dvlab-research / Mask-Attention-Free-Transformer

Official Implementation for "Mask-Attention-Free Transformer for 3D Instance Segmentation"
59 stars 6 forks source link

Question about the pretrained weights in training #8

Open peoplelu opened 11 months ago

peoplelu commented 11 months ago

I observed that you utilized the pretrained weights from SSTNet during the training process. However, the SSTNet model's original input does not encompass normal information. In the context of incorporating normal information into the model, the question arises: which pretrained weights should be employed post the integration of normal information?