Improve too slow / too many overlapping of networks' unit tests

[Warvito]

Currently the networks are taking significant amount of time in the unit tests. It can be improved by remove redundancy and using smaller networks in the tests.

For example:
For the AutoencoderKL

GenerativeModels/tests/test_autoencoderkl.py

Line 38 in dd08bff

TEST_CASE_1 = [

and

GenerativeModels/tests/test_autoencoderkl.py

Line 23 in dd08bff

TEST_CASE_0 = [

are building similar networks with same components, having 2 test cases that do not increase coverage.

Other example:
For the VQVAE

GenerativeModels/tests/test_vqvae.py

Line 25 in dd08bff

[1, 3], # Batch size

is testing the network forward using a single image or 3 example in the minibatch. These 2 test cases does not test different methods of the network or different conditions, and this do not test any part added in the VQVAE class.

[ericspod]

Smaller networks and smaller input images would both help. Unless there's a minimum size for a network we should make images smaller, eg. we don't need 256 sized images necessarily.