Skip to content

Conversation

@optima2005
Copy link
Contributor

This is a part of attempts to implement #4009
This PR is to add conv3d to TF frontend.

@masahi

@masahi masahi self-assigned this Dec 31, 2019
@masahi masahi merged commit 1ef1605 into apache:master Jan 1, 2020
@masahi
Copy link
Member

masahi commented Jan 1, 2020

Thanks @optima2005


def _callback(op):
if op.tag == 'conv3d_ndhwc':
schedule_direct_3d_cuda(cfg, s, op.output(0))
Copy link
Member

@icemelon icemelon Jan 6, 2020

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

@optima2005 @masahi
I have one question here. It seems that schedule_direct_3d_cuda only supports NCDHW. So here invoking schedule_direct_3d_cuda looks incorrect. Could you double check on this? correct me if I'm wrong.

Copy link
Member

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

ping @optima2005 can you comment?

Copy link
Contributor Author

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

@icemelon9 You are correct. I made a mistake here. Sorry about that.
Just like NHWC for conv2d, The NDHWC layout conv3d won't be supported for cuda. So the schedule won't be needed. I would remove it by raising a new PR.

alexwong pushed a commit to alexwong/tvm that referenced this pull request Feb 26, 2020
* [FRONTEND][TF] Add conv3d

* fix high rtol
alexwong pushed a commit to alexwong/tvm that referenced this pull request Feb 28, 2020
* [FRONTEND][TF] Add conv3d

* fix high rtol
zhiics pushed a commit to neo-ai/tvm that referenced this pull request Mar 2, 2020
* [FRONTEND][TF] Add conv3d

* fix high rtol
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Labels

None yet

Projects

None yet

Development

Successfully merging this pull request may close these issues.

3 participants