Making use of LightningDataModule and simplification of data loading

This merge request adds LightningDataModule to better organize the code and make better use of lightning's features. This centralizes common tasks such as DataLoader creation and application of transforms into a base class to be inherited from.

Data loading was also simplified by removing custom Sample classes and maker functions, and the addition of RuntimeDataset and CachedDataset.

Remaining tasks:

• (@dcarron) Create a common/default DataModule for the shenzhen dataset that takes protocols and transforms as parameters to avoid copying code for each protocol configuration
• (@dcarron) Add typehints to ShenzenDataModule
• (@dcarron) Investigate issue where training a new model with ElasticDeformation as a transform converges more slowly if the data is not cached.
• (@andre.anjos) Update documentation on ShenzenDataModule
• (@biosignal) Update all datasets, using Shenzhen as a reference
  • (@mdelitroz) Montgomery
  • (@mdelitroz) Hivtb
  • (@andre.anjos) Indian
  • (@andre.anjos) Padchest
  • (@mdelitroz) Tbpoc
  • (@andre.anjos) tbx11_simplified -> renamed as tbx11k, protocol v1 (uses original dataset organisation)
  • (@andre.anjos) tbx11_simplified_v2 -> renamed as tbx11k, protocol v2 (uses original dataset organisation)
  • (@andre.anjos) mc_ch -> renamed as montgomery-shenzhen
  • (@andre.anjos) mc_ch_in -> renamed as montgomery-shenzhen-indian
  • (@andre.anjos) mc_ch_in_11k -> renamed as montgomery-shenzhen-indian-tbx11k-v1
  • (@andre.anjos) mc_ch_in_11k_v2 -> renamed as montgomery-shenzhen-indian-tbx11k-v2
  • (@andre.anjos) mc_ch_in_pc -> renamed as montgomery-shenzhen-indian-padchest
  • (@andre.anjos) nih_cxr14_re -> renamed as nih-cxr14 (n.b.: multi-class dataset, radiological findings)
  • (@andre.anjos) nih_cxr14_re_pc -> renamed as nih-cxr14-padchest
• (@dcarron) Update models
• (@dcarron) Update evaluation scripts
• (@dcarron) Update support for extra_validation datasets
• (@biosignal) Update full documentation
• (@biosignal) Update unit tests

Addresses the following issues:

• Closes #14 (closed)
• Closes #18 (closed)
• Closes #19 (closed)
• Closes #21 (closed)
• Closes #29 (closed)

src/ptbench/utils/checkpointer.py

 import logging
 import os
 
+import typing
 logger = logging.getLogger(__name__)
 
 
-def get_checkpoint(output_folder, resume_from):
+def get_checkpoint(output_folder: str, resume_from: typing.Literal["last", "best"] | str | None) -> str | None : 
     """Gets a checkpoint file.
 
     Can return the best or last checkpoint, or a checkpoint at a specific path.
     Ensures the checkpoint exists, raising an error if it is not the case.
 
+    If resume_from is None, checks the output directory if a checkpoint already exists and returns it.
+    If no checkpoint is found, returns None.
+
     Parameters
     ----------
 
-    output_folder : :py:class:`str`
+    output_folder:
         Directory in which checkpoints are stored.
 
-    resume_from : :py:class:`str`
+    resume_from:
         Which model to get. Can be one of "best", "last", or a path to a checkpoint.
+        If None, gets the last checkpoint if it exists, otherwise returns None
 
     Returns
     -------
 
-    checkpoint_file : :py:class:`str`
-        The requested model.
+    checkpoint_file:
+        Path to the requested checkpoint or None.
     """
     last_checkpoint_path = os.path.join(output_folder, "model_final_epoch.ckpt")
     best_checkpoint_path = os.path.join(
@@ -49,7 +54,11 @@ def get_checkpoint(output_folder, resume_from):
             )
 
     elif resume_from is None:
-        checkpoint_file = None
+        if os.path.isfile(last_checkpoint_path):
+            checkpoint_file = last_checkpoint_path
+            logger.info(f"Found existing checkpoint {last_checkpoint_path}. Loading.")
+        else:
+            return None
 
     else:
         if os.path.isfile(resume_from):