Closed OrangeSodahub closed 11 months ago
And the error lies in inds_inverse
:
feat_3d shape: torch.Size([18840, 768])
inds_inverse shape: torch.Size([81369])
No I don't try to evaluate on the train set because during training, we input the entire point cloud (81369 points) but only supervise with the features of a subset of the point clouds (as you can see, there are only 18840 points having features). This is done due to GPU memory consideration. If you truly want to evaluate on the training set, you need to modify our feature fusion code accordingly.
After I modify that two arguments, the feat_fuse
got no errors, but the same type of error occurred at
https://github.com/pengsongyou/openscene/blob/0f369bc73d0724ae24b5e46bbada193f8ee9d193/run/evaluate.py#L307
Hi, I was wondering, did you ever try to eval on
train
split? Means setsplit
totrain
in e.g.ours_openseg_pretrained.yaml
. I tried but got errors:If I set to
val
, it looks good.Hope some advice! If it's a bug, hope to fix it!