Implement new models

[georgeyiasemis]

Implements new MRI models along with tests:

• Conjugate Gradient Network - ConjGradNet (along with baseline)
• Iterative Dual Network - IterDualNet (Similar to JointICNet but no optimisation for sensitivity maps in the model)
• Simple Residual Network - ResNet, which can be used as a denoiser (replacement of UNet or DIDN, etc)
• Variable Splitting Network - VarSplitNet, solves the variable splitting optimization problem for MRI using a DL denoiser for the denoising equation and gradient descent for the data consistency equation

Also adds complex_dot_product and complex_division transforms

[codecov[bot]]

Codecov Report

Base: 81.91% // Head: 82.92% // Increases project coverage by +1.01% :tada:

Coverage data is based on head (c02fdc9) compared to base (73eb5c6). Patch coverage: 97.65% of modified lines in pull request are covered.

Additional details and impacted files

```diff @@ Coverage Diff @@ ## main #228 +/- ## ========================================== + Coverage 81.91% 82.92% +1.01% ========================================== Files 77 88 +11 Lines 5589 5967 +378 ========================================== + Hits 4578 4948 +370 - Misses 1011 1019 +8 ``` | [Impacted Files](https://codecov.io/gh/NKI-AI/direct/pull/228?src=pr&el=tree&utm_medium=referral&utm_source=github&utm_content=comment&utm_campaign=pr+comments&utm_term=NKI-AI) | Coverage Δ | | |---|---|---| | [direct/nn/varnet/varnet.py](https://codecov.io/gh/NKI-AI/direct/pull/228/diff?src=pr&el=tree&utm_medium=referral&utm_source=github&utm_content=comment&utm_campaign=pr+comments&utm_term=NKI-AI#diff-ZGlyZWN0L25uL3Zhcm5ldC92YXJuZXQucHk=) | `94.44% <ø> (ø)` | | | [direct/types.py](https://codecov.io/gh/NKI-AI/direct/pull/228/diff?src=pr&el=tree&utm_medium=referral&utm_source=github&utm_content=comment&utm_campaign=pr+comments&utm_term=NKI-AI#diff-ZGlyZWN0L3R5cGVzLnB5) | `77.77% <64.70%> (-22.23%)` | :arrow_down: | | [direct/nn/varsplitnet/varsplitnet.py](https://codecov.io/gh/NKI-AI/direct/pull/228/diff?src=pr&el=tree&utm_medium=referral&utm_source=github&utm_content=comment&utm_campaign=pr+comments&utm_term=NKI-AI#diff-ZGlyZWN0L25uL3ZhcnNwbGl0bmV0L3ZhcnNwbGl0bmV0LnB5) | `95.89% <95.89%> (ø)` | | | [direct/constants.py](https://codecov.io/gh/NKI-AI/direct/pull/228/diff?src=pr&el=tree&utm_medium=referral&utm_source=github&utm_content=comment&utm_campaign=pr+comments&utm_term=NKI-AI#diff-ZGlyZWN0L2NvbnN0YW50cy5weQ==) | `100.00% <100.00%> (ø)` | | | [direct/data/datasets\_config.py](https://codecov.io/gh/NKI-AI/direct/pull/228/diff?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/mri\_transforms.py](https://codecov.io/gh/NKI-AI/direct/pull/228/diff?src=pr&el=tree&utm_medium=referral&utm_source=github&utm_content=comment&utm_campaign=pr+comments&utm_term=NKI-AI#diff-ZGlyZWN0L2RhdGEvbXJpX3RyYW5zZm9ybXMucHk=) | `97.00% <100.00%> (ø)` | | | [direct/data/transforms.py](https://codecov.io/gh/NKI-AI/direct/pull/228/diff?src=pr&el=tree&utm_medium=referral&utm_source=github&utm_content=comment&utm_campaign=pr+comments&utm_term=NKI-AI#diff-ZGlyZWN0L2RhdGEvdHJhbnNmb3Jtcy5weQ==) | `96.31% <100.00%> (+0.68%)` | :arrow_up: | | [direct/engine.py](https://codecov.io/gh/NKI-AI/direct/pull/228/diff?src=pr&el=tree&utm_medium=referral&utm_source=github&utm_content=comment&utm_campaign=pr+comments&utm_term=NKI-AI#diff-ZGlyZWN0L2VuZ2luZS5weQ==) | `75.00% <100.00%> (ø)` | | | [direct/nn/conjgradnet/conjgrad.py](https://codecov.io/gh/NKI-AI/direct/pull/228/diff?src=pr&el=tree&utm_medium=referral&utm_source=github&utm_content=comment&utm_campaign=pr+comments&utm_term=NKI-AI#diff-ZGlyZWN0L25uL2NvbmpncmFkbmV0L2NvbmpncmFkLnB5) | `100.00% <100.00%> (ø)` | | | [direct/nn/conjgradnet/conjgradnet.py](https://codecov.io/gh/NKI-AI/direct/pull/228/diff?src=pr&el=tree&utm_medium=referral&utm_source=github&utm_content=comment&utm_campaign=pr+comments&utm_term=NKI-AI#diff-ZGlyZWN0L25uL2NvbmpncmFkbmV0L2NvbmpncmFkbmV0LnB5) | `100.00% <100.00%> (ø)` | | | ... and [9 more](https://codecov.io/gh/NKI-AI/direct/pull/228/diff?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.