eustin

loss = tf.keras.losses.KLDivergence()
batch_loss = loss(relevance_grades_prob_dist, scores_prob_dist)

print(batch_loss)

eustin

relevance_grades_prob_dist = tf.nn.softmax(relevance_grades, axis=-1)

print(relevance_grades_prob_dist)

eustin

scores_for_softmax = tf.squeeze(scores_out, axis=-1)
scores_prob_dist = tf.nn.softmax(scores_for_softmax, axis=-1)

print(scores_prob_dist)

eustin

scores = tf.keras.layers.Dense(units=1, activation='linear')
scores_out = scores(dense_1_out)

print(scores_out)

eustin

dense_1 = tf.keras.layers.Dense(units=3, activation='relu')
dense_1_out = dense_1(expanded_batch)

print(dense_1_out)

eustin

expanded_batch = np.concatenate([expanded_queries, docs_averaged_embeddings], axis=-1)

print(expanded_batch)

eustin

NUM_DOCS_PER_QUERY = 5

expanded_queries = tf.gather(query_embeddings, [0 for x in range(NUM_DOCS_PER_QUERY)], axis=1).numpy()

print(expanded_queries)

eustin

print(docs_averaged_embeddings.shape)

eustin

docs_averaged_embeddings = []
for docs_set in docs_embeddings:
    this_docs_set = []
    for doc in docs_set:
        this_docs_set.append(tf.reduce_mean(doc, axis=0, keepdims=True))
    concatenated_docs_set = tf.concat(this_docs_set, axis=0).numpy()
    docs_averaged_embeddings.append(concatenated_docs_set)
    
docs_averaged_embeddings = np.array(docs_averaged_embeddings)

eustin

for embeddings in docs_embeddings[1]:
    print()
    print(embeddings)