def get_eval_parameters(opt, force_categories=None):
evaluate = DD()
if opt.eval_sampler == "beam":
evaluate.bs = opt.beam_size
elif opt.eval_sampler == "greedy":
evaluate.bs = 1
elif opt.eval_sampler == "topk":
evaluate.k = opt.topk_size
evaluate.smax = opt.gen_seqlength
evaluate.sample = opt.eval_sampler
evaluate.numseq = opt.num_sequences
evaluate.gs = opt.generate_sequences
evaluate.es = opt.evaluate_sequences
if opt.dataset == "atomic":
if "eval_categories" in opt and force_categories is None:
evaluate.categories = opt.eval_categories
else:
evaluate.categories = force_categories
return evaluate
def get_training_parameters(opt):
train = DD()
static = DD()
static.exp = opt.exp
static.seed = opt.random_seed
# weight decay
static.l2 = opt.l2
static.vl2 = True
static.lrsched = opt.learning_rate_schedule # 'warmup_linear'
static.lrwarm = opt.learning_rate_warmup # 0.002
# gradient clipping
static.clip = opt.clip
# what loss function to use
static.loss = opt.loss
dynamic = DD()
dynamic.lr = opt.learning_rate # learning rate
dynamic.bs = opt.batch_size # batch size
# optimizer to use {adam, rmsprop, etc.}
dynamic.optim = opt.optimizer
# rmsprop
# alpha is interpolation average
static.update(opt[dynamic.optim])
train.static = static
train.dynamic = dynamic
return train