kevinthesun commented on a change in pull request #5588:
URL: https://github.com/apache/incubator-tvm/pull/5588#discussion_r425613386
##########
File path: python/tvm/relay/frontend/tensorflow.py
##########
@@ -1378,9 +1378,11 @@ def _gather_nd():
def _impl(inputs, attr, params, mod):
indices_dims = len(_infer_shape(inputs[1], mod))
indices = _op.transpose(inputs[1], axes=[-1] +
list(range(indices_dims-1)))
+ attr_new = {}
+ attr_new['one_dim_support'] = True
Review comment:
Thanks for clarification. IMO, if topi gather_nd has capability to
handle >= 1d cases, it would be better to put the decision on the frontend.
##########
File path: python/tvm/relay/frontend/tensorflow.py
##########
@@ -1378,9 +1378,11 @@ def _gather_nd():
def _impl(inputs, attr, params, mod):
indices_dims = len(_infer_shape(inputs[1], mod))
indices = _op.transpose(inputs[1], axes=[-1] +
list(range(indices_dims-1)))
+ attr_new = {}
+ attr_new['one_dim_support'] = True
Review comment:
Thanks for clarification. IMO, if topi gather_nd has capability to
handle >= 1d cases, it would be better to put the decision at the frontend.
----------------------------------------------------------------
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]
