Why two gradient tapes are used?

[NoAchache]

Hello, I was just wondering if instead of this:

with tf.GradientTape() as gen_tape, tf.GradientTape() as disc_tape:

       ....

        gradients_of_generator = gen_tape.gradient(gen_loss, self.GAN.GM.trainable_variables)
        gradients_of_discriminator = disc_tape.gradient(disc_loss, self.GAN.D.trainable_variables)

, you could do this? :

with tf.GradientTape() as tape
       ....

        gradients_of_generator = tape.gradient(gen_loss, self.GAN.GM.trainable_variables)
        gradients_of_discriminator = tape.gradient(disc_loss, self.GAN.D.trainable_variables)

Would that work? In this case, is it not a waste of gpu space to use 2 tapes?

[IIIBlueberry]

Resources held by a GradientTape are released as soon as GradientTape.gradient() is called by default, so he will need two GradientTape to compute both models gradient