[GitHub] [tvm] lixiaoquan commented on pull request #9723: [Frontend] Add Span filling for frontends to Relay

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

lixiaoquan commented on pull request #9723:
URL: https://github.com/apache/tvm/pull/9723#issuecomment-992346440


   I just feel that in `one to many` case, the original tensor/layer name should be attached to the last node in the group. Because that's where the computational result (and tensor type) matches between original graph and relay IR. And we may need to find the last node of a group frequently, keep original layer's name there can make it easier.
   
   For example, a LSTM can become thousands of nodes in relay IR. If its name is not attached to the last, we'll have to try to search layer_DERIVED_xxxx many times to find the end.
   
   ```text
   def @main(%input: Tensor[(?, ?, 3, 1), float32]) {
   %10 = shape_of(%input, dtype="int32") /* Shape /;
   %11 = strided_slice(%10, begin=[0], end=[1], strides=[1], axes=None) / strided_slice_PART_0) /;
   %12 = squeeze(%11) / strided_slice /;
   %13 = expand_dims(%12, axis=0) / stack_PART_0 /;
   %14 = expand_dims(3, axis=0) / stack_PART_1 /;
   %15 = expand_dims(3, axis=0) / stack_PART_2 /;
   %16 = (%13, %14, %15) / stack_PART_3 /;
   %17 = concatenate(%16) / stack /;
   dyn.reshape(%input, %17, newshape=[]) / output */
   }
   ```
   


-- 
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