Validation takes very long time (10x) about nast HOT 4 CLOSED

@thangld201
I am not sure but here are some possible causes:

• BLEU calculation may be slow.
• A classifier is used to determine the style.

To eliminate these effects, can you measure the time between this lines?

from nast.

@hzhwcmhf , I found that Line 334: predict_res.append(self.param.volatile.cls.predict_str(sents)) was the cause (took up 99% of the time). I will dive a bit more....not sure why this is slow...

from nast.

@hzhwcmhf , I found that Line 334: predict_res.append(self.param.volatile.cls.predict_str(sents)) was the cause (took up 99% of the time). I will dive a bit more....not sure why this is slow...

It runs a classifier. Maybe check whether this classifier is on gpu?

from nast.

It runs a classifier. Maybe check whether this classifier is on gpu?

Yeah, you are right, self.param.volatile.cls.net was on cpu.

In NAST/styletransformer/run_cls.py, Line 47-69:

L47: parser.add_argument('--cuda', action="store_true", help='Use cuda (gpu).')
...
L69: args.cuda = "cuda" if cargs.cuda else "cpu"

since cargs was parsed from Line 64 in NAST/styletransformer/main.py i.e.
cls_param.args = run_cls.run("--dryrun", "--restore", args.clsrestore) # <----- do not have cuda flags

so I changed Line 64 to
cls_param.args = run_cls.run("--cuda", "--dryrun", "--restore", args.clsrestore)

And it worked! Validation now takes less than half a minute (Yelp)!
Thank you!

from nast.