You are viewing a plain text version of this content. The canonical link for it is here.
Posted to commits@tvm.apache.org by lm...@apache.org on 2021/01/22 23:57:26 UTC

[tvm] branch main updated: [AutoScheduler] Fix conv3d's op strategy for auto-scheduler (#7328)

This is an automated email from the ASF dual-hosted git repository.

lmzheng pushed a commit to branch main
in repository https://gitbox.apache.org/repos/asf/tvm.git


The following commit(s) were added to refs/heads/main by this push:
     new 3ec67f0  [AutoScheduler] Fix conv3d's op strategy for auto-scheduler (#7328)
3ec67f0 is described below

commit 3ec67f0b4b871be7b174d71dc1b0f60bed984d22
Author: Lianmin Zheng <li...@gmail.com>
AuthorDate: Fri Jan 22 15:56:53 2021 -0800

    [AutoScheduler] Fix conv3d's op strategy for auto-scheduler (#7328)
---
 python/tvm/relay/op/strategy/x86.py | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/python/tvm/relay/op/strategy/x86.py b/python/tvm/relay/op/strategy/x86.py
index 9e3e191..edfaaee 100644
--- a/python/tvm/relay/op/strategy/x86.py
+++ b/python/tvm/relay/op/strategy/x86.py
@@ -304,7 +304,7 @@ def conv3d_strategy_cpu(attrs, inputs, out_type, target):
         # or packed layouts.
         if layout == "NCDHW":
             strategy.add_implementation(
-                wrap_compute_conv3d(topi.nn.conv3d_ncdhw, need_auto_scheduler_layout=True),
+                wrap_compute_conv3d(topi.nn.conv3d_ncdhw),
                 naive_schedule,
                 name="conv3d_ncdhw.x86",
             )