Skip to content

fix error message of large kernel size in conv2D #12791

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
weiyangfb wants to merge 4 commits into from
Closed

fix error message of large kernel size in conv2D #12791

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
4 commits
Select commit Hold shift + click to select a range
00c1ef7
change printf %ld to %ld for kH and kW
weiyangfb Oct 17, 2018
84a8c4e
fix in cuda as well
weiyangfb Oct 17, 2018
06859f5
add test case for conv2d
weiyangfb Oct 18, 2018
a10602e
fix conv3d as well
weiyangfb Oct 18, 2018
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 aten/src/THCUNN/generic/SpatialConvolutionMM.cu
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -47,7 +47,7 @@ static inline void THNN_(SpatialConvolutionMM_shapeCheck)(

if (exactInputHeight < kH || exactInputWidth < kW) {
THError("Calculated padded input size per channel: (%ld x %ld). "
"Kernel size: (%ld x %ld). Kernel size can't be greater than actual input size",
"Kernel size: (%d x %d). Kernel size can't be greater than actual input size",
exactInputHeight, exactInputWidth, kH, kW);
}

Expand Down
2 changes: 1 addition & 1 deletion aten/src/THNN/generic/SpatialConvolutionMM.c
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -46,7 +46,7 @@ static inline void THNN_(SpatialConvolutionMM_shapeCheck)(

if (exactInputHeight < kH || exactInputWidth < kW) {
THError("Calculated padded input size per channel: (%ld x %ld). "
"Kernel size: (%ld x %ld). Kernel size can't be greater than actual input size",
"Kernel size: (%d x %d). Kernel size can't be greater than actual input size",
exactInputHeight, exactInputWidth, kH, kW);
}

Expand Down
2 changes: 1 addition & 1 deletion aten/src/THNN/generic/VolumetricConvolutionMM.c
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -74,7 +74,7 @@ static void inline THNN_(VolumetricConvolutionMM_shapeCheck)(

if (exactInputDepth < kT || exactInputHeight < kH || exactInputWidth < kW) {
THError("Calculated padded input size per channel: (%ld x %ld x %ld). "
"Kernel size: (%ld x %ld x %ld). Kernel size can't be greater than actual input size",
"Kernel size: (%d x %d x %d). Kernel size can't be greater than actual input size",
exactInputDepth, exactInputHeight, exactInputWidth, kT, kH, kW);
}

Expand Down
7 changes: 7 additions & 0 deletions test/test_nn.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -755,6 +755,13 @@ def test_invalid_conv2d(self):
input = torch.empty(1, 1, 4, 4)
self.assertRaises(RuntimeError, lambda: module(input))

module = nn.Conv2d(in_channels=3, out_channels=33, kernel_size=10, stride=1, bias=True)
input = torch.randn(1, 3, 1, 1)
with self.assertRaisesRegex(RuntimeError,
'Calculated padded input size per channel: \(1 x 1\). ' +
'Kernel size: \(10 x 10\). Kernel size can\'t be greater than actual input size'):
module(input)

def test_invalid_conv3d(self):
module = torch.nn.Conv3d(1, 1, kernel_size=3, dilation=2, stride=2)
input = torch.empty(1, 1, 4, 4, 4)
Expand Down