AzizIlyosov comments

Results 5 comments of


                                            AzizIlyosov

Has anyone implemented retrieval model in ways other than 2 tower model?

@amit-timalsina I guess, that model is implemented in softmax model section of this [colab](https://colab.research.google.com/github/google/eng-edu/blob/main/ml/recommendation-systems/recommendation-systems.ipynb?utm_source=ss-recommendation-systems&utm_campaign=colab-external&utm_medium=referral&utm_content=recommendation-systems#scrollTo=4OKzworlo4ue)

Question about the loss of model.evaluate

I have same problem too

Which metric of model should I focus to stop training. Validation top N accuracy or validation loss ?

@patrickorlando thanks for your answer. Validation/training was randomly split with 20/80 ratio randomly . The thing I am wondering is that why accuracy is increasing parallelly with epoch validation loss?

notebook not find

I think you can find them from here : [multitask recommendation ](https://www.tensorflow.org/recommenders/examples/multitask) , [side features ](https://www.tensorflow.org/recommenders/examples/featurization)

[Question] How to create embeddings from one-hot-encoded features?

I think it is not good idea to use embedding for low dimensional features , just make one-hot encoding vector using CategoryEncoding ``` self.make_categorical_gender = tf.keras.Sequential([ tf.keras.layers.StringLookup( vocabulary=number_of_tokens, mask_token=None), tf.keras.layers.CategoryEncoding(...