Biapy

Fixes:
- Change ``DATA.PREPROCESS.*.ACTIVATE`` to ``DATA.PREPROCESS.*.ENABLE`` as the rest of the variables in all the files (changed only in config.py by error).
- Separate per_image, full_image and as_3D_stack instance files in different folders.
- Separate instance segmentation metrics when multiple choices are selected. Before full_image and per_image metrics were mixed.
- Simplify inference by setting as default patch/merge reconstruction of the prediction. This implied to remove ``TEST.STATS`` and leave only ``FULL_IMG`` to be optional.
- ``TEST.FULL_IMG`` to ``False`` by default.

Quick patch to fix some issues:
- Move ``sys.exit()`` call to ``main.py`` to prevent errors inside jupyter notebooks
- Fix issue during BMZ export in classification
- Rename ``DATA.PREPROCESSING.*.ACTIVATE`` to ``ENABLE`` as in other variables.
- Remove ``DATA.PREPROCESS.MEDIAN_BLUR.FOOTPRINT`` as it is a Numpy array and it can not be declared through YACS

Quick patch to fix some issues:
- Fix ``FORCE_RGB`` variable usage in classification
- Adapt skimage's ``relabel_sequential()`` to be as the old function we were using so the matching metrics process doesn't get stuck anymore.

General changes
Major
- Separate instance filtering and statistical measurements with ``TEST.POST_PROCESSING.MEASURE_PROPERTIES`` and ``TEST.POST_PROCESSING.MEASURE_PROPERTIES.REMOVE_BY_PROPERTIES``
- Add sphericity (3D), perimeter/surface area (2D/3D) and elongation (2D) calculations using the same formulas as described in [MorphoLibJ](https://imagej.net/plugins/morpholibj)
- Multi-GPU prediction by chunks (Zarr/H5):
* Add versatile axis order
* Fix some overlap errors
- Add data preprocessing options:
* Resize
* Gaussian blur
* Median blur
* Histogram matching
* Contrast Limited Adaptive Histogram Equalization (CLAHE)
* Canny or edge detection (only 2D - grayscale or RGB)
- Change BiaPy into a class so we can call functions individually (e.g. BMZ model exportation)
- Detection:
* Add overlap in detection during multi-GPU prediction by chunks
* Now point coords work in global position
Minor
- Add ``TEST.DET_EXCLUDE_BORDER`` option

Bugs fixed:
- 2D test time augmentation bug with ``MODEL.N_CLASSES`` solved
- Fix bug when ``TEST.BY_CHUNKS`` selected using ``TEST.BY_CHUNKS.INPUT_IMG_AXES_ORDER`` of len 4.
- Avoid dividing with zero during instance stats

General changes
Major
- Fix TTA bug in full image prediction
- Add [Bioimage Model Zoo (BMZ)](https://bioimage.io/#/) as a source to load pretrained models for inference
- Add option to export a model into BMZ format
- Add TorchVision as a source for building models
- Add ``TEST.BY_CHUNKS.INPUT_IMG_AXES_ORDER`` to control the order of the Zarr/H5 input image axes
- Change project structure to be able to call BiaPy through command line
Minor
- Add CODE_OF_CONDUCT.md
- Changed variable default values:
* ``PROBLEM.INSTANCE_SEG.DATA_CHECK_MW`` to ``False``
* ``PROBLEM.DETECTION.DATA_CHECK_MW`` to ``False``
* ``DATA.VAL.SPLIT_TRAIN`` to ``0.1``
* Remove ``TEST.MATCHING_SEGCOMPARE`` not used
- Add [imagecodec](https://pypi.org/project/imagecodecs/) as dependency so all TIFF files are loaded
- Increase timeout in ``TEST.BY_CHUNKS`` setting

Bugs fixed:
- Fix bug using ``TEST.BY_CHUNKS`` when no GPU is used
- Fix bug in cross validation for workflows that do not require GT (e.g. denoising)
- Fix semantic seg issues in multiclass
- Fix bug in image saving when Z axis is less than 5

New functionality added:

General
Major changes
- Add [ResUNet++](https://arxiv.org/pdf/1911.07067.pdf) model
- Add ``TEST.POST_PROCESSING.REMOVE_BY_PROPERTIES``, and its options, to remove instances by the conditions based in each instance properties. This merges ``PROBLEM.INSTANCE_SEG.WATERSHED_CIRCULARITY``, ``PROBLEM.INSTANCE_SEG.DATA_REMOVE_SMALL_OBJ_AFTER`` and ``PROBLEM.INSTANCE_SEG.DATA_REMOVE_SMALL_OBJ_AFTER`` functionalities.
- New options and upgrades to save memory:
* Move normalization to ``load_sample`` function inside the generators if ``DATA.*.IN_MEMORY`` is selected, which allows to have in memory the dataset in its original dtype (usuarlly ``uint8`` or ``uint16``) and not in ``float32``, consuming less memory, at the cost of having to do the normalization per batch.
* Update``TEST.REDUCE_MEMORY`` option to reduce also the dtype of the prediction from ``float32`` to ``float16``
* Add ``TEST.BY_CHUNKS``, and its options, to process large images by chunks: load/save steps work with ``H5`` or ``Zarr`` formats. This option helps to generate model's prediction with overlap/padding with low memory footprint by constructing it patch by patch. It is also prepared to do multi-GPU inference to accelerate the reconstruction process. It can also work loading ``TIF`` images but with ``H5`` and ``Zarr`` only the patches processed are loaded into memory, and nothing else, so you can should scale to TB of data without having memory problems.
* Add ``TEST.BY_CHUNKS.WORKFLOW_PROCESS``, and a few more options related to it, to continue or not the workflow _normal_ steps after the model prediction. With ``TEST.BY_CHUNKS.WORKFLOW_PROCESS.TYPE`` you can tell the worklow to process the predicted image patch by patch or as just one image. By patch option is currently only supported in ``DETECTION`` workflow.
Minor changes
- Delete ``MODEL.KERNEL_INIT``
- ``TRAIN.PATIENCE`` default changed to ``-1``
- Add ``utils/scripts/h5_to_zarr.py`` auxiliary script
- Now ``warmupcosine``learning rate scheduler is done by iterations and not by epochs.
- Update notebooks to work with BiaPy based on Pytorch
Workflows
Instance segmentation
- Add ``TEST.POST_PROCESSING.CLEAR_BORDER`` to remove instances in the border
Denoising
- Change N2V masks to be created always on the fly (saving memory)
Detection
- Remove ``TEST.DET_LOCAL_MAX_COORDS`` option
- Add ``TEST.DET_POINT_CREATION_FUNCTION``, and a few more options related to it, to decide whether to use ``peak_local_max`` or ``blob_log`` (from scikit-image) functions to create the final points from probabilities.
SSL
- Add ``MODEL.MAE_MASK_RATIO`` option
SR
- Add ``3D`` support
- Add notebooks

Bugs fixed:
- Correct bug on 2D UNETR definition
- Fix bug in 2D cross validation
- Minor bugs created when switching from Tensorflow to Pytorch