up `DataLoader`.
- Refactored `DataLoader._load_metadata()` into smaller functions for clarity and efficiency.
- Fixed incorrect logging of array examples by class.
- Changed model loading to use included CTLearn models by default.
- Added contributing guidelines.
- Made `run_model.py` append the CTLearn version number to config files.
- Updated TensorFlow version to v1.12.
- Added benchmark configuration files for CTLearn v0.3.0.
- Removed deprecated models.

Major Features
- User-defined TensorFlow classification models with custom configuration parameters can now be imported, in addition to the Single Telescope, CNN-RNN, and Variable Input Network models provided with CTLearn.
- Image mapping added for all CTA telescope types as well as VERITAS.
- Data loading, data processing, and image mapping have been refactored into separate classes with methods to load HDF5 files, preprocess generic IACT data, and map telescope data to square images. Each class is defined in a separate module.
- Configuration now uses YAML instead of INI format, allowing lists and dictionaries to be configured cleanly.

Minor Improvements
- Benchmark configuration files and results have been produced using Single Telescope and CNN-RNN models for all CTA telescope types.
- Package installation now uses a conda environment file to resolve dependencies, providing clean and light installation and removal.
- Training and prediction now handled as two modes within `run_model`.
- Updated `run_multiple_configurations.py` to allow configuration parameter combinations to be grouped together.
- Image mapping is now configurable with options for padding and hexagonal conversion algorithm.
- Prediction output is now NumPy-compatible and includes the run number, event number, and telescope ID (if applicable) of each example.

Bug Fixes and Other Changes
- Renamed project to CTLearn from CTALearn.
- Added BSD 3-Clause license.
- TensorFlow version updated to v1.9.0.
- Clarified telescope sorting options.
- Fixed errors in and otherwise updated supplementary scripts.
- Moved unsupported models to `models/deprecated` and will be removed in the next release.
- Removed `plot_gpu_util.py`.
- Added workaround to handle overflow error in tel_id parameter of ImageExtractor HDF5 file format.
- Removed dependency on TensorFlow-Slim.

This release updates the requirements to provide support for OSX.

This release includes three main improvements. First, the TensorFlow version has been updated to the most recent version v1.7. Second, the CNN-RNN model has been updated and improved and can be used for classification. Third, a script has been added for prediction so that trained models can now be applied to test data. In addition, several supplementary scripts are provided to plot ROC curves using the predicted classification values.