Questions about unused modules in Model class for training implementation #6

Activity

1. Colin97 commented on May 30, 2025

   

   Colin97

   on May 30, 2025

   Contributor

   More actions

   Hello,

   In our original version, we also included an SDF prediction task as an auxiliary objective; sdf_decoder and grid_coord were used for this purpose. However, this task was later discarded, so you may now ignore these two components.

   As for the feature loss, please refer to our paper or the following code snippet (without hard negative mining):

   ` N, M, _ = PA.shape
   coord = torch.cat((PA, PB, PC), 1) # N, 3M, 3

       point_feat = sample_triplane_feat(planes, coord) # N, 3M, C
       l1_reg = self.l1_loss(point_feat, torch.zeros_like(point_feat)).mean()
   
       featA, featB, featC = torch.split(point_feat, M, dim=1)
       
       cosAB = torch.exp(F.cosine_similarity(featA, featB, dim=2) * self.logit_scale)
       cosAC = torch.exp(F.cosine_similarity(featA, featC, dim=2) * self.logit_scale)
       cosBC = torch.exp(F.cosine_similarity(featB, featC, dim=2) * self.logit_scale)
   
       triplet_loss = -(torch.log(cosAB / (cosAB + cosAC)) + torch.log(cosAB / (cosAB + cosBC))) / 2
   
       triplet_acc = torch.logical_and(cosAB > cosAC, cosAB > cosBC)
       return triplet_loss.mean(), triplet_acc.float().mean(dim=-1), l1_reg`
   
2. Colin97 commented on Jun 17, 2025

   

   Colin97

   on Jun 17, 2025

   Contributor

   More actions

   Sorry, after checking with the team, we confirmed that in our final version, we still retained SDF field prediction as an auxiliary task, using the ground-truth SDF of the mesh as supervision. The sdf_decoder and grid_coord were used for this purpose.
3. StupidAdam commented on Jun 23, 2025

   

   StupidAdam

   on Jun 23, 2025

   Author

   More actions

   @Colin97 ​​Thanks for your detailed explanation! To clarify our concern: In the code snippet l1_reg = self.l1_loss(point_feat, torch.zeros_like(point_feat)).mean(), the L1 loss is computed between point_feat and a zero tensor. Could you elaborate on the motivation behind this design?
4. lauvli commented on Jul 15, 2025

   

   lauvli

   on Jul 15, 2025

   Last edited by lauvli

   More actions

   Hello,

   In our original version, we also included an SDF prediction task as an auxiliary objective; sdf_decoder and grid_coord were used for this purpose. However, this task was later discarded, so you may now ignore these two components.

   As for the feature loss, please refer to our paper or the following code snippet (without hard negative mining):

   ` N, M, _ = PA.shape coord = torch.cat((PA, PB, PC), 1) # N, 3M, 3

       point_feat = sample_triplane_feat(planes, coord) # N, 3M, C
       l1_reg = self.l1_loss(point_feat, torch.zeros_like(point_feat)).mean()
   
       featA, featB, featC = torch.split(point_feat, M, dim=1)
       
       cosAB = torch.exp(F.cosine_similarity(featA, featB, dim=2) * self.logit_scale)
       cosAC = torch.exp(F.cosine_similarity(featA, featC, dim=2) * self.logit_scale)
       cosBC = torch.exp(F.cosine_similarity(featB, featC, dim=2) * self.logit_scale)
   
       triplet_loss = -(torch.log(cosAB / (cosAB + cosAC)) + torch.log(cosAB / (cosAB + cosBC))) / 2
   
       triplet_acc = torch.logical_and(cosAB > cosAC, cosAB > cosBC)
       return triplet_loss.mean(), triplet_acc.float().mean(dim=-1), l1_reg`
   

   Hello, while reproducing your team's work, I noticed that you used several loss terms including triplet(1.0), sdf(1.0), feat(10.0), and l1 loss(0.0).

   From my understanding:

   • triplet_loss = -(torch.log(cosAB / (cosAB + cosAC)) + torch.log(cosAB / (cosAB + cosBC))) / 2
   • sdf_loss represents the SDF prediction task
   • l1_reg = self.l1_loss(point_feat, torch.zeros_like(point_feat)).mean()

   However, I'm unclear about what the feat loss specifically represents. Moreover, I noticed its weight is significantly larger compared to other auxiliary losses, which makes me think it might be a crucial loss function. Could you please provide some guidance on this?
5. Colin97 commented on Jul 16, 2025

   

   Colin97

   on Jul 16, 2025

   Contributor

   More actions

   @Colin97 ​​Thanks for your detailed explanation! To clarify our concern: In the code snippet l1_reg = self.l1_loss(point_feat, torch.zeros_like(point_feat)).mean(), the L1 loss is computed between point_feat and a zero tensor. Could you elaborate on the motivation behind this design?

   it's just a regularization term.
6. Colin97 commented on Jul 16, 2025

   

