Skip to content

[TFLite] Add support for quantized mirror pad #16243

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

Merged
merged 1 commit into from
Dec 15, 2023
Merged

[TFLite] Add support for quantized mirror pad #16243

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
1 commit
Select commit
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
6 changes: 0 additions & 6 deletions python/tvm/relay/frontend/tflite.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -2677,12 +2677,6 @@ def convert_mirror_pad(self, op):
except ImportError:
raise ImportError("The tflite package must be installed")

# the quantized form MirrorPad is not yet implemented in TFLite.
if self.is_quantized(op):
raise tvm.error.OpNotImplemented(
"TFlite quantized MIRROR_PAD operator is not supported yet."
)

input_tensors = self.get_input_tensors(op)
assert len(input_tensors) == 2, "input tensors length should be 2"

Expand Down
24 changes: 23 additions & 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 @@ -3436,7 +3436,13 @@ def _test_pad(data, mode="CONSTANT", quantized=False):
inq_data[0], ops.convert_to_tensor(data[1], dtype=data[1].dtype), mode=mode
)
compare_tflite_with_tvm(
[data[0]], ["inq_0:0"], inq_data, [out], quantized=True, input_range=input_range
[data[0]],
["inq_0:0"],
inq_data,
[out],
quantized=True,
input_range=input_range,
experimental_new_converter=True,
)
else:
out = array_ops.pad(
Expand Down Expand Up @@ -3506,6 +3512,22 @@ def test_forward_pad():
],
quantized=True,
)
_test_pad(
[
np.arange(0, 256, dtype=np.uint8).reshape((1, 256)),
np.array([[1, 1], [2, 2]], dtype=np.int32),
],
quantized=True,
mode="SYMMETRIC",
)
_test_pad(
[
np.arange(0, 256, dtype=np.uint8).reshape((1, 256)),
np.array([[0, 0], [2, 2]], dtype=np.int32),
],
quantized=True,
mode="REFLECT",
)


#######################################################################
Expand Down