search

wanmeihuali / taichi_3d_gaussian_splatting

An unofficial implementation of paper 3D Gaussian Splatting for Real-Time Radiance Field Rendering by taichi lang.
Apache License 2.0
637 stars 58 forks source link

Segmentation fault (core dumped) #149

Open luuude opened 9 months ago

luuude commented 9 months ago

Hi I am getting segmentation fault. Any idea why?

python3 gaussian_point_train.py --train_config config/tat_truck_every_8_test.yaml

[Taichi] version 1.6.0, llvm 15.0.4, commit f1c6fbbd, linux, python 3.10.12 [Taichi] Starting on arch=cuda 0%| | 0/30001 [00:00<?, ?it/s]/home/ai/.local/lib/python3.10/site-packages/torchvision/transforms/functional.py:1603: UserWarning: The default value of the antialias parameter of all the resizing transforms (Resize(), RandomResizedCrop(), etc.) will change from None to True in v0.17, in order to be consistent across the PIL and Tensor backends. To suppress this warning, directly pass antialias=True (recommended, future default), antialias=None (current default, which means False for Tensors and True for PIL), or antialias=False (only works on Tensors - PIL will still use antialiasing). This also applies if you are using the inference transforms from the models weights: update the call to weights.transforms(antialias=True). warnings.warn( /home/ai/.local/lib/python3.10/site-packages/taichi/lang/expr.py:101: DeprecationWarning: In future, it will be an error for 'np.bool_' scalars to be interpreted as an index return Expr(_ti_core.make_const_expr_int(constant_dtype, val)) 0%| | 11/30001 [00:04<1:50:52, 4.51it/s]Segmentation fault (core dumped)

jb-ye commented 9 months ago

I had exactly segfault issue with the latest commit and had to revert this commit to proceed.

wanmeihuali commented 9 months ago

already roll back to previous commit, the problem shall be fix now