Remove optimization_for_gpu_delegate flag for TF exports (#21482)
Signed-off-by: Mohammed Yasin <32206511+Y-T-G@users.noreply.github.com> Co-authored-by: UltralyticsAssistant <web@ultralytics.com>
This commit is contained in:
parent
9dccbd4229
commit
dcc8becf9b
@ -124,6 +124,9 @@ Francesco.mttl@gmail.com:
|
||||
Fruchtzwerg94@users.noreply.github.com:
|
||||
avatar: https://avatars.githubusercontent.com/u/29866610?v=4
|
||||
username: Fruchtzwerg94
|
||||
aaurelions@gmail.com:
|
||||
avatar: null
|
||||
username: null
|
||||
abirami.vina@gmail.com:
|
||||
avatar: https://avatars.githubusercontent.com/u/25847604?v=4
|
||||
username: abirami-vina
|
||||
|
||||
@ -1014,7 +1014,6 @@ class Exporter:
|
||||
enable_batchmatmul_unfold=True, # fix lower no. of detected objects on GPU delegate
|
||||
output_signaturedefs=True, # fix error with Attention block group convolution
|
||||
disable_group_convolution=self.args.format in {"tfjs", "edgetpu"}, # fix error with group convolution
|
||||
optimization_for_gpu_delegate=True,
|
||||
)
|
||||
YAML.save(f / "metadata.yaml", self.metadata) # add metadata.yaml
|
||||
|
||||
|
||||
Loading…
x
Reference in New Issue
Block a user