How to use Keras.backend in TensorflowJS ?

[jackfrost1411]

The below code snippet is written in python Keras.

from keras import backend as K
...

layer_name ='Mask'
NewInput = model.get_layer(layer_name).output
visualization = K.function([model.input], [NewInput])
...

I want to write this code in Tensorflow.JS .. I am unable to find the right lines in TensorflowJS for this code snippet.

Can anyone help ?!

[jackfrost1411]

I had to reopen this issue as I couldn't find the solution anywhere.. Is there an alternative for doing the above task?

[pyu10055]

There some of the concept of backend in the tfjs-core package, what is the particular thing you want to do on the keras backend package?

[jackfrost1411]

There some of the concept of backend in the tfjs-core package, what is the particular thing you want to do on the keras backend package?

I have trained a model Keras that ends with a softmax layer. But I want to get output from an intermediate Convolution layer. How can I do this?

[pyu10055]

You can access layers using tfjs-layers function model, example is here
https://stackoverflow.com/questions/50942677/tensorflowjs-how-to-get-inner-layer-output-in-a-cnn-prediction/51316516#51316516

[google-ml-butler]

This issue has been automatically marked as stale because it has not had recent activity. It will be closed in 7 days if no further activity occurs. Thank you.

[google-ml-butler]

Closing as stale. Please @mention us if this needs more attention.

[google-ml-butler]

Are you satisfied with the resolution of your issue?
Yes
No