Related
I have an idea for a tensor operation that would not be difficult to implement via iteration, with batch size one. However I would like to parallelize it as much as possible.
I have two tensors with shape (n, 5) called X and Y. X is actually supposed to represent 5 one-dimensional tensors with shape (n, 1): (x_1, ..., x_n). Ditto for Y.
I would like to compute a tensor with shape (n, 25) where each column represents the output of the tensor operation f(x_i, y_j), where f is fixed for all 1 <= i, j <= 5. The operation f has output shape (n, 1), just like x_i and y_i.
I feel it is important to clarify that f is essentially a fully-connected layer from the concatenated [...x_i, ...y_i] tensor with shape (1, 10), to an output layer with shape (1,5).
Again, it is easy to see how to do this manually with iteration and slicing. However this is probably very slow. Performing this operation in batches, where the tensors X, Y now have shape (n, 5, batch_size) is also desirable, particularly for mini-batch gradient descent.
It is difficult to really articulate here why I desire to create this network; I feel it is suited for my domain of 'itemized tabular data' and cuts down significantly on the number of weights per operation, compared to a fully connected network.
Is this possible using tensorflow? Certainly not using just keras.
Below is an example in numpy per AloneTogether's request
import numpy as np
features = 16
batch_size = 256
X_batch = np.random.random((features, 5, batch_size))
Y_batch = np.random.random((features, 5, batch_size))
# one tensor operation to reduce weights in this custom 'layer'
f = np.random.random((features, 2 * features))
for b in range(batch_size):
X = X_batch[:, :, b]
Y = Y_batch[:, :, b]
for i in range(5):
x_i = X[:, i:i+1]
for j in range(5):
y_j = Y[:, j:j+1]
x_i_y_j = np.concatenate([x_i, y_j], axis=0)
# f(x_i, y_j)
# implemented by a fully-connected layer
f_i_j = np.matmul(f, x_i_y_j)
All operations you need (concatenation and matrix multiplication) can be batched.
Difficult part here is, that you want to concatenate features of all items in X with features of all items in Y (all combinations).
My recommended solution is to expand the dimensions of X to [batch, features, 5, 1], expand dimensions of Y to [batch, features, 1, 5]
Than tf.repeat() both tensors so their shapes become [batch, features, 5, 5].
Now you can concatenate X and Y. You will have a tensor of shape [batch, 2*features, 5, 5]. Observe that this way all combinations are built.
Next step is matrix multiplication. tf.matmul() can also do batch matrix multiplication, but I use here tf.einsum() because I want more control over which dimensions are considered as batch.
Full code:
import tensorflow as tf
import numpy as np
batch_size=3
features=6
items=5
x = np.random.uniform(size=[batch_size,features,items])
y = np.random.uniform(size=[batch_size,features,items])
f = np.random.uniform(size=[2*features,features])
x_reps= tf.repeat(x[:,:,:,tf.newaxis], items, axis=3)
y_reps= tf.repeat(y[:,:,tf.newaxis,:], items, axis=2)
xy_conc = tf.concat([x_reps,y_reps], axis=1)
f_i_j = tf.einsum("bfij, fg->bgij", xy_conc,f)
f_i_j = tf.reshape(f_i_j , [batch_size,features,items*items])
I have two sparse matrices declared using the tf.sparse_placeholder. I need to perform the element-wise multiplication between the two matrices. But I cannot find such an implementation in tensorflow. The most related function is tf.sparse_tensor_dense_matmul, but this is a function performing matrix multiplication between one sparse matrix and one dense matrix.
What I hope to find is to performing element-wise multiplication between two sparse matrices. Is there any implementation of this in tensorflow?
I show the following example of performing multiplication between dense matrices. I'm looking forward to seeing a solution.
import tensorflow as tf
import numpy as np
# Element-wise multiplication, two dense matrices
A = tf.placeholder(tf.float32, shape=(100, 100))
B = tf.placeholder(tf.float32, shape=(100, 100))
C = tf.multiply(A, B)
sess = tf.InteractiveSession()
RandA = np.random.rand(100, 100)
RandB = np.random.rand(100, 100)
print sess.run(C, feed_dict={A: RandA, B: RandB})
# matrix multiplication, A is sparse and B is dense
A = tf.sparse_placeholder(tf.float32)
B = tf.placeholder(tf.float32, shape=(5,5))
C = tf.sparse_tensor_dense_matmul(A, B)
sess = tf.InteractiveSession()
indices = np.array([[3, 2], [1, 2]], dtype=np.int64)
values = np.array([1.0, 2.0], dtype=np.float32)
shape = np.array([5,5], dtype=np.int64)
Sparse_A = tf.SparseTensorValue(indices, values, shape)
RandB = np.ones((5, 5))
print sess.run(C, feed_dict={A: Sparse_A, B: RandB})
Thank you very much!!!
