How could I get the BLEU score after I run
bash ./inference_scrpts/iwslt_inf.sh path-to-ckpts/ema_0.9999_280000.pt path-to-save-results path-to-ckpts/alpha_cumprod_step_260000.npy
It seems you remove the code for DDIM. Do I have to keep the number of timesteps for inference the same as the one for training?
Hi,
I could successfully train a model on IWSLT De-En. Now I have some questions about inference:
decoder_attention_mask
is not in the args. Should I just comment it out? https://github.com/Yuanhy1997/SeqDiffuSeq/blob/ed56ca480002b89a26ebd16b0257e1aa880f80f1/inference_main.py#L124bash ./inference_scrpts/iwslt_inf.sh path-to-ckpts/ema_0.9999_280000.pt path-to-save-results path-to-ckpts/alpha_cumprod_step_260000.npy