zhangyi_1015

您好。当我修改beam_size=2的时候，出现了错误。

17

File "train.py", line 224, in train(opt) File "train.py", line 168, in train val_loss, predictions, lang_stats = eval_utils.eval_split(dp_model, crit, loader, eval_kwargs) File "/media/enjoy/32F872CFF87290B9/CODE/self-critical-beam.pytorch-master/eval_utils.py", line 107, in eval_split print('\n'.join([utils.decode_sequence(loader.get_vocab(), _['seq'].unsqueeze(0))[0] for _...

a question about download pretrained 'conditional' model

1

Sorry to bother you. But when I download the pre-train models form Tencent. There only has four folder. 'imagenet', 'places', 'celebA', 'bedroom', not including 'conditional' model you have mentioned? Can...