TensorFlow currently has no sparse-sparse element-wise multiplication operation.
We don't plan to add support for this currently, but contributions are definitely welcome! Feel free to create a github issue here: https://github.com/tensorflow/tensorflow/issues/new and perhaps you or someone in the community can pick it up :)
Thanks!
you can use tf.matmul or tf.sparse_matmulfor sparse matrices also; setting a_is_sparse and b_is_sparse as True.
matmul(
a,
b,
transpose_a=False,
transpose_b=False,
adjoint_a=False,
adjoint_b=False,
a_is_sparse=False,
b_is_sparse=False,
name=None
)
For element-wise multiplication, one workaround is to use tf.sparse_to_dense for converting sparse tensor to dense representation and using tf.multiply for element-wise multiplication
Solution from another post works.
https://stackoverflow.com/a/45103767/2415428
Use the __mul__ to perform the element-wise multiplication.
TF2.1 ref: https://www.tensorflow.org/api_docs/python/tf/sparse/SparseTensor#mul
I'm using Tensorflow 2.4.1.
Here's my workaround to multiply two sparse tensor element-wise:
def sparse_element_wise_mul(a: tf.SparseTensor, b: tf.SparseTensor):
a_plus_b = tf.sparse.add(a, b)
a_plus_b_square = tf.square(a_plus_b)
minus_a_square = tf.negative(tf.square(a))
minus_b_square = tf.negative(tf.square(b))
_2ab = tf.sparse.add(
tf.sparse.add(
a_plus_b_square,
minus_a_square
),
minus_b_square
)
ab = tf.sparse.map_values(tf.multiply, _2ab, 0.5)
return ab
Here's some simple explanation:
Given that
(a+b)^2 = a^2 + 2a*b + b^2
we can calculate a*b by
a*b = ((a+b)^2 - a^2 - b^2) / 2
It seems the gradient can be calculated correctly with such a workaround.
Given a tensor A of shape [?, n, l] and a tensor D of shape [?, n], I want to divide each row of tensor a of shape [n,l] of A by the corresponding scalar of D.
I thought I could somehow do this by using the broadcasting behavior of tf.div. Unfortunatley I am stuck.
Here you need to extend D to match the dimension of A:
res = A / D[...,tf.newaxis])
I ma trying to understand tf.rank function in tensorflow. From the documentation here, I understood that rank should return the number of distinct elements in the tensor.
Here x and weights are 2 distinct 2*2 tensors with 4 distinct elemnts in each of them. However, rank() function outputs are:
Tensor("Rank:0", shape=(), dtype=int32) Tensor("Rank_1:0", shape=(),
dtype=int32)
Also, for the tensor x, I used tf.constant() with dtype = float to convert ndarray into float32 tensor but the rank() still outputs as int32.
g = tf.Graph()
with g.as_default():
weights = tf.Variable(tf.truncated_normal([2,2]))
x = np.asarray([[1 , 2], [3 , 4]])
x = tf.constant(x, dtype = tf.float32)
y = tf.matmul(weights, x)
print (tf.rank(x), tf.rank(weights))
with tf.Session(graph = g) as s:
tf.initialize_all_variables().run()
print (s.run(weights), s.run(x))
print (s.run(y))
How should I interpret the output.
Firstly, tf.rank returns the dimension of a tensor, not the number of elements. For instance, the output from tf.rank called for the 2x2 matrix would be 2.
To print the rank of a tensor, create an appropriate node, e.g. rank = tf.rank(x) and then evaluate this node using a Session.run(), as you've done for weights and x. Execution of print (tf.rank(x), tf.rank(weights)) expectedly prints out description of tensors, as tf.rank(x), tf.rank(weights) are nodes of the graph, not the variables with defined values.
Tensorflow has a function called batch_matmul which multiplies higher dimensional tensors. But I'm having a hard time understanding how it works, perhaps partially because I'm having a hard time visualizing it.
What I want to do is multiply a matrix by each slice of a 3D tensor, but I don't quite understand what the shape of tensor a is. Is z the innermost dimension? Which of the following is correct?
