Skip to content

Added option to select the device on which the tensors are constructed #2

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Closed
AleksandarPetrov wants to merge 2 commits into from
Closed

Added option to select the device on which the tensors are constructed #2

Changes from all commits
Commits
Show all changes
2 commits
Select commit Hold shift + click to select a range
6283b0c
device selector added
AleksandarPetrov Nov 14, 2019
7041413
default None added
AleksandarPetrov Nov 14, 2019
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
11 changes: 6 additions & 5 deletions layers.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -20,11 +20,12 @@ class SinkhornDistance(nn.Module):
- Input: :math:`(N, P_1, D_1)`, :math:`(N, P_2, D_2)`
- Output: :math:`(N)` or :math:`()`, depending on `reduction`
"""
def __init__(self, eps, max_iter, reduction='none'):
def __init__(self, eps, max_iter, device=None, reduction='none'):
super(SinkhornDistance, self).__init__()
self.eps = eps
self.max_iter = max_iter
self.reduction = reduction
self.device = device

def forward(self, x, y):
# The Sinkhorn algorithm takes as input three variables :
Expand All @@ -38,12 +39,12 @@ def forward(self, x, y):

# both marginals are fixed with equal weights
mu = torch.empty(batch_size, x_points, dtype=torch.float,
requires_grad=False).fill_(1.0 / x_points).squeeze()
requires_grad=False, device=self.device).fill_(1.0 / x_points).squeeze()
nu = torch.empty(batch_size, y_points, dtype=torch.float,
requires_grad=False).fill_(1.0 / y_points).squeeze()
requires_grad=False, device=self.device).fill_(1.0 / y_points).squeeze()

u = torch.zeros_like(mu)
v = torch.zeros_like(nu)
u = torch.zeros_like(mu, device=self.device)
v = torch.zeros_like(nu, device=self.device)
# To check if algorithm terminates because of threshold
# or max iterations reached
actual_nits = 0
Expand Down