Yannis Pappas comments

Results 6 comments of


                                            Yannis Pappas

How to get confidence for prediction?

I believe the faktorizedTop3 on the testing dataset will give you the percentage of the times where the actual selection was in the top 3 recommendations, which may suit you....

Add User Feature in the "Recommending movies: retrieval"

I believe you can add additional features to the user model. e.g. ```python class UserModel(keras.Model, ABC): def __init__(self): super().__init__() self.session_id_embedding = keras.Sequential( [ preprocessing.Hashing(num_bins=200_000), layers.Embedding(input_dim=200_000, output_dim=32), ] ) self.another_embedding =...

Question: How best to prepare a dataset for sequential recommendation.

We have implemented a similar logic by selecting a sliding window of (up to) N items of the sequence (left padded with 0s) as input to a GRU and the...

Not able to save model for the quickstart example

If you check the [model serving](https://www.tensorflow.org/recommenders/examples/basic_retrieval#model_serving) section, you can use the "index" as the model. ```python # Export the query model. with tempfile.TemporaryDirectory() as tmp: path = os.path.join(tmp, "model") #...

Evaluator fails with ValueError in Airflow when caching is turned off and retries are allowed

Our evaluator also fails in GCP AI pipelines with caching = True. I provide you with a screenshot, the evaluator logs and the requirements.txt (for the versions of used libraries)...

openHAB Cloud service

@markusvitz just follow the steps @thopiekar mentions above: 1. Open a console connection via SSH to your NAS 2. Go to /share/CACHE[...]/.qpkg/openHAB/ 3. Run openHAB.sh stop 4. Wait for approx...