how to return NDCG as a metric

[Lulu20220]

Hello,

I am following the tutorial here https://www.tensorflow.org/recommenders/examples/dcn to build a dcn model, but I want to have ndcg as a metric. Then I did
model.compile(optimizer='sgd', metrics=[tfr.keras.metrics.NDCGMetric()])

but still not returning ndcg.

Could someone guide me through here please?

[rlcauvin]

Which metrics is it outputting? RMSE?

[patrickorlando]

@Lulu20220 The custom model defined in the tutorial overrides the default keras train and test steps so passing a metric to compile will not work.
You need to pass the metric object to the the Ranking task defined in the DCN model here.