evaluate.py running out of memory because there is no no_grad modifier

mit-han-lab / spvnas

[ECCV 2020] Searching Efficient 3D Architectures with Sparse Point-Voxel Convolution

http://spvnas.mit.edu/

MIT License

585 stars 109 forks source link

evaluate.py running out of memory because there is no no_grad modifier #108

Closed sandeepnmenon closed 1 year ago

sandeepnmenon commented 1 year ago

When I run

python evaluate.py configs/semantic_kitti/default.yaml --name SemanticKITTI_val_SPVCNN@119GMACs

I get the distributed init error because it is not run using torchpack unlike the train script On fixing that, there is a CUDA out of memory error because there is not no_grad decorator arround the inference script