[GitHub] [tvm] wzh99 commented on a diff in pull request #11728: [Relay] Implement `SoftmaxRel` for softmax operators.

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

wzh99 commented on code in PR #11728:
URL: https://github.com/apache/tvm/pull/11728#discussion_r897888041


##########
src/relay/op/nn/nn.cc:
##########
@@ -399,6 +399,27 @@ where :math:`*` is an channelwise multiplication for each sample in the batch.
 // relay.softmax
 TVM_REGISTER_NODE_TYPE(SoftmaxAttrs);
 
+bool SoftmaxRel(const Array<Type>& types, int num_inputs, const Attrs& attrs,
+                const TypeReporter& reporter) {
+  ICHECK_EQ(types.size(), 2);
+  const auto* data = types[0].as<TensorTypeNode>();
+  if (data == nullptr) return false;
+
+  const SoftmaxAttrs* param = attrs.as<SoftmaxAttrs>();
+  ICHECK(param != nullptr);
+  int axis = param->axis;
+  int ndim = static_cast<int>(data->shape.size());
+  if (axis >= ndim || axis < -ndim) {
+    reporter->GetDiagCtx().EmitFatal(Diagnostic::Error(reporter->GetSpan())
+                                     << "The axis is not in range [" << -ndim << ", " << ndim

Review Comment:
   I have modified the error message as you suggest.



-- 
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