Moved code to lightning

Updating codebase to make use of pytorch-lightning

• Main train/valid loops are handled by lightning
• Removed device-handling code
• Each model implements its own train/valid/predict steps
• Updated config files for use with lightning
• Using lightning checkpointing and logging callbacks
• Updated DeviceMonitor to be compatible with lightning

doc/install.rst

@@ -171,7 +171,7 @@ In addition to the splits presented in the following table, 10 folds
      - 6600
      - 1800
      - 2800
-   * - TBX11K-SIMPLIFIED_
+   * - TBX11K_SIMPLIFIED_
      - [TBX11K-SIMPLIFIED-2020]_
      - 512 x 512
      - 11'200
@@ -180,7 +180,7 @@ In addition to the splits presented in the following table, 10 folds
      - 2800
 
 
-.. _ptbench.setup.datasets.tb+signs:
+.. _ptbench.setup.datasets.tbmultilabel+signs:
 
 Tuberculosis + radiological findings dataset
 ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~