Result with enable bernoulli

[mahmoudEltaher]

Hi, @paschalidoud ,

I try to train the model by Running a command :
python scripts/train_network.py ../../03001627_simple_chair/ tmp/ --epochs 50000 --use_sq --lr 1e-4 --n_primitives 20 --architecture tulsiani --dataset_type shapenet_v2 --use_chamfer --run_on_gpu --batch_size 4

then I test the model
python scripts/forward_pass.py demo/03001627/ tmp/ --model_tag "94ceeee26248a275e8e2378aa23e4253" --n_primitives 20 --weight_file tmp/I77FAV1YI_without_Bernoulli/model_49999 --use_sq --dataset_type shapenet_v2

The result is good as following.

But once I train_with_bernoulli, the result is not good as following:

and I notice also that the sparsity regulaizer is always zero , so it is not have effect on the training, what is the effected of this regulizer on the training.
I wonder if I miss something when I apply the model with train_with_bernoulli.

waiting for you kindly advice.