You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
For models exported by tao toolkit v4.0 (yolov v4 for my case):
It seems like encoder_image_mean and encoder_image_stddev needs to be set to 0 and 1/255 respectively to get any proper inference (thereby nullifying the normalization). When normalizing image between 0 to 1, TAO exported models never output correct predictions.
Is there any way to turn off normalization by a parameter for encoder node?
The text was updated successfully, but these errors were encountered:
As you've observed, the encoder_image_mean and encoder_image_stddev parameters can be set to 0 and 1/255 respectively to effectively turn the normalization step into a no-op.
We will look into adding a more explicit flag for disabling normalization.
For models exported by tao toolkit v4.0 (yolov v4 for my case):
It seems like
encoder_image_mean
andencoder_image_stddev
needs to be set to 0 and 1/255 respectively to get any proper inference (thereby nullifying the normalization). When normalizing image between 0 to 1, TAO exported models never output correct predictions.Is there any way to turn off normalization by a parameter for encoder node?
The text was updated successfully, but these errors were encountered: