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
We have used Keras-cv to create a custom image classification mobile. We have used the keras_cv.models.ImageClassifier.from_preset("efficientnetv2_b0_imagenet"...) model.
We want to deploy it using TensorFlow JS. We have run the TFJS Converter to convert it to a TFJS graph model. However when we load it, TFJS reports an error Unknown layer: ImageClassifier.
This appears to be a custom Keras CV layer. Is it possible to port this layer to TFJS? Or provide some hints on how best to export a keras-cv model for use in TFJS?
reacted with thumbs up emoji reacted with thumbs down emoji reacted with laugh emoji reacted with hooray emoji reacted with confused emoji reacted with heart emoji reacted with rocket emoji reacted with eyes emoji
-
Hi,
We have used Keras-cv to create a custom image classification mobile. We have used the
keras_cv.models.ImageClassifier.from_preset("efficientnetv2_b0_imagenet"...)
model.We want to deploy it using TensorFlow JS. We have run the TFJS Converter to convert it to a TFJS graph model. However when we load it, TFJS reports an error
Unknown layer: ImageClassifier
.This appears to be a custom Keras CV layer. Is it possible to port this layer to TFJS? Or provide some hints on how best to export a keras-cv model for use in TFJS?
Thanks a million!
Beta Was this translation helpful? Give feedback.
All reactions