ANSHUMAN87 commented on a change in pull request #6889:
URL: https://github.com/apache/incubator-tvm/pull/6889#discussion_r526079596
##########
File path: src/relay/op/nn/sparse.cc
##########
@@ -85,10 +117,11 @@ RELAY_REGISTER_OP("nn.sparse_dense")
)code" TVM_ADD_FILELINE)
.set_attrs_type<SparseDenseAttrs>()
.set_num_inputs(4)
- .add_argument("data", "nD Tensor", "Input data.")
- .add_argument("weight_data", "1D Tensor", "Weight data matrix.")
- .add_argument("weight_indices", "1D Tensor", "Weight indices matrix.")
- .add_argument("weight_indptr", "1D Tensor", "Weight indptr matrix.")
+ .add_argument("input_tensor1", "nD Tensor",
Review comment:
@tkonolige : Sorry for late response. I think somehow i missed your last
reply.
I agree with the naming you suggested, but the issue here is one tensor
represents 2 different use case altogether.
For example:
"input_tensor2" => "weight_data_or_data_indices"
So it can be sparse_data in one case and sparse_indices in another case.
So i am wondering what is the best way to merge both representation ?
----------------------------------------------------------------
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
