mxnet example error

[NanyangYe]

Dear all:

I have found an error when running fine-tuning pre-trained example (http://mxnet.io/how_to/finetune.html) with the latest mxnet version. Is there any way to fix it?

Traceback (most recent call last):
File "FineTune.py", line 76, in
mod_score = fit(new_sym, new_args, aux_params, train, val, batch_size, num_gpus)
File "FineTune.py", line 66, in fit
return mod.score(val)
TypeError: score() takes at least 3 arguments (2 given)

[devaib]

Hello, @lincolnBush.
First,

from mxnet import metric

then,

metric = mx.metric.Accuracy()
return mod.score(val, metric)

There are also other metrics for you to choose from.

[szha]

This issue is closed due to lack of activity in the last 90 days. Feel free to reopen if this is still an active issue. Thanks!