elliot.recommender.visual_recommenders.VNPR package

Submodules

elliot.recommender.visual_recommenders.VNPR.VNPR module

Module description:

class elliot.recommender.visual_recommenders.VNPR.VNPR.VNPR(data, config, params, *args, **kwargs)

Bases: elliot.recommender.recommender_utils_mixin.RecMixin, elliot.recommender.base_recommender_model.BaseRecommenderModel

Visual Neural Personalized Ranking for Image Recommendation

For further details, please refer to the paper

Parameters

• lr – Learning rate

• epochs – Number of epochs

• mf_factors: – Number of latent factors for Matrix Factorization:

• mlp_hidden_size – Tuple with number of units for each multi-layer perceptron layer

• prob_keep_dropout – Dropout rate for multi-layer perceptron

• batch_size – Batch size

• batch_eval – Batch for evaluation

• l_w – Regularization coefficient

To include the recommendation model, add it to the config file adopting the following pattern:

models:
  VNPR:
    meta:
      save_recs: True
    lr: 0.001
    epochs: 50
    mf_factors: 10
    mlp_hidden_size: (32, 1)
    prob_keep_dropout: 0.2
    batch_size: 64
    batch_eval: 64
    l_w: 0.001

get_recommendations(k: int = 100)

property name

train()

elliot.recommender.visual_recommenders.VNPR.VNPR_model module

Module description:

class elliot.recommender.visual_recommenders.VNPR.VNPR_model.VNPRModel(*args, **kwargs)

Bases: tensorflow.python.keras.engine.training.Model

call(inputs, training=None, mask=None)

get_recs(inputs, training=False, **kwargs)

Get full predictions on the whole users/items matrix.

Returns

The matrix of predicted values.

get_top_k(preds, train_mask, k=100)

predict(inputs, training=False, **kwargs)

Get full predictions on the whole users/items matrix.

Returns

The matrix of predicted values.

predict_item_batch(start, stop, item_mf_e_1, item_mf_e_2, feat)

train_step(batch)

Module contents