Rundi Wu

Results 37 comments of Rundi Wu

这个就是通过训练强行把两个模态映射到同一个空间,类似于CLIP把image和text映射到同一个空间。

Hi, Did you specify `--res 128` when [preparing the data](https://github.com/ChrisWu1997/SingleShapeGen#training-data-preparation)? Could you check the processed `.h5` file does have voxels of resolution 128? If so, running `main.py` as above should...

Just to confirm, are you saying after training on resolution (64, 128, 256), the final generated shapes (of the same resolution) lack diversity (i.e., they look similar)? Or results from...

Hi, unfortunately I couldn't find it now.

I managed to find a version of it and put it here: https://github.com/ChrisWu1997/DeepCAD/blob/master/pc2cad_train.py. Hope it helps!

It cannot convert STEP file to Fusion 360 construction sequence format. STEP file only contains the final B-rep representation, there is no CAD operation sequence information.