Skip to content

Remove double transpose for Conv2DBatchnorm #965

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

Open
wants to merge 2 commits into
base: main
Choose a base branch
from
Open

Remove double transpose for Conv2DBatchnorm #965

Changes from all commits
Commits
Show all changes
2 commits
Select commit Hold shift + click to select a range
09564c3
remove double transpose
jmitrevs Feb 8, 2024
6262ee9
Merge remote-tracking branch 'upstream/main' into transpose_to_backend
jmitrevs Aug 21, 2024
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
13 changes: 2 additions & 11 deletions hls4ml/model/layers.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -591,17 +591,8 @@ def _get_folded_weights(self):
def initialize(self):
super().initialize()
folded_weights, folded_bias = self._get_folded_weights()
if self.model.config.is_resource_strategy(self) and self.model.config.backend.name in [
'Vivado',
'VivadoAccelerator',
'Catapult',
]:
self.weights['weight'].data_unquantized = np.transpose(folded_weights, axes=[3, 0, 1, 2])
self.weights['weight'].data = self.get_attr('weight_quantizer')(self.weights['weight'].data_unquantized)

else:
self.weights['weight'].data_unquantized = folded_weights
self.weights['weight'].data = self.get_attr('weight_quantizer')(folded_weights)
self.weights['weight'].data_unquantized = folded_weights
self.weights['weight'].data = self.get_attr('weight_quantizer')(folded_weights)
self.weights['bias'].data_unquantized = folded_bias
bias_q = self.get_attr('bias_quantizer')
if bias_q is not None:
Expand Down