nsample missing arguments

[eric-le-12]

Hi during running your code, i was unexpectedly see an error due to missing arguments

File "/notebooks/slamp/helpers.py", line 362, in eval_step
nsample = opt.nsample

File args.py doesnt have any definition about nsample, what does nsample mean?
I suppose it should be the number of samples per batch in evaluation which means eval batch size
Thanks for your reading

[kaanakan]

Hi,

Thank you for your interest in our work. In the literature, the stochastic models generate more than one sample because the samples differ because of the latent variables. nsample refers to the number of samples to generate for each example in the test/validation set.

Since it is used in the evaluation code, the evaluation code contains that nsample argument.

slamp/evaluate.py

Line 67 in 7c47e6b

parser.add_argument('--nsample', type=int, default=100, help='number of samples')

However, if you encounter that error while training the model, then we need to fix that issue by adding nsample to args.py.

Best regards,
Kaan