I have a trained model,and load it in the follow way. Since I have custom loss.

I am working with a simple TensorFlow model given by

Is there a way to attach the USE as an embedding layer to a Recursive Neural Network (RNN) or a Bi-directional RNN? I got a value error trying to add it to a Sequential model. I am open to using the functional model construction syntax, e.g.

So I am trying to install tensorflow on Linux Machine(Ubuntu 22.04LTS) and I have gone tru all steps in the install page (https://www.tensorflow.org/install/pip) but I am still getting this error.

I’ve been trying to balance my data using the sample_from_datasets method but sometimes I get the following error :

I need to calculate the exponential moving average on a tensor inside of a custom loss function but searching on the internet it looks like tensorflow only supports calculating the moving average on a model’s parameters.

I have list of files (X_files and Y_files) containing numpy arrays of shape N x … and N x …, where N is a sample dimension. I can load them in a tensorflow dataset like this:

I have list of files (X_files and Y_files) containing numpy arrays of shape N x … and N x …, where N is a sample dimension. I can load them in a tensorflow dataset like this: