recommenders

recommenders copied to clipboard

loss becomes nan

1

58/108 [===============>..............] - ETA: 1:05:49 - root_mean_squared_error: nan - factorized_top_k/top_1_categorical_accuracy: 0.0045 - factorized_top_k/top_5_categorical_accuracy: 0.0089 - factorized_top_k/top_10_categorical_accuracy: 0.0130 - factorized_top_k/top_50_categorical_accuracy: 0.0295 - factorized_top_k/top_100_categorical_accuracy: 0.0380 - loss: nan - regularization_loss: nan -...

zhifeng-huang

index_from_dataset returns indices rather than movie names

3

Hello In my code I added another feature to the candidate tower in addition to movie title (for each movie I have a vector representation of that movie which is...

abdollahpouri

[Question] Using Temperature and Hard Negative Mining for Retrieval Models

22

I've read in a couple of papers that mention that careful tuning the temperature hyperparameter is critical for retrieval quality Quoting from the [paper](https://storage.googleapis.com/pub-tools-public-publication-data/pdf/6c8a86c981a62b0126a11896b7f6ae0dae4c3566.pdf) From what i understand about the...

OmarMAmin

Hello In the vanilla Keras models, I have been using `tf.keras.utils.plot_model()` to see the model architecture which has been extremely useful. However, the function does not work on the model...

abdollahpouri

Tensorflow Recommenders on M1

2

Hi Team, Whenever I need to install tf-recommenders, I can only install earlier versions, as the latest version strictly require tensorflow>=2.9.0 in the requirements.txt file, and in the case of...

OmarMAmin

[Question] Difference between ncf and two-tower-model

18

Hi all, as I delved further into the topic of recommender systems, the question came up of what the difference is between the two-tower model used here "https://www.tensorflow.org/recommenders/examples/basic_retrieval" and neural...

jillwalker99

[Question] Loss computation in movielens examples

2

Hi, I'm trying to understand the loss computation for the movielens retrieval example. In case of movielens dataset there are ~900 users and ~1600 movies, and when we train the...

dibya-pati

How to create a feature in the candidate model that depends (varies) for each row in the dataset?

2

Hi everyone. I'm implementing a multitask model to predict the next item in the basket. In my candidate model, I would like to insert a feature that represents the score...

msoutojr

[Question] Item-to-Item recommendations with the candidate model

12

Hi ! On the [retrieval tutorial page](https://www.tensorflow.org/recommenders/examples/basic_retrieval?hl=en. ), item-to-item recommendations are mentionned at the end of the page. The paragraph suggests to use items for both towers and then train...

jeremybastin1207

[Question]Retrieval with CategoricalCrossentropy really minimizing the affinity between the query and negative candidates?

5

In [tfrs.tasks.retireval document](https://www.tensorflow.org/recommenders/api_docs/python/tfrs/tasks/Retrieval#call), retrieval task is explained like `The main argument are pairs of query and candidate embeddings: the first row of query_embeddings denotes a query for which the candidate...

canonrock16