Skip to content

bug in human matting #3920

@ausk

Description

@ausk

问题确认 Search before asking

Bug描述 Describe the Bug

> /tmp/PaddleSeg/Matting/ppmatting/models/human_matting.py(399)forward()
-> x = F.interpolate(x,
(Pdb) (h_half, w_half)
(1024, 1024)
(Pdb) paddle.stack((h_half, w_half)).squeeze()


--------------------------------------
C++ Traceback (most recent call last):
--------------------------------------
0   paddle::pybind::eager_api_stack(_object*, _object*, _object*)
1   paddle::pybind::GetTensorListFromArgs(std::string const&, std::string const&, _object*, long, bool, phi::distributed::ProcessMesh const*)
2   phi::TypeInfoTraits<phi::TensorBase, phi::distributed::DistTensor>::classof(phi::TensorBase const*)

复现环境 Environment

platform: Linux-5.4.0-216-generic-x86_64-with-glibc2.31
Python: 3.11.8 (main, Feb 26 2024, 21:39:34) [GCC 11.2.0]
Paddle compiled with cuda: False
GCC: gcc (Ubuntu 9.4.0-1ubuntu1~20.04.2) 9.4.0
PaddleSeg: 0.0.0.dev0
PaddlePaddle: 2.6.2
OpenCV: 4.10.0

Bug描述确认 Bug description confirmation

  • 我确认已经提供了Bug复现步骤、代码改动说明、以及环境信息,确认问题是可以复现的。I confirm that the bug replication steps, code change instructions, and environment information have been provided, and the problem can be reproduced.

是否愿意提交PR? Are you willing to submit a PR?

  • 我愿意提交PR!I'd like to help by submitting a PR!

Metadata

Metadata

Assignees

Labels

bugSomething isn't working

Type

No type

Projects

No projects

Milestone

No milestone

Relationships

None yet

Development

No branches or pull requests

Issue actions