errors in step 2 Run_VAE_Models.py

[ynpan910]

Hi, thank you for the great work. I was using the pancreas dataset you provided to run and learn the model.

However, in step 2, I came across this error:

---> 63 kl_loss = - 0.5 * K.sum(1 + z_log_var - K.square(z_mean) - K.exp(z_log_var), axis=-1)
65 return K.mean(reconstruction_loss + (K.get_value(beta) * kl_loss))

ValueError: Tried to convert 'x' to a tensor and failed. Error: A KerasTensor cannot be used as input to a TensorFlow function. A KerasTensor is a symbolic placeholder for a shape and dtype, used when constructing Keras Functional models or Keras Functions. You can only use it as input to a Keras layer or a Keras operation (from the namespaces keras.layers and keras.operations). You are likely doing something like:

x = Input(...)
...
tf_fn(x)  # Invalid.

What you should do instead is wrap tf_fn in a layer:

class MyLayer(Layer):
    def call(self, x):
        return tf_fn(x)

x = MyLayer()(x)

My code is: %run -i ./MODEL_TRAININGS/Run_VAE_Models.py PANCREAS 5 0 100

TensorFlow version: 2.18.0
Keras version: 3.7.0

Wondering if you could provide some instructions on how to solve it. Thank you in advance!

[ynpan910]

Nevermind! I got it solved by putting this

from tensorflow.python.framework.ops import disable_eager_execution
disable_eager_execution()

Thanks anyway!