tqchen commented on a change in pull request #5770:
URL: https://github.com/apache/incubator-tvm/pull/5770#discussion_r441826518
##########
File path: python/tvm/contrib/graph_runtime.py
##########
@@ -162,7 +162,11 @@ def set_input(self, key=None, value=None, **params):
keys = list(params.keys())
keys.sort(key=lambda x: -np.prod(params[x].shape))
for k in keys:
- self._get_input(k).copyfrom(params[k])
+ # TODO(zhiics) Skip the weights for submodule in a better way.
+ # We could get all inputs required by graphruntime first,
+ # we should use MetadataModule for initialization.
Review comment:
This part of the logic seems to be a bit too hacky, cryptic Shall we
simply skip inside the set_params instead? If the weights are emedded in the
metadata, do we still allow overriding of weights?
----------------------------------------------------------------
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:
[email protected]
