-
Notifications
You must be signed in to change notification settings - Fork 6.8k
Conversation
@Jerryzcn @eric-haibin-lin @sxjscience for review. |
@hetong007 @szha for review/approve |
CI passed, training convergence passed, can you guys help merge it since the furture gluoncv models depends on this PR? @eric-haibin-lin @sxjscience |
num_deformable_group=num_deformable_group) | ||
if grad_nodes[0] == 'offset_data': | ||
# wider tolerance needed for coordinate differential | ||
rtol, atol = 1.0, 1e-2 |
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
rtol = 1.0
looks too large...
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
I think it's because the gradient for the offset is not very accurate. We should use some other ways to test the offset_data.
* add deformable conv v2 * fix lint and compiler warning * fix lint * fix pylint * fix clang and lint * fix base class, add test case * fix gluon impl, add cpu forward * address comment * fix duplicate kernel name * fix cpplint * con't fix cpplint * address comments * fix mask scale * make initial mask centered at 1 rather than 0.5 * fix submodule
Anyone built from this commit ? Or is this gonna be available in 1.5.1 or later ? |
@djaym7 It's included after 1.5.1, you can use nightly built mxnet to use this operator for example |
Description
Add Deformable Convolution operators and corresponding gluon block.
This is a PR that follows the closed PR: #15552
Checklist
Essentials
Please feel free to remove inapplicable items for your PR.
Changes
Comments