Skip to content
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

Jump to bottom

Fix misspelling #1800

Merged
merged 1 commit into from
Dec 17, 2021
Merged

Fix misspelling #1800

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
4 changes: 2 additions & 2 deletions tf2onnx/onnx_opset/nn.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -59,8 +59,8 @@ def get_channels_last_permutation(spatial):

def conv_convert_inputs(ctx, node, with_kernel=False, new_kernel_shape=None,
input_indices=None, output_indices=None, spatial=2):
"""Convert input and kernel from tensorflow to onnx. This maybe require to
to insert transpose ops for input, kernel and output unless they are constants
"""Convert input and kernel from tensorflow to onnx. This may be required to
hwangdeyu marked this conversation as resolved.
Show resolved Hide resolved
insert transpose ops for input, kernel, and output unless they are constants
and we can transpose the constant.
We transpose inputs if they are in NHWC. We always transpose the kernel from
HWNC to NCHW. Outputs are transposed if the format is NHWC.
Expand Down