masahi commented on a change in pull request #10691:
URL: https://github.com/apache/tvm/pull/10691#discussion_r831644935
##########
File path: tests/python/frontend/tensorflow/test_forward.py
##########
@@ -5607,7 +5611,10 @@ def _test_unique_with_counts(n, dtype, is_dyn):
)
else:
compare_tf_with_tvm(
- None, "", ["UniqueWithCounts:0", "UniqueWithCounts:1",
"UniqueWithCounts:2"]
+ np_data,
+ "",
+ ["UniqueWithCounts:0", "UniqueWithCounts:1",
"UniqueWithCounts:2"],
+ mode="vm",
Review comment:
`Unique` is naturally a dynamic op, but for some reason this test was
running on the graph runtime and it happens to be working just because the
dynamic input is bound to a constant tensor before `relay.build(...)`. So the
test was effectively running `unique(const_tensor)`, which is not really
useful.
##########
File path: tests/python/frontend/tensorflow/test_forward.py
##########
@@ -5607,7 +5611,10 @@ def _test_unique_with_counts(n, dtype, is_dyn):
)
else:
compare_tf_with_tvm(
- None, "", ["UniqueWithCounts:0", "UniqueWithCounts:1",
"UniqueWithCounts:2"]
+ np_data,
+ "",
+ ["UniqueWithCounts:0", "UniqueWithCounts:1",
"UniqueWithCounts:2"],
+ mode="vm",
Review comment:
`Unique` is naturally a dynamic op, but for some reason this test was
running on the graph runtime and it happens to be working just because the
dynamic input is bound to a constant tensor before `relay.build(...)`. So the
test was effectively running `unique(const_tensor)`, which is not really
useful.
--
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: [email protected]
For queries about this service, please contact Infrastructure at:
[email protected]
