deep-learning-with-python-notebooks
deep-learning-with-python-notebooks copied to clipboard
8.4.3 The kl_loss in Listing 8.26 seems not correct
Here kl_loss formulation uses -5e-4 * K.mean(…). However, according to the essay, it should be -0.5 * K.sum(…). Here are two implementations: 1. from Keras website: https://keras.io/examples/variational_autoencoder/ from PyTorch examples: https://github.com/pytorch/examples/blob/master/vae/main.py