modulus
modulus copied to clipboard
NVIDIA
Open-source deep-learning framework for building, training, and fine-tuning deep learning models using state-of-the-art Physics-ML methods
### Version source - main ### On which installation method(s) does this occur? Docker ### Describe the issue The `test_healpix.py` can sometimes report a failure if run with the full...
### Version 0.6.0 ### On which installation method(s) does this occur? Docker ### Describe the issue In examples/weather/dataset_download/start_mirror.py the global_means and global_stds files (used later for normalization) are computed on...
### Version latest ### On which installation method(s) does this occur? Source ### Describe the issue CorrDiff loss is scaled by hyper-parameter, therefore we could not make a hyper-parameter search,...
### Version source - main ### On which installation method(s) does this occur? Source ### Describe the issue Currently the aerographnet utils use `shapely` ([reference](https://github.com/NVIDIA/modulus/blob/main/examples/cfd/aero_graph_net/utils.py#L23)) but this is not being...
### Is this a new feature, an improvement, or a change to existing functionality? Improvement ### How would you describe the priority of this feature request Medium ### Please provide...
### Version 0.6.0 ### On which installation method(s) does this occur? Docker ### Describe the issue I wanted to include the normalization coefficients in the saved model, so I attached...
### Version Latest from source ### On which installation method(s) does this occur? Source ### Describe the issue In CorrDiff generate.py there seems to be a bug on these lines:...
```[tasklist] ### P0 - Must have - [ ] https://github.com/NVIDIA/modulus/issues/570 - [ ] https://github.com/NVIDIA/modulus/issues/571 - [ ] https://github.com/NVIDIA/modulus/issues/572 - [ ] https://github.com/NVIDIA/modulus/issues/579 - [ ] https://github.com/NVIDIA/modulus/issues/580 ```