[GitHub] [tvm] masahi commented on a change in pull request #10421: [BYOC-DNNL] Support DNNL optimal layout

[GitBox <gi...@apache.org>]

masahi commented on a change in pull request #10421:
URL: https://github.com/apache/tvm/pull/10421#discussion_r819224145



##########
File path: src/relay/op/nn/convolution.cc
##########
@@ -244,7 +250,12 @@ bool Conv2DRel(const Array<Type>& types, int num_inputs, const Attrs& attrs,
     ICHECK_EQ(param->dilation.size(), 2);
     Array<IndexExpr> wshape;
 
-    if (is_depthwise) {
+    if (is_group) {
+      // infer weight's shape for group convolution
+      wshape = {{param->groups, indexdiv(param->channels, param->groups),
+                 indexdiv(dshape_nchw[1], param->groups), param->kernel_size[0],
+                 param->kernel_size[1]}};

Review comment:
       I'm pretty sure we already support group convolution and this one looks unusual. If this is DNNL specific, can you come up with a better name than `is_group`?




-- 
This is an automated message from the Apache Git Service.
To respond to the message, please log on to GitHub and use the
URL above to go to the specific comment.

To unsubscribe, e-mail: commits-unsubscribe@tvm.apache.org

For queries about this service, please contact Infrastructure at:
users@infra.apache.org