This repository contains the code for the CVPR 2020 paper "Differentiable Volumetric Rendering: Learning Implicit 3D Representations without 3D Supervision"
Dear Authors,
Thank you so much for a great paper !
Did a training on 1 shapenet class.
Trying generate.py on this newly trained model.
Getting:
RuntimeError: Error(s) in loading state_dict for DVR:
size mismatch for decoder.fc_p.weight: copying a param with shape torch.Size([128, 3]) from checkpoint, the shape in current model is torch.Size([512, 3]).
Going through the code to identify which parameter should be adjusted.
Any hints would be appreciated.
No such issue on the pretrained model
Thanks a lot !
Dear Authors, Thank you so much for a great paper ! Did a training on 1 shapenet class. Trying generate.py on this newly trained model. Getting: RuntimeError: Error(s) in loading state_dict for DVR: size mismatch for decoder.fc_p.weight: copying a param with shape torch.Size([128, 3]) from checkpoint, the shape in current model is torch.Size([512, 3]). Going through the code to identify which parameter should be adjusted. Any hints would be appreciated. No such issue on the pretrained model Thanks a lot !