physicsnemo
physicsnemo 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 main ### On which installation method(s) does this occur? Source ### Describe the issue pytest failures with dataloader tests since data artifacts are not available locally. This is...
Tracker for the issues related to integrating VFGN ```[tasklist] ### Pytest - [ ] https://github.com/NVIDIA/modulus/issues/451 ```
```[tasklist] ### Integration - [x] Integration of the TPUN - [x] Enable Hydra config - [ ] Add docstrings - [ ] Add license headers - [ ] Add README...
### Version main ### On which installation method(s) does this occur? _No response_ ### Describe the issue there appears to be an inconsistency in the sigma passed to the regression...
### Is this a new feature, an improvement, or a change to existing functionality? Improvement ### How would you describe the priority of this feature request Critical (currently preventing usage)...
```[tasklist] ### Code structuring - [ ] Split generate.py, train.py and training_loop.py into functions/classes that handle more well-defined tasks - [ ] Reduce redundancy between the above files - [x]...
```[tasklist] ### Tasks - [x] Compare fast neighbor list routines (Open3D, RAFT, PySDF) - [x] https://github.com/NVIDIA/modulus/issues/369 - [ ] Documentation of the Modulus neighbor list - [x] Develop unit tests...
### Version 0.5.0 ### On which installation method(s) does this occur? Pip ### Describe the issue In the training loop, an accumulated loss is computing in an additive manner [here](https://github.com/NVIDIA/modulus/blob/9b0b7cc71fb280c028e09ee56726c0caa387c63b/examples/generative/corrdiff/training/training_loop.py#L236)...
