Skip to content

[TFLite][Frontend] Support quantized ARG_MIN #15922

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Closed
tlopex wants to merge 3 commits into from
Closed

[TFLite][Frontend] Support quantized ARG_MIN #15922

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
3 commits
Select commit Hold shift + click to select a range
2c6da0c
add quantized arg_min
tlopex Oct 12, 2023
971002e
add tests for quantized arg_min
tlopex Oct 12, 2023
87fab6b
delete the annotation
tlopex Oct 12, 2023
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
4 changes: 0 additions & 4 deletions python/tvm/relay/frontend/tflite.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -1898,10 +1898,6 @@ def _convert_arg_min_max(self, relay_op, op):

def convert_arg_min(self, op):
"""Convert TFLite ARG_MIN"""
if self.is_quantized(op):
raise tvm.error.OpNotImplemented(
"TFlite quantized ARG_MIN operator is not supported yet."
)
return self._convert_arg_min_max(_op.argmin, op)

def convert_arg_max(self, op):
Expand Down
2 changes: 1 addition & 1 deletion tests/python/frontend/tflite/test_forward.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -3261,9 +3261,9 @@ def test_forward_arg_min_max():
"""Arg min max"""
# test quantized
for data in [np.array(np.random.uniform(-100, 100, (3, 4)), dtype=np.uint8)]:
# There is no quantized version of ArgMin
for axis in [None, 0, 1, -1]:
_test_arg_min_max(math_ops.argmax, data, axis, True)
_test_arg_min_max(math_ops.argmin, data, axis, True)

for data in [np.array(np.random.uniform(-100, 100, (3, 4)), dtype=np.float32)]:
for axis in [None, 0, 1, -1]:
Expand Down