Hardik Shah

Following are the proposed changes: [Fix 1](https://github.com/Brummi/MonoRec/commit/2d46273196306659f41ef3921727ece6d5791df1): Masking of the depth from a given roi had a mistake in the [ply_utils.py](https://github.com/Brummi/MonoRec/compare/main...hardik01shah:MonoRec:main#diff-712b0e42e4b8959dc0ae59ab6dfa355279062c21eb555f74604365a434886f12) file [Fix 2](https://github.com/Brummi/MonoRec/commit/51bdbdc2c3c2f883563b594e60f837ee1c9e1d9e): Parameter for mask_module checkpoint location in...

Hi, In your paper I noticed that you have done some ablation studies on the Virtual KITTI dataset. You mentioned that you used the sparse depth masks corresponding to the...

Hi, I installed habitat-sim from source using `python setup.py install`, without any other flags. My system is a Lenovo Thinkbook without a GPU, and that is the reason I did...

Softmax was being applied by default to the output of the Last2D block, and the `softmax` argument in the forward method was unused. Fixed it to use the argument to...

Symmetric vs Random Initialization for some benchmarks

1

For some benchmarks like [correlation](https://github.com/spcl/npbench/tree/main/npbench/benchmarks/polybench/correlation/correlation.py) and [covariance](https://github.com/spcl/npbench/tree/main/npbench/benchmarks/polybench/covariance/covariance.py), the initialization of the matrix is a symmetric matrix. This unfortunately validates incorrect implementations for the benchmarks. Is there any specific reason for...

Benchmarks that do not return output / updated arrays are not validated

1

Certain benchmarks like `lu`, `cavity_flow`, `scattering_self_energies` and many more do not return the output arrays that the benchmark computes, or the input arrays that are updated during the computation. These...

Mode argument not used for numba evaluations

1

The mode argument in the [run_benchmark.py](https://github.com/spcl/npbench/blob/0bc108b70579d4691ec4bd3555b16431bebb881a/run_benchmark.py#L23) and [quickstart.py](https://github.com/spcl/npbench/blob/main/quickstart.py) files is not used at all. I presume this was introduced to evaluate a specific mode in the numba implementations. Happy to...

Fix the distance calculation for the `dilation_filter_kernel` in `elevation_mapping_cupy/script/elevation_mapping_cupy/kernels/custom_kernels.py`. Use `abs(dx) + abs(dy)` instead of `dx + dy` since `dx` and `dy` can be negative.