float division by zero for small datasets

[luiztauffer]

A float division by zero is likely to occur when using small video sizes and large values for batch_size.

[LOGGING STARTED AT: 2024-08-16 11-07-10]2024-08-16 11:07:10.729 INFO  --- [Thread-61 (process_request_thread)] vame.model.rnn_vae : 378 : Train Variational Autoencoder - model name: VAME 

2024-08-16 11:07:10.729 INFO  --- [Thread-61 (process_request_thread)] vame.model.rnn_vae : 387 : Using CUDA
2024-08-16 11:07:10.729 INFO  --- [Thread-61 (process_request_thread)] vame.model.rnn_vae : 388 : GPU active: True
2024-08-16 11:07:10.729 INFO  --- [Thread-61 (process_request_thread)] vame.model.rnn_vae : 389 : GPU used: NVIDIA GeForce RTX 2060
2024-08-16 11:07:10.729 INFO  --- [Thread-61 (process_request_thread)] vame.model.rnn_vae : 437 : Latent Dimensions: 30, Time window: 30, Batch Size: 256, Beta: 1, lr: 0.0005

2024-08-16 11:07:11.442 INFO  --- [Thread-61 (process_request_thread)] vame.model.rnn_vae : 487 : Scheduler step size: 100, Scheduler gamma: 0.20

2024-08-16 11:07:11.442 INFO  --- [Thread-61 (process_request_thread)] vame.model.rnn_vae : 493 : Start training... 
2024-08-16 11:07:11.442 INFO  --- [Thread-61 (process_request_thread)] vame.model.rnn_vae : 87 : Training Model:   0%|          | 0/49 [00:00<?, ?epoch/s]
2024-08-16 11:07:11.803 INFO  --- [Thread-61 (process_request_thread)] vame.model.rnn_vae : 87 : Training Model:   0%|          | 0/49 [00:00<?, ?epoch/s]
2024-08-16 11:07:11.803 ERROR --- [Thread-61 (process_request_thread)] vame.model.rnn_vae : 566 : An error occurred: float division by zero
Traceback (most recent call last):
  File "vame/model/rnn_vae.py", line 502, in train_model
  File "vame/model/rnn_vae.py", line 351, in test
ZeroDivisionError: float division by zero

original issue: EthoML/vame-desktop#48