Skip to content
This repository has been archived by the owner on Feb 12, 2022. It is now read-only.

Error in moving to GPU #4

Closed
Taha-Bahadori opened this issue Aug 26, 2017 · 1 comment
Closed

Error in moving to GPU #4

Taha-Bahadori opened this issue Aug 26, 2017 · 1 comment

Comments

@Taha-Bahadori
Copy link

Taha-Bahadori commented Aug 26, 2017

@Smerity I tried the following code:

import torch
import torch.nn as nn

class Model(nn.Module):
    def __init__(self):
        super(Model, self).__init__()
        self.gru = nn.GRU(10, 10)
        self.gru = WeightDrop(self.gru, ['weight_hh_l0'], dropout=0.5)

m = Model()
# The following operation throws an error
m.cuda()

Can you take a look and see where the problem occurs? I am using PyTorch 0.2.

@Taha-Bahadori Taha-Bahadori changed the title Error moving to GPU Error in moving to GPU Aug 26, 2017
@Smerity
Copy link
Contributor

Smerity commented Aug 27, 2017

As noted in the README, PyTorch 0.1.12 is currently required, with one reason being that WeightDrop needs to be updated.

This is mentioned in #3. Given the work shall take place in that issue, I'll close this one. You are welcome to help fix the issue and contribute the changes!

@Smerity Smerity closed this as completed Aug 27, 2017
Sign up for free to subscribe to this conversation on GitHub. Already have an account? Sign in.
Labels
None yet
Projects
None yet
Development

No branches or pull requests

2 participants