Implement Espirit, make some transforms nn.Modules, add new transforms

[georgeyiasemis]

• Implements Espirit calibration sensitivity map estimation and methods to calculate maximum eigenvalue numerically (e.g. powermethod)
• Some transforms are now nn.Modules and can be implemented batch-wise
• MRI transforms split to pre-transforms and post-transforms. Plan is to call pre-transforms before collation and post-transforms after collation on device [not implemented yet, functionality now is as it was].
• Adding augmentation transforms: RandomFlip and RandomRotation:
  • They work by backprojecting the k-space to the image domain, transforming it, and then projecting back to k-space domain.

[codecov[bot]]

Codecov Report

Base: 83.55% // Head: 83.74% // Increases project coverage by +0.19% :tada:

Coverage data is based on head (66cef0a) compared to base (5bda5c5). Patch coverage: 89.40% of modified lines in pull request are covered.

Additional details and impacted files

```diff @@ Coverage Diff @@ ## main #232 +/- ## ========================================== + Coverage 83.55% 83.74% +0.19% ========================================== Files 88 91 +3 Lines 6001 6289 +288 ========================================== + Hits 5014 5267 +253 - Misses 987 1022 +35 ``` | [Impacted Files](https://codecov.io/gh/NKI-AI/direct/pull/232?src=pr&el=tree&utm_medium=referral&utm_source=github&utm_content=comment&utm_campaign=pr+comments&utm_term=NKI-AI) | Coverage Δ | | |---|---|---| | [direct/algorithms/optimization.py](https://codecov.io/gh/NKI-AI/direct/pull/232?src=pr&el=tree&utm_medium=referral&utm_source=github&utm_content=comment&utm_campaign=pr+comments&utm_term=NKI-AI#diff-ZGlyZWN0L2FsZ29yaXRobXMvb3B0aW1pemF0aW9uLnB5) | `73.46% <73.46%> (ø)` | | | [direct/data/mri\_transforms.py](https://codecov.io/gh/NKI-AI/direct/pull/232?src=pr&el=tree&utm_medium=referral&utm_source=github&utm_content=comment&utm_campaign=pr+comments&utm_term=NKI-AI#diff-ZGlyZWN0L2RhdGEvbXJpX3RyYW5zZm9ybXMucHk=) | `92.56% <86.09%> (-4.45%)` | :arrow_down: | | [direct/algorithms/\_\_init\_\_.py](https://codecov.io/gh/NKI-AI/direct/pull/232?src=pr&el=tree&utm_medium=referral&utm_source=github&utm_content=comment&utm_campaign=pr+comments&utm_term=NKI-AI#diff-ZGlyZWN0L2FsZ29yaXRobXMvX19pbml0X18ucHk=) | `100.00% <100.00%> (ø)` | | | [direct/algorithms/mri.py](https://codecov.io/gh/NKI-AI/direct/pull/232?src=pr&el=tree&utm_medium=referral&utm_source=github&utm_content=comment&utm_campaign=pr+comments&utm_term=NKI-AI#diff-ZGlyZWN0L2FsZ29yaXRobXMvbXJpLnB5) | `100.00% <100.00%> (ø)` | | | [direct/data/datasets\_config.py](https://codecov.io/gh/NKI-AI/direct/pull/232?src=pr&el=tree&utm_medium=referral&utm_source=github&utm_content=comment&utm_campaign=pr+comments&utm_term=NKI-AI#diff-ZGlyZWN0L2RhdGEvZGF0YXNldHNfY29uZmlnLnB5) | `100.00% <100.00%> (ø)` | | | [direct/data/transforms.py](https://codecov.io/gh/NKI-AI/direct/pull/232?src=pr&el=tree&utm_medium=referral&utm_source=github&utm_content=comment&utm_campaign=pr+comments&utm_term=NKI-AI#diff-ZGlyZWN0L2RhdGEvdHJhbnNmb3Jtcy5weQ==) | `96.47% <100.00%> (+0.16%)` | :arrow_up: | | [direct/train.py](https://codecov.io/gh/NKI-AI/direct/pull/232?src=pr&el=tree&utm_medium=referral&utm_source=github&utm_content=comment&utm_campaign=pr+comments&utm_term=NKI-AI#diff-ZGlyZWN0L3RyYWluLnB5) | `56.93% <100.00%> (ø)` | | | [direct/types.py](https://codecov.io/gh/NKI-AI/direct/pull/232?src=pr&el=tree&utm_medium=referral&utm_source=github&utm_content=comment&utm_campaign=pr+comments&utm_term=NKI-AI#diff-ZGlyZWN0L3R5cGVzLnB5) | `84.37% <100.00%> (+6.59%)` | :arrow_up: | | [direct/utils/\_\_init\_\_.py](https://codecov.io/gh/NKI-AI/direct/pull/232?src=pr&el=tree&utm_medium=referral&utm_source=github&utm_content=comment&utm_campaign=pr+comments&utm_term=NKI-AI#diff-ZGlyZWN0L3V0aWxzL19faW5pdF9fLnB5) | `77.63% <100.00%> (+2.80%)` | :arrow_up: | | ... and [2 more](https://codecov.io/gh/NKI-AI/direct/pull/232?src=pr&el=tree-more&utm_medium=referral&utm_source=github&utm_content=comment&utm_campaign=pr+comments&utm_term=NKI-AI) | | Help us with your feedback. Take ten seconds to tell us [how you rate us](https://about.codecov.io/nps?utm_medium=referral&utm_source=github&utm_content=comment&utm_campaign=pr+comments&utm_term=NKI-AI). Have a feature suggestion? [Share it here.](https://app.codecov.io/gh/feedback/?utm_medium=referral&utm_source=github&utm_content=comment&utm_campaign=pr+comments&utm_term=NKI-AI)

:umbrella: View full report at Codecov.
:loudspeaker: Do you have feedback about the report comment? Let us know in this issue.