Skip to content
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.

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

[WebGPU] Failed to run Depthwise 2D convolution test with dilations > 1 using DepthwiseConv2D3x3Program #6263

Closed
BruceDai opened this issue Mar 25, 2022 · 3 comments
Assignees
Labels
type:bug Something isn't working

Comments

@BruceDai
Copy link
Contributor

Please make sure that this is a bug. As per our
GitHub Policy,
we only address code/doc bugs, performance issues, feature requests and
build/installation issues on GitHub. tag:bug_template

System information

  • Have I written custom code (as opposed to using a stock example script provided in TensorFlow.js): Yes
  • OS Platform and Distribution (e.g., Linux Ubuntu 16.04): Windows 10, Ubuntu 18.04
  • Mobile device (e.g. iPhone 8, Pixel 2, Samsung Galaxy) if the issue happens on mobile device: No
  • TensorFlow.js installed from (npm or script link): build tfjs-backend-webgpu from source
  • TensorFlow.js version (use command below): 3.14.0
  • Browser version: 101.0.4951.7 (Official Build) dev

Describe the current behavior
Run DepthwiseConv2d test successfully by WebGPU backend as the same as by WebGL backend.

Describe the expected behavior
Failed to run DepthwiseConv2d test by WebGPU backend

Standalone code to reproduce the issue
Provide a reproducible test case that is the bare minimum necessary to generate
the problem. If possible, please share a link to Colab/CodePen/any notebook.
DepthwiseConv2d test use input of shape [1,7,7,4], weights of shape [3,3,4,1], strides=1, pad='same', dataFormat='NHWC', dilations=2

@qjia7 PTAL, thanks.

@BruceDai BruceDai added the type:bug Something isn't working label Mar 25, 2022
@qjia7 qjia7 self-assigned this Mar 25, 2022
@BruceDai
Copy link
Contributor Author

This DepthwiseConv2d issue would lead run DeepLapv3 (dilated) model with incorrect result.

image
image

image

@qjia7
Copy link
Contributor

qjia7 commented Mar 30, 2022

Fixed by #6264

@qjia7 qjia7 closed this as completed Mar 30, 2022
@google-ml-butler
Copy link

Are you satisfied with the resolution of your issue?
Yes
No

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
type:bug Something isn't working
Projects
None yet
Development

No branches or pull requests

2 participants