TMJ
**Hardware**: xavier nx **Code**: train.py **Config file**: resnet18_baseline_att_224x224_A.json **Issue**: Trains properly with fp32. Fails with mixed precision training. I'm retraining the network on the xavier nx in order to incorporate...
**Is your feature request related to a problem? Please describe.** More of a question than a request. I'm doing reinforcement learning which requires episodic trajectory rollouts. It would be convenient...
On line 324 of Compound.cpp, it states that drag is computed for externally declared parts that are submerged. That makes sense. However, does the app compute drag for the hull,...
I have an existing onnx detectnet model for which I have lost the .pth checkpoint. Is it possible to convert the onnx model back to a .pth checkpoint so that...
Hi, I've preprocessed my data set according to preprocess_dataset.py and then I run train.py and get the following error Traceback (most recent call last): File "train.py", line 210, in main()...
The problem: Can't install giotto-tda, giotto-ph, giotto-time etc on aarch64 (NVIDIA Jetson) architectures. I get the error: ERROR: Could not build wheels for giotto-tda. The reason: Allowing us to use...