Move load_state_dict into LitModular

[dxoigmn]

What does this PR do?

The mechanism for wrapping a module in mart.nn.load_state_dict makes YAML configuration more verbose and is unnecessary if that logic is moved into LitModular. Ideally, however, we would support custom syntax within the YAML configuration for things that do not support weight loading. For example:

model:
  _target_: torchvision.models.detection.fasterrcnn_resnet50_fpn
  _load_state_dict_: path/to/weights.pt

Type of change

Please check all relevant options.

• [ ] Improvement (non-breaking)
• [ ] Bug fix (non-breaking)
• [ ] New feature (non-breaking)
• [ ] Breaking change (fix or feature that would cause existing functionality to not work as expected)
• [ ] This change requires a documentation update

Testing

Please describe the tests that you ran to verify your changes. Consider listing any relevant details of your test configuration.

• [ ] Test A
• [ ] Test B

Before submitting

• [ ] The title is self-explanatory and the description concisely explains the PR
• [ ] My PR does only one thing, instead of bundling different changes together
• [ ] I list all the breaking changes introduced by this pull request
• [ ] I have commented my code
• [ ] I have added tests that prove my fix is effective or that my feature works
• [ ] New and existing unit tests pass locally with my changes
• [ ] I have run pre-commit hooks with pre-commit run -a command without errors

Did you have fun?

Make sure you had fun coding 🙃

[mzweilin]

Usage example:

python -m mart \
experiment=ArmoryCarlaOverObjDet_TorchvisionFasterRCNN \
fit=false \
+trainer.limit_test_batches=1 \
+model.load_state_dict.losses_and_detections.model=/home/weilinxu/coder/GARD-with-MART/oscar/model_zoo/carla_rgb_weights_eval6.pt