conv_encoder function Differs from Beta-VAE Paper?

[nmichlo]

disentanglement_lib/disentanglement_lib/methods/shared/architectures.py

Lines 148 to 150 in 86a644d

	Based on row 3 of Table 1 on page 13 of "beta-VAE: Learning Basic Visual
	Concepts with a Constrained Variational Framework"
	(https://openreview.net/forum?id=Sy2fzU9gl)

The Beta-VAE paper states that all the convolutional kernels are of size 4x4. I am not sure if it is intended that the 3rd and 4th convolutional layers in the conv_encoder function reduce these kernel sizes to 2x2?

disentanglement_lib/disentanglement_lib/methods/shared/architectures.py

Lines 184 to 201 in 86a644d

	e3 = tf.layers.conv2d(
	inputs=e2,
	filters=64,
	kernel_size=2,
	strides=2,
	activation=tf.nn.relu,
	padding="same",
	name="e3",
	)
	e4 = tf.layers.conv2d(
	inputs=e3,
	filters=64,
	kernel_size=2,
	strides=2,
	activation=tf.nn.relu,
	padding="same",
	name="e4",
	)

[nmichlo]

An open issue already exists. Sorry. #23