vvchernov commented on a change in pull request #8709:
URL: https://github.com/apache/tvm/pull/8709#discussion_r697456678
##########
File path: python/tvm/relay/frontend/pytorch.py
##########
@@ -148,29 +146,13 @@ def infer_type(self, node, mod=None):
if node in self.types:
return self.types[node]
- if isinstance(node, tvm.relay.Var):
- return node.type_annotation
-
- tf = _TypeFinder(types=self.types)
- new_node = tf.visit(node)
- fn = _function.Function(list(tf.vars.values()), new_node)
- new_mod = IRModule({"main": fn})
- if mod is not None:
- new_mod.update(mod)
- new_mod = transform.RemoveUnusedFunctions()(new_mod)
- new_mod = transform.InferType()(new_mod)
- entry = new_mod["main"]
- ty = entry.body.checked_type
- self.types[node] = ty
- return self.types[node]
Review comment:
Thank you @t-vi ! I think other frontends needs incremental type
inference. It is simply to understand by counting all calls of infer_type and
infer_shape methods in frontend (~100 for onnx). In general frontends have many
similarities and it moved me try to unify some duplicates. This task is not so
simple as seemed before I will try to study all details around and do it
carefully.
--
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-unsubscr...@tvm.apache.org
For queries about this service, please contact Infrastructure at:
us...@infra.apache.org
