반응형
for param in self.model.Traj_Dec.decoder_mlp.parameters():
param.requires_grad = FalseDeep Learning
[Pytorch] Stop updating params of a layer of a model during back-propagation
'Deep Learning' Related Articles
-
Kullback–Leibler divergence (KL divergence)
-
How to make novel ideas?
- [Pytorch] Assign (loaded) pre-trained model params to a specific layer of a new model
- D. Choi et al., "Regularizing neural networks for future trajectory prediction via inverse reinforcement learning framework," IET Computer Vision, In Press.
