Skip to content

Increase tol in DeformConv2d test for more robustness #3320

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
merged 3 commits into from
Jan 28, 2021
Merged

Increase tol in DeformConv2d test for more robustness #3320

Changes from all commits
Commits
Show all changes
3 commits
Select commit Hold shift + click to select a range
509b10c
increase tol
NicolasHug Jan 28, 2021
bd0a003
Merge branch 'master' of github.com:pytorch/vision into increase_tol
NicolasHug Jan 28, 2021
1091dd9
Merge branch 'master' into increase_tol
datumbox Jan 28, 2021
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
3 changes: 1 addition & 2 deletions test/test_ops.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -549,7 +549,7 @@ def _test_forward_with_batchsize(self, device, contiguous, batch_sz, dtype):
out_channels = 2
kernel_size = (3, 2)
groups = 2
tol = 1e-3 if dtype is torch.half else 1e-5
tol = 2e-3 if dtype is torch.half else 1e-5

layer = ops.DeformConv2d(in_channels, out_channels, kernel_size, stride=stride, padding=padding,
dilation=dilation, groups=groups).to(device=x.device, dtype=dtype)
Expand Down Expand Up @@ -651,7 +651,6 @@ def test_compare_cpu_cuda_grads(self):

@unittest.skipIf(not torch.cuda.is_available(), "CUDA unavailable")
def test_autocast(self):
set_rng_seed(0)
for dtype in (torch.float, torch.half):
with torch.cuda.amp.autocast():
self._test_forward(torch.device("cuda"), False, dtype=dtype)
Expand Down