The expanded size of the tensor (4) must match the existing size (32) at non-singleton dimension 1. Target sizes: [32, 4]. Tensor sizes: [32] #8
Description
Hi, I used pytorch 1.4.0 it raised this error. Any idea where goes wrong? Thanks ~
File "cadAutoEncCuboids/primSelTsdfChamfer.py", line 125, in train
predParts, stocastic_actions = netPred.forward(inputVol) ## B x nPars*11
File "cadAutoEncCuboids/primSelTsdfChamfer.py", line 199, in forward
primitives, stocastic_actions = self.primitivesTable(features)
File "/home/pingzi/PycharmProjects/proj1/python3.6_vir/lib/python3.6/site-packages/torch/nn/modules/module.py", line 532, in call
result = self.forward(*input, **kwargs)
File "/home/pingzi/PycharmProjects/volumetricPrimitivesPytorch-reinforce/modules/primitives.py", line 166, in forward
output, stocastic_outputs = l(feature)
File "/home/pingzi/PycharmProjects/proj1/python3.6_vir/lib/python3.6/site-packages/torch/nn/modules/module.py", line 532, in call
result = self.forward(*input, **kwargs)
File "/home/pingzi/PycharmProjects/volumetricPrimitivesPytorch-reinforce/modules/primitives.py", line 137, in forward
quat = self.quatPred(feature)
File "/home/pingzi/PycharmProjects/proj1/python3.6_vir/lib/python3.6/site-packages/torch/nn/modules/module.py", line 532, in call
result = self.forward(*input, **kwargs)
File "/home/pingzi/PycharmProjects/volumetricPrimitivesPytorch-reinforce/modules/primitives.py", line 68, in forward
x = normalize(x)
File "/home/pingzi/PycharmProjects/volumetricPrimitivesPytorch-reinforce/modules/primitives.py", line 73, in normalize
x = x/ (1E-12 + torch.norm(x, dim=1, p=2).expand(x.size()))
RuntimeError: The expanded size of the tensor (4) must match the existing size (32) at non-singleton dimension 1. Target sizes: [32, 4]. Tensor sizes: [32]