Skip to content

Follow the input tensor's device instead of forcing CUDA #4

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

Open
itzzdev09 wants to merge 1 commit into
base: main
Choose a base branch
from
+16 −4
Open

Follow the input tensor's device instead of forcing CUDA #4

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
1 commit
Select commit
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
5 changes: 4 additions & 1 deletion DK wind speed forecasting/WeatherGCNet with gamma/model_dk.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -75,7 +75,10 @@ def forward(self, x):
f_in = x.contiguous().view(N, C * T, V)

adj_mat = None
self.A = self.A.cuda(x.get_device())
# x.get_device() returns -1 for a CPU tensor, and .cuda() forces CUDA
# regardless, so this raised "Device index must not be negative" on any
# machine without a GPU. .to() follows whichever device x is already on.
self.A = self.A.to(x.device)
adj_mat = self.B[:,:] + self.gamma * self.A[:,:]
adj_mat_min = torch.min(adj_mat)
adj_mat_max = torch.max(adj_mat)
Expand Down
5 changes: 4 additions & 1 deletion DK wind speed forecasting/WeatherGCNet/model_dk.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -76,7 +76,10 @@ def forward(self, x):
f_in = x.contiguous().view(N, C * T, V)

adj_mat = None
self.A = self.A.cuda(x.get_device())
# x.get_device() returns -1 for a CPU tensor, and .cuda() forces CUDA
# regardless, so this raised "Device index must not be negative" on any
# machine without a GPU. .to() follows whichever device x is already on.
self.A = self.A.to(x.device)
adj_mat = self.B[:,:] + self.A[:,:]
adj_mat_min = torch.min(adj_mat)
adj_mat_max = torch.max(adj_mat)
Expand Down
5 changes: 4 additions & 1 deletion NL wind speed forecasting/WeatherGCNet with gamma/model_nl.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -77,7 +77,10 @@ def forward(self, x):
f_in = x.contiguous().view(N, C * T, V)

adj_mat = None
self.A = self.A.cuda(x.get_device())
# x.get_device() returns -1 for a CPU tensor, and .cuda() forces CUDA
# regardless, so this raised "Device index must not be negative" on any
# machine without a GPU. .to() follows whichever device x is already on.
self.A = self.A.to(x.device)
adj_mat = self.B[:,:] + self.gamma * self.A[:,:]
adj_mat_min = torch.min(adj_mat)
adj_mat_max = torch.max(adj_mat)
Expand Down
5 changes: 4 additions & 1 deletion NL wind speed forecasting/WeatherGCNet/model_nl.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -74,7 +74,10 @@ def forward(self, x):
f_in = x.contiguous().view(N, C * T, V)

adj_mat = None
self.A = self.A.cuda(x.get_device())
# x.get_device() returns -1 for a CPU tensor, and .cuda() forces CUDA
# regardless, so this raised "Device index must not be negative" on any
# machine without a GPU. .to() follows whichever device x is already on.
self.A = self.A.to(x.device)
adj_mat = self.B[:,:] + self.A[:,:]
adj_mat_min = torch.min(adj_mat)
adj_mat_max = torch.max(adj_mat)
Expand Down