search

YujiaLiu76 / point2cad

Code for "Point2CAD: Reverse Engineering CAD Models from 3D Point Clouds"
Apache License 2.0
231 stars 26 forks source link

Sharing weights of ParSeNet #3

Closed yilinliu77 closed 3 months ago

yilinliu77 commented 9 months ago

Hi Yujia,

Thanks for sharing the code!

I noticed that the weight of ParSeNet is no longer available. I couldn't find it in the ParSeNet repository. Can you kindly share the two weights files with an additional link?

Thanks in advance!

DietmarGrabowski commented 8 months ago

Hi, in ParSeNet the version of PyTorch is 1.2 and i want to load the parsenet_no_normals.pth from your link. I get: RuntimeError: ./logs/pretrained_models/parsenet_no_normals.pth is a zip archive (did you mean to use torch.jit.load()?) and with torch.jit.load() i get: File "/root/miniconda3/envs/parsenet/lib/python3.6/site-packages/torch/jit/init.py", line 162, in load cpp_module = torch._C.import_ir_module(cu, f, map_location, _extra_files) RuntimeError: version_number <= kMaxSupportedFileFormatVersion INTERNAL ASSERT FAILED at /pytorch/caffe2/serialize/inline_container.cc:131, please report a bug to PyTorch. Attempted to read a PyTorch file with version 3, but the maximum supported version for reading is 1. Your PyTorch installation may be too old.

YujiaLiu76 commented 5 months ago

Hi, the weights in point2cad/logs can be used.