Slideflow

- Enables extracting tiles at downsample/magnification level without resizing; use by setting tile_um equal to a string of format "[int/float]x", such as "10x", "40x", "2.5x"
- New `Dataset.img_format` property which verifies all tfrecords have the same image format, returning the image format
- Datasets will raise `ValueError` if mismatched image formats are found in tfrecords
- Model training now saves `img_format` property in `params.json`
- Slide-level prediction (via heatmaps) now extracts tiles using the same image format (PNG or JPG) as the trained model
- Speeds up test suite by switching to tile_px=76 and tile_um=1208
- Slides will log an error if there is no matching downsample level at that layer
- Fixes edge case where Torch TFRecord reading was skipping TFRecords with fewer records than the number of shards/workers
- Unified sf.io.detect_tfrecord_format() between backends; no longer imports torch/tensorflow
- The first argument of sf.io.detect_tfrecord_format() now returns a list of features, rather than a dictionary
- Enables `include_top=True|False` with PyTorch backend
- Improves model compatibility with PyTorch backend
- Fixes tile extraction PDF bug (error with displaying log(blur_burden))
- Neptune logging fix

- Fixes bug where only one tile per tfrecord was included in mosaic report
- Fixes bug when loading SlideMap from cache
- Fixes normalized images always saved as JPG during tile extraction, even if img_format = PNG
- Fixes neptune logging during evaluation
- Fixes TypeError when training with 3+ outcomes (due to error in sf.Dataset)
- Fixes pandas dtype error for CLAM submodule when slide names are integers
- Fixes DatasetFeatures bug if categorical outcomes are integers
- Fixes bug where IndexError is raised when using filters with mosaic map, or SlideMap.filter()
- Fixes 131
- Sets progress bars to ncols=80
- Adds error handling if Mosaic is created with no tfrecords
- Improves error handling during slide loading (e.g. missing thumbnails)
- DatasetFeatures.normalizer is now an instance of slideflow.StainNormalizer rather than a string and is instanced from hp.get_normalizer()
- Documentation updates: mosaic / layer activations
- stats.py docstring updates

- Fixes test.py, now respects logging level
- Fixes stats.predict_from_layer bug
- Fixes bug in filter_blank where patients with outcome of 0 were being excluded when using linear outcomes
- Fixes errors if slide ID is integer (annotations files now read in str format into pandas DataFrame, rather than auto-detecting dtype)
- Fixes bug where training augmentation strategy set in ModelParams was incorrectly ignored in PyTorch backend (previously forced to always True)
- Fixes 136
- Fixes 134
- Fixes 132
- Addresses 133
- Sets num_parallel_reads=1 and num_workers=1 when calculating activations for DatasetFeatures to ensure records from TFRecord files are correctly ordered
- Changes default augmentation to False when calling sf.io.interleave() or sf.Dataset.torch() or tensorflow()
- Condensed dockerfiles
- Updated DOI (v1.0.4)

- Automatic num_threads for tile extraction based on CPU core count
- Fixes heatmap() batch_size argument (previously ignored)
- Fixes dataset error handling for missing tfrecords
- Fixed Dataset.tfrecord_report()
- Removes previously deprecated vmtouch buffer
- Fixes TMA tile extraction
- Updated QuPath ROI instructions (legacy compatibility)
- Removed Dataset.slide_report() (just do extract_tiles(... dry_run=True)
- Updated sample_actions.py
- Reports split ID when loading a validation split
- TestConfigurator -> TestConfig
- slideflow.statistics -> slideflow.stats

_Doc updates:_
- New "Installation" section
- "Switching backends" section
- Updated "Troubleshooting" section
- Updated wording for what differentiates tutorials 1 & 2
- New tutorial 3 - evaluation & heatmaps
- Doc source cleanup - removed unused images
- Various minor updates
- Collapsed navigation for docs
- Updated github links
- Purple color update
- removed example from bash
- code example improvements

- Fixes bug where model was not saved if val_strategy is None (PyTorch backend)
- Fixes erroneous divide by zero warning with np.log when calculating blur burden
- Fixes bug with Features and real-time normalization (PyTorch)
- Fixes FileNotFoundError when saving a mosaic to the current working directory

- Fixes incorrect requirements.txt
- Test script improvements, setup.py
- Removes gitpython from install_requires, adds click
- TF/PyTorch import fixes, git fix
- Skips CLAM testing if torch not installed
- Adds ubuntu pixman==0.38 repair
- Adds Tensorflow dockerfile & Torch dockerfile
- Adds more testing CLI options to test.py script
- Moves tfrecord2idx to sf.util so it does not import pytorch
- Builds libvips from source with tensorflow dockerfile
- CLAM submodule fixes
- Neptune logging fixes
- Fixes pytorch early stopping bug
- numpy must be <1.21