kevinthesun commented on a change in pull request #5429:
URL: https://github.com/apache/incubator-tvm/pull/5429#discussion_r415237031



##########
File path: include/tvm/relay/op_attr_types.h
##########
@@ -81,10 +81,16 @@ using TOpIsStateful = bool;
  */
 using TNonComputational = bool;
 
+enum ShapeDependantKind {
+  kShapeDependantShape = 0,
+  kShapeDependantData = 1,
+  kShapeDependantBoth = 2,

Review comment:
       
https://github.com/apache/incubator-tvm/pull/4312/files#diff-81885bc0d9c067a058536e5a22ff6b23R108
 strided_slice_shape_func iterates data shape over ndim. In reshape shape func, 
I think you can iterate through newshape.shape[0], which can also be put inside 
const_range. In the worst case, you can always allocate a buffer to store data 
shape. And this would be exactly the same as you pass data shape tensor into it.




----------------------------------------------------------------
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.

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


Reply via email to