   Colin97

   on Jul 16, 2025

   Contributor

   More actions

   Hello,
   In our original version, we also included an SDF prediction task as an auxiliary objective; sdf_decoder and grid_coord were used for this purpose. However, this task was later discarded, so you may now ignore these two components.
   As for the feature loss, please refer to our paper or the following code snippet (without hard negative mining):
   ` N, M, _ = PA.shape coord = torch.cat((PA, PB, PC), 1) # N, 3M, 3

       point_feat = sample_triplane_feat(planes, coord) # N, 3M, C
       l1_reg = self.l1_loss(point_feat, torch.zeros_like(point_feat)).mean()
   
       featA, featB, featC = torch.split(point_feat, M, dim=1)
       
       cosAB = torch.exp(F.cosine_similarity(featA, featB, dim=2) * self.logit_scale)
       cosAC = torch.exp(F.cosine_similarity(featA, featC, dim=2) * self.logit_scale)
       cosBC = torch.exp(F.cosine_similarity(featB, featC, dim=2) * self.logit_scale)
   
       triplet_loss = -(torch.log(cosAB / (cosAB + cosAC)) + torch.log(cosAB / (cosAB + cosBC))) / 2
   
       triplet_acc = torch.logical_and(cosAB > cosAC, cosAB > cosBC)
       return triplet_loss.mean(), triplet_acc.float().mean(dim=-1), l1_reg`
   

   Hello, while reproducing your team's work, I noticed that you used several loss terms including triplet(1.0), sdf(1.0), feat(10.0), and l1 loss(0.0).

   From my understanding:

   • triplet_loss = -(torch.log(cosAB / (cosAB + cosAC)) + torch.log(cosAB / (cosAB + cosBC))) / 2
   • sdf_loss represents the SDF prediction task
   • l1_reg = self.l1_loss(point_feat, torch.zeros_like(point_feat)).mean()

   However, I'm unclear about what the feat loss specifically represents. Moreover, I noticed its weight is significantly larger compared to other auxiliary losses, which makes me think it might be a crucial loss function. Could you please provide some guidance on this?

   where did you find triplet(1.0), sdf(1.0), feat(10.0), and l1 loss(0.0)
7. lauvli commented on Jul 17, 2025

   

   lauvli

   on Jul 17, 2025

   More actions

   Hello,
   In our original version, we also included an SDF prediction task as an auxiliary objective; sdf_decoder and grid_coord were used for this purpose. However, this task was later discarded, so you may now ignore these two components.
   As for the feature loss, please refer to our paper or the following code snippet (without hard negative mining):
   ` N, M, _ = PA.shape coord = torch.cat((PA, PB, PC), 1) # N, 3M, 3

       point_feat = sample_triplane_feat(planes, coord) # N, 3M, C
       l1_reg = self.l1_loss(point_feat, torch.zeros_like(point_feat)).mean()
   
       featA, featB, featC = torch.split(point_feat, M, dim=1)
       
       cosAB = torch.exp(F.cosine_similarity(featA, featB, dim=2) * self.logit_scale)
       cosAC = torch.exp(F.cosine_similarity(featA, featC, dim=2) * self.logit_scale)
       cosBC = torch.exp(F.cosine_similarity(featB, featC, dim=2) * self.logit_scale)
   
       triplet_loss = -(torch.log(cosAB / (cosAB + cosAC)) + torch.log(cosAB / (cosAB + cosBC))) / 2
   
       triplet_acc = torch.logical_and(cosAB > cosAC, cosAB > cosBC)
       return triplet_loss.mean(), triplet_acc.float().mean(dim=-1), l1_reg`
   

   Hello, while reproducing your team's work, I noticed that you used several loss terms including triplet(1.0), sdf(1.0), feat(10.0), and l1 loss(0.0).
   From my understanding:

   • triplet_loss = -(torch.log(cosAB / (cosAB + cosAC)) + torch.log(cosAB / (cosAB + cosBC))) / 2
   • sdf_loss represents the SDF prediction task
   • l1_reg = self.l1_loss(point_feat, torch.zeros_like(point_feat)).mean()

   However, I'm unclear about what the feat loss specifically represents. Moreover, I noticed its weight is significantly larger compared to other auxiliary losses, which makes me think it might be a crucial loss function. Could you please provide some guidance on this?

   where did you find triplet(1.0), sdf(1.0), feat(10.0), and l1 loss(0.0)

   I was examining the model configuration via model = torch.load('./model/model_objaverse.ckpt') and noticed the following loss settings in model['hyper_parameters']:

   'loss': CfgNode({'triplet': 1.0, 'sdf': 1.0, 'feat': 10.0, 'l1': `0.0})`
   

   Additionally, I observed the sampling parameters:

   'num_pos': 64, 'num_neg_random': 256, 'num_neg_hard_pc': 256, 'num_neg_hard_emb': 0
   

   I’m curious about two points:

   ​​feat loss term​​: Could you clarify what this term represents? Given its high weight (10.0), it seems to play a critical role, but I couldn’t find documentation on its specifics.
   ​​Hard negative sampling​​: The setting num_neg_hard_emb=0 suggests that feature-based hard negatives might have been disabled in the second stage. Was this an intentional design choice? If so, could you share the rationale behind it?
   Thank you for your time and insights!
8. Colin97 commented on Oct 13, 2025

   

   Colin97

   on Oct 13, 2025

   Contributor

   More actions

   Training with triplet loss and SDF loss should work fine.

   Training with only distance-based hard negative mining should yield sufficiently good results.