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

use tf.shape instead of .shape for dynamic axes in InstanceNormalization #771

Open
wants to merge 12 commits into
base: main
Choose a base branch
from
Open

use tf.shape instead of .shape for dynamic axes in InstanceNormalization #771

Changes from 7 commits
Commits
Show all changes
12 commits
Select commit Hold shift + click to select a range
3bc773c
use tf.shape instead of .shape for dynamic axes
masakistan Sep 19, 2020
7b27f5d
Add model stepping test for Mnist (#734)
chinhuang007 Sep 23, 2020
87ea741
Merge branch 'master' into fix_instance_norm
masakistan Sep 29, 2020
de3d673
Merge branch 'master' into fix_instance_norm
masakistan Oct 3, 2020
cea3239
Merge branch 'master' into fix_instance_norm
masakistan Oct 8, 2020
24877e8
Merge branch 'master' into fix_instance_norm
masakistan Oct 15, 2020
610feae
Merge branch 'master' into fix_instance_norm
masakistan Nov 1, 2020
9ef09b8
use onnx-tf tf_shape instead of tf.shape
masakistan Nov 12, 2020
56f239a
Merge branch 'master' into fix_instance_norm
masakistan Nov 12, 2020
1e27b6e
Merge branch 'master' into fix_instance_norm
masakistan Nov 13, 2020
efb9561
Merge branch 'master' into fix_instance_norm
chinhuang007 Dec 15, 2020
31f63d1
Merge branch 'master' into fix_instance_norm
chinhuang007 Dec 17, 2020
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
2 changes: 1 addition & 1 deletion onnx_tf/handlers/backend/instance_normalization.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -31,7 +31,7 @@ def _common(cls, node, **kwargs):
beta = tensor_dict[node.inputs[2]]

inputs = tensor_dict[node.inputs[0]]
inputs_shape = inputs.shape
inputs_shape = tf.shape(inputs)
masakistan marked this conversation as resolved.
Show resolved Hide resolved
inputs_rank = inputs.shape.ndims

moments_axes = list(range(inputs_rank))[2:]
Expand Down