tf.nn.embedding_lookup(params, ids, partition_strategy='mod', name=None)
matrix = np.random.random([1024, 64]) # 64-dimensional embeddings
ids = np.array([0, 5, 17, 33])
print matrix[ids] # prints a matrix of shape [4, 64]
params = tf.constant([10,20,30,40])
ids = tf.constant([0,1,2,3])
print tf.nn.embedding_lookup(params,ids).eval()
params = tf.constant([10,20,30,40])
ids = tf.constant([1,1,3])
print tf.nn.embedding_lookup(params,ids).eval()
params1 = tf.constant([1,2])
params2 = tf.constant([10,20])
ids = tf.constant([2,0,2,1,2,3])
result = tf.nn.embedding_lookup([params1, params2], ids)
params1 = tf.constant([1,2])
params2 = tf.constant([10,20])
ids = tf.constant([2,0,2,1,2,3])
result = tf.nn.embedding_lookup([params1, params2], ids)
[ 2 1 2 10 2 20]
Another way to look at it is , assume that you flatten out the tensors to one dimensional array, and then you are performing a lookup
(eg) Tensor0=[1,2,3], Tensor1=[4,5,6], Tensor2=[7,8,9]
The flattened out tensor will be as follows [1,4,7,2,5,8,3,6,9]
Now when you do a lookup of [0,3,4,1,7] it will yeild [1,2,5,4,6]
(i,e) if lookup value is 7 for example , and we have 3 tensors (or a tensor with 3 rows) then,
7 / 3 : (Reminder is 1, Quotient is 2) So 2nd element of Tensor1 will be shown, which is 6
the 0.418 0.24968 -0.41242 0.1217 0.34527 -0.044457 -0.49688 -0.17862
like 0.36808 0.20834 -0.22319 0.046283 0.20098 0.27515 -0.77127 -0.76804
between 0.7503 0.71623 -0.27033 0.20059 -0.17008 0.68568 -0.061672 -0.054638
did 0.042523 -0.21172 0.044739 -0.19248 0.26224 0.0043991 -0.88195 0.55184
just 0.17698 0.065221 0.28548 -0.4243 0.7499 -0.14892 -0.66786 0.11788
national -1.1105 0.94945 -0.17078 0.93037 -0.2477 -0.70633 -0.8649 -0.56118
day 0.11626 0.53897 -0.39514 -0.26027 0.57706 -0.79198 -0.88374 0.30119
country -0.13531 0.15485 -0.07309 0.034013 -0.054457 -0.20541 -0.60086 -0.22407
under 0.13721 -0.295 -0.05916 -0.59235 0.02301 0.21884 -0.34254 -0.70213
such 0.61012 0.33512 -0.53499 0.36139 -0.39866 0.70627 -0.18699 -0.77246
second -0.29809 0.28069 0.087102 0.54455 0.70003 0.44778 -0.72565 0.62309
vocab = ['the','like','between','did','just','national','day','country','under','such','second']
emb = np.array([[0.418, 0.24968, -0.41242, 0.1217, 0.34527, -0.044457, -0.49688, -0.17862],
[0.36808, 0.20834, -0.22319, 0.046283, 0.20098, 0.27515, -0.77127, -0.76804],
[0.7503, 0.71623, -0.27033, 0.20059, -0.17008, 0.68568, -0.061672, -0.054638],
[0.042523, -0.21172, 0.044739, -0.19248, 0.26224, 0.0043991, -0.88195, 0.55184],
[0.17698, 0.065221, 0.28548, -0.4243, 0.7499, -0.14892, -0.66786, 0.11788],
[-1.1105, 0.94945, -0.17078, 0.93037, -0.2477, -0.70633, -0.8649, -0.56118],
[0.11626, 0.53897, -0.39514, -0.26027, 0.57706, -0.79198, -0.88374, 0.30119],
[-0.13531, 0.15485, -0.07309, 0.034013, -0.054457, -0.20541, -0.60086, -0.22407],
[ 0.13721, -0.295, -0.05916, -0.59235, 0.02301, 0.21884, -0.34254, -0.70213],
[ 0.61012, 0.33512, -0.53499, 0.36139, -0.39866, 0.70627, -0.18699, -0.77246 ],
[ -0.29809, 0.28069, 0.087102, 0.54455, 0.70003, 0.44778, -0.72565, 0.62309 ]])
emb.shape
# (11, 8)
Embedding Lookup in TensorFlow
Now we will see how can we perform embedding lookup for some arbitrary input sentence.
In [54]: from collections import OrderedDict
# embedding as TF tensor (for now constant; could be tf.Variable() during training)
In [55]: tf_embedding = tf.constant(emb, dtype=tf.float32)
# input for which we need the embedding
In [56]: input_str = "like the country"
# build index based on our `vocabulary`
In [57]: word_to_idx = OrderedDict({w:vocab.index(w) for w in input_str.split() if w in vocab})
# lookup in embedding matrix & return the vectors for the input words
In [58]: tf.nn.embedding_lookup(tf_embedding, list(word_to_idx.values())).eval()
Out[58]:
array([[ 0.36807999, 0.20834 , -0.22318999, 0.046283 , 0.20097999,
0.27515 , -0.77126998, -0.76804 ],
[ 0.41800001, 0.24968 , -0.41242 , 0.1217 , 0.34527001,
-0.044457 , -0.49687999, -0.17862 ],
[-0.13530999, 0.15485001, -0.07309 , 0.034013 , -0.054457 ,
-0.20541 , -0.60086 , -0.22407 ]], dtype=float32)
When the params tensor is in high dimensions, the ids only refers to top dimension. Maybe it's obvious to most of people but I have to run the following code to understand that:
embeddings = tf.constant([[[1,1],[2,2],[3,3],[4,4]],[[11,11],[12,12],[13,13],[14,14]],
[[21,21],[22,22],[23,23],[24,24]]])
ids=tf.constant([0,2,1])
embed = tf.nn.embedding_lookup(embeddings, ids, partition_strategy='div')
with tf.Session() as session:
result = session.run(embed)
print (result)
Just trying the 'div' strategy and for one tensor, it makes no difference.
Here is the output:
[[[ 1 1]
[ 2 2]
[ 3 3]
[ 4 4]]
[[21 21]
[22 22]
[23 23]
[24 24]]
[[11 11]
[12 12]
[13 13]
[14 14]]]