Chris Choy

Yes, that is the usual speed. The default argument uses batch size = 4, which uses a fraction of GPU. Try to increase the batch size. Also, the codebase is...

No I haven't. There are several poorly written parts in data loader that take up huge resources and one of them is https://github.com/chrischoy/FCGF/blob/master/lib/data_loaders.py#L257 which uses parallel KD trees to create...

I cannot reproduce this error. Did you get this error while training was running for some time?

The Eq.7 has two summations. One for the dataset, one for the correspondences. It evaluates the correspondences.

It is 32G. Possibly, it seems that FCGF gives too many inliers for TEASER and allocating too much memory.

Ah thanks for letting me know. It is the same weight, but you have to use the argument `python main.py --conv1_kernel_size 5 ...` for the weights. I'll update the ModelZoo...

It is 0.2% mIoU lower than the current one I put on the Model Zoo in this repository. But for all purposes, they are pretty state of the art.

Its in the original synthia dataset.

Okay, let me get back to it this weekend.

You mean this one? https://github.com/chrischoy/SpatioTemporalSegmentation/blob/master/scripts/train_synthia4d_temporal.sh