-
Notifications
You must be signed in to change notification settings - Fork 3.5k
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
[FRONTEND][TF] Add conv3d #4604
Conversation
Thanks @optima2005 |
|
||
def _callback(op): | ||
if op.tag == 'conv3d_ndhwc': | ||
schedule_direct_3d_cuda(cfg, s, op.output(0)) |
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.
@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.
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.
ping @optima2005 can you comment?
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.
@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.
* [FRONTEND][TF] Add conv3d * fix high rtol
* [FRONTEND][TF] Add conv3d * fix high rtol
* [FRONTEND][TF] Add conv3d * fix high rtol
This is a part of attempts to implement #4009
This PR is to add conv3d to TF frontend.
@masahi