Skip to content

NLLLoss: current code works with dim = 3, so I added it to dim checks #4654

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

Merged
apaszke merged 1 commit into from
Jan 13, 2018
Merged

NLLLoss: current code works with dim = 3, so I added it to dim checks #4654

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
2 changes: 1 addition & 1 deletion test/common_nn.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -259,7 +259,7 @@ def kldivloss_reference(input, target, size_average=True, reduce=True):

def nlllossNd_reference(input, target, weight=None, ignore_index=-100,
size_average=True, reduce=True):
assert input.dim() >= 4
assert input.dim() >= 3
N = input.size(0)
C = input.size(1)
out_size = (N,) + input.size()[2:]
Expand Down
9 changes: 9 additions & 0 deletions test/test_nn.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -4266,6 +4266,15 @@ def forward(self, *args):
check_no_size_average=True,
desc='higher_dim'
),
dict(
module_name='NLLLoss',
input_size=(2, 3, 5),
target_fn=lambda: torch.rand(2, 5).mul(3).floor().long(),
reference_fn=lambda i, t, m:
loss_reference_fns['NLLLossNd'](i, t, size_average=get_size_average(m)),
check_no_size_average=True,
desc='dim_is_3'
),
dict(
module_name='PoissonNLLLoss',
input_size=(2, 3, 4, 5),
Expand Down
8 changes: 4 additions & 4 deletions torch/nn/functional.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -1162,10 +1162,10 @@ def nll_loss(input, target, weight=None, size_average=True, ignore_index=-100, r

Args:
input: :math:`(N, C)` where `C = number of classes` or :math:`(N, C, H, W)`
in case of 2D Loss, or :math:`(N, C, d_1, d_2, ..., d_K)` where :math:`K > 2`
in case of 2D Loss, or :math:`(N, C, d_1, d_2, ..., d_K)` where :math:`K > 1`
in the case of K-dimensional loss.
target: :math:`(N)` where each value is `0 <= targets[i] <= C-1`,
or :math:`(N, C, d_1, d_2, ..., d_K)` where :math:`K >= 2` for
or :math:`(N, C, d_1, d_2, ..., d_K)` where :math:`K >= 1` for
K-dimensional loss.
weight (Tensor, optional): a manual rescaling weight given to each
class. If given, has to be a Tensor of size `C`
Expand All @@ -1192,7 +1192,7 @@ def nll_loss(input, target, weight=None, size_average=True, ignore_index=-100, r
return torch._C._nn.nll_loss(input, target, weight, size_average, ignore_index, reduce)
elif dim == 4:
return torch._C._nn.nll_loss2d(input, target, weight, size_average, ignore_index, reduce)
elif dim > 4:
elif dim == 3 or dim > 4:
n = input.size(0)
c = input.size(1)
out_size = (n,) + input.size()[2:]
Expand All @@ -1206,7 +1206,7 @@ def nll_loss(input, target, weight=None, size_average=True, ignore_index=-100, r
out = torch._C._nn.nll_loss2d(input, target, weight, size_average, ignore_index, reduce)
return out.view(out_size)
else:
raise ValueError('Expected 2, 4, or more than 4 dimensions (got {})'.format(dim))
raise ValueError('Expected 2 or more dimensions (got {})'.format(dim))


def poisson_nll_loss(input, target, log_input=True, full=False, size_average=True, eps=1e-8, reduce=True):
Expand Down