Vivek Gopalakrishnan

Remove `@non_differentiable` for `trunc`?

1

I saw that the `@non_differentiable` tag was removed for floor, ceil, and round recently (https://github.com/JuliaDiff/ChainRules.jl/commit/1770bb29ca42d4e07643284e0a4917ad6ea35b57). Should the same thing be done for `trunc`? https://github.com/JuliaDiff/ChainRules.jl/blob/7faaf5d540e1249e6b2087c1d52cbef4b85c58e8/src/rulesets/Base/nondiff.jl#L433 I am trying to take the...

R feature importance here https://github.com/neurodata/SPORF/blob/staging/R-Project/R/FeatureImportance.R Port to Python implementation

The 3D volume and the 2D detector plane are stored as their physical analogs (3D voxelgrid and 4D tensor of spatial coordinates, respectively). This is helpful for conceptualization, but there...

The last PR (#65) might have broken 3D plotting functions Switching to einsum notation will break some of the indexing for getting source point and detector plane

some combination of this - https://dev.to/epassaro/caching-anaconda-environments-on-github-actions-2d08 - https://github.com/epassaro/cache-conda-envs - https://github.com/actions/cache - https://github.com/conda-incubator/setup-miniconda

Instead of multiresolution rays, use a multiresolution voxel grid (ie, octree represent the CT)

- [ ] Pick out a doc provider (sphinx, readthedocs, etc) - [ ] Doctests? (#49) - [ ] Add badge

Dynamically delete tensors during DRR generation

1

Once a large tensor like `alpha`, `alphamids` or `step_length` is no longer necessary, it should be deleted to free up memory on the GPU This would also potentially allow us...

Want to be able to compute just a subset of the pixels also would be helpful to have sparse implementations of loss functions too!

Get the initialization neural network working

2

Nalini's advice: 1. Check the training loss 2. Make sure the network can learn a single example 3. Use batchnorm 4. Use residual connections 5. Try a deeper network 6....