Roger L. Cauvin comments

Results 39 comments of


                                            Roger L. Cauvin

What is the benefit of having two separate class one for user and one for query?

I don't think it's necessary to have separate classes for the user and query model or for the movie and candidate model. The tutorial is showing how to add a...

Not possible to run the basic retrieval example

The ridiculous hack described [here](https://stackoverflow.com/questions/71759248/importerror-cannot-import-name-builder-from-google-protobuf-internal.) worked for me: ``` pip install --upgrade protobuf # Open a terminal and execute: # mkdir -p ~/protobuf_hack # cp ~/anaconda3/envs/tensorflow2_p310/lib/python3.10/site-packages/google/protobuf/internal/builder.py protobuf_hack/ pip install protobuf==3.19.6...

Not possible to run the basic retrieval example

I apply the hack after installing all other packages (and ignoring the package conflict warnings). ``` > pip freeze | grep tensor tensorboard==2.11.0 tensorboard-data-server==0.6.1 tensorboard-plugin-wit==1.8.1 tensorflow==2.11.0 tensorflow-datasets==4.9.2 tensorflow-estimator==2.11.0 tensorflow-io-gcs-filesystem==0.29.0 tensorflow-metadata==1.13.1...

[Idea] Learn from Positives and Negatives Using Two Retrieval Models

I looked at the code for tfrs.layers.factorized_top_k.BruteForce and realized I could create a nearly identical class (BruteForceFurthest) that returns the furthest neighbors by changing one line of code. Here is...

[Idea] Learn from Positives and Negatives Using Two Retrieval Models

Thanks for sharing the Mixed Negative Sampling method, @caesarjuly. I'm going to study it and try to figure out how it works. As for your questions: **1. Are the negative...

tfrs.metrics.FactorizedTopK

This is a bug in the implementation of the `tfrs.layers.factorized_top_k` module. In [recommenders/tensorflow_recommenders/layers/factorized_top_k.py](https://github.com/tensorflow/recommenders/blob/v0.7.3/tensorflow_recommenders/layers/factorized_top_k.py#L376), we find: ``` self._counter = self.add_weight("counter", dtype=tf.int32, trainable=False) ``` Note that the first argument passed to `add_weight`...