Pytorch: 'torch.nn' has no attribute 'TripletMarginLoss'
Calling
triplet_loss = nn.TripletMarginLoss()
results in:
AttributeError: module 'torch.nn' has no attribute 'TripletMarginLoss'
even with
import torch.nn as nn
Related PR that added introduced TripletMarginLoss: #1165
Work-around for now is to use F.triplet_margin_loss directly, where F is import torch.nn.functional as F.
high priority
bartolsthoorn
All 3 comments
Another workaround would be to add from torch.nn.modules.loss import TripletMarginLoss.
apaszke
on 10 Apr 2017
👍2
fixed in master. will be in next release.
soumith
on 11 Apr 2017
🎉1
Hi, similar thing happens when I call m = nn.Upsample(scale_factor=2, mode='bilinear')
AttributeError: 'module' object has no attribute 'Upsample'
But I can successfully call nn.UpsamplingBilinear2d.
Besides, is there any plan to implement the Cubic Upsample~
D-X-Y
on 22 Jun 2017
❤4
Was this page helpful?
0 / 5 - 0 ratings
Related issues
dablyo
·
3Comments
Coderx7
·
3Comments
bartvm
·
3Comments
kdexd
·
3Comments
mishraswapnil
·
3Comments
Most helpful comment
Hi, similar thing happens when I call
m = nn.Upsample(scale_factor=2, mode='bilinear')AttributeError: 'module' object has no attribute 'Upsample'
But I can successfully call
nn.UpsamplingBilinear2d.Besides, is there any plan to implement the
Cubic Upsample~