- 原型:tf.nn.embedding_lookup(params, ids, partition_strategy='mod', name=None, validate_indices=True, max_norm=None)
- In fact tf.nn.embedding_lookup role is to find the vector under're looking for embedding data in the corresponding row.
- Simply look through the code, ids 1 line or several lines include:
# -*- coding= utf-8 -*- import tensorflow as tf import numpy as np a = [[0.1, 0.2, 0.3], [1.1, 1.2, 1.3], [2.1, 2.2, 2.3], [3.1, 3.2, 3.3], [4.1, 4.2, 4.3]] a = np.asarray(a) idx1 = tf.Variable([0, 2, 3, 1], tf.int32) idx2 = tf.Variable([[0, 2, 3, 1], [4, 0, 2, 2]], tf.int32) out1 = tf.nn.embedding_lookup(a, idx1) out2 = tf.nn.embedding_lookup(a, idx2) init = tf.global_variables_initializer() with tf.Session() as sess: sess.run(init) print sess.run(out1) print out1 print '==================' print sess.run(out2) print out2
- Output:
[[ 0.1 0.2 0.3] [ 2.1 2.2 2.3] [ 3.1 3.2 3.3] [ 1.1 1.2 1.3]] Tensor("embedding_lookup:0", shape=(4, 3), dtype=float64) ================== [[[ 0.1 0.2 0.3] [ 2.1 2.2 2.3] [ 3.1 3.2 3.3] [ 1.1 1.2 1.3]] [[ 4.1 4.2 4.3] [ 0.1 0.2 0.3] [ 2.1 2.2 2.3] [ 2.1 2.2 2.3]]] Tensor("embedding_lookup_1:0", shape=(2, 4, 3), dtype=float64)
-
Dimensions discussion : In looking at the corresponding vector index spliced in embedding data in're looking for. It is always part ids + dimensions except the first dimension of the embedding dimension spliced portion. Obviously, we can obtain, IDS is the value which must be less than or equal embedding a reduced largest dimension of.
Reference article : https://www.jianshu.com/p/ad88a0afa98f