I would most prefer the first to be correct -- it's most intuitive to me and easy to see in the .eval() output. But I suspect the second is correct.
Tensorflow says that batch_matmul performs:
out[..., :, :] = matrix(x[..., :, :]) * matrix(y[..., :, :])
What does that mean? What does that mean in the context of my example? What is being multiplied with with what? And why aren't I getting a 3D tensor the way I expected?
You can imagine it as doing a matmul over each training example in the batch.
For example, if you have two tensors with the following dimensions:
a.shape = [100, 2, 5]
b.shape = [100, 5, 2]
and you do a batch tf.matmul(a, b), your output will have the shape [100, 2, 2].
100 is your batch size, the other two dimensions are the dimensions of your data.
First of all tf.batch_matmul() was removed and no longer available. Now you suppose to use tf.matmul():
The inputs must be matrices (or tensors of rank > 2, representing
batches of matrices), with matching inner dimensions, possibly after
transposition.
So let's assume you have the following code:
import tensorflow as tf
batch_size, n, m, k = 10, 3, 5, 2
A = tf.Variable(tf.random_normal(shape=(batch_size, n, m)))
B = tf.Variable(tf.random_normal(shape=(batch_size, m, k)))
tf.matmul(A, B)
Now you will receive a tensor of the shape (batch_size, n, k). Here is what is going on here. Assume you have batch_size of matrices nxm and batch_size of matrices mxk. Now for each pair of them you calculate nxm X mxk which gives you an nxk matrix. You will have batch_size of them.
Notice that something like this is also valid:
A = tf.Variable(tf.random_normal(shape=(a, b, n, m)))
B = tf.Variable(tf.random_normal(shape=(a, b, m, k)))
tf.matmul(A, B)
and will give you a shape (a, b, n, k)
You can now do it using tf.einsum, starting from Tensorflow 0.11.0rc0.
For example,
M1 = tf.Variable(tf.random_normal([2,3,4]))
M2 = tf.Variable(tf.random_normal([5,4]))
N = tf.einsum('ijk,lk->ijl',M1,M2)
It multiplies the matrix M2 with every frame (3 frames) in every batch (2 batches) in M1.
The output is:
[array([[[ 0.80474716, -1.38590837, -0.3379252 , -1.24965811],
[ 2.57852983, 0.05492432, 0.23039417, -0.74263287],
[-2.42627382, 1.70774114, 1.19503212, 0.43006262]],
[[-1.04652011, -0.32753903, -1.26430523, 0.8810069 ],
[-0.48935518, 0.12831448, -1.30816901, -0.01271309],
[ 2.33260512, -1.22395933, -0.92082584, 0.48991606]]], dtype=float32),
array([[ 1.71076882, 0.79229093, -0.58058828, -0.23246667],
[ 0.20446332, 1.30742455, -0.07969904, 0.9247328 ],
[-0.32047141, 0.66072595, -1.12330854, 0.80426538],
[-0.02781649, -0.29672042, 2.17819595, -0.73862702],
[-0.99663496, 1.3840003 , -1.39621222, 0.77119476]], dtype=float32),
array([[[ 0.76539308, 2.77609682, -1.79906654, 0.57580602, -3.21205115],
[ 4.49365759, -0.10607499, -1.64613271, 0.96234947, -3.38823152],
[-3.59156275, 2.03910899, 0.90939498, 1.84612727, 3.44476724]],
[[-1.52062428, 0.27325237, 2.24773455, -3.27834225, 3.03435063],
[ 0.02695178, 0.16020992, 1.70085776, -2.8645196 , 2.48197317],
[ 3.44154787, -0.59687197, -0.12784094, -2.06931567, -2.35522676]]], dtype=float32)]
I have verified, the arithmetic is correct.
tf.tensordot should solve this problem. It supports batch operations, e.g., if you want to contract a 2D tensor with a 3D tensor, with the latter having a batch dimension.
If a is shape [n,m] b is shape [?,m,l], then
y = tf.tensordot(b, a, axes=[1, 1]) will produce a tensor of shape [?,n,l]
https://www.tensorflow.org/api_docs/python/tf/tensordot
It is simply like splitting on the first dimension respectively, multiply and concat them back. If you want to do 3D by 2D, you can reshape, multiply, and reshape it back. I.e. [100, 2, 5] -> [200, 5] -> [200, 2] -> [100, 2, 2]
The answer to this particular answer is using tf.scan function.
If a = [5,3,2] #dimension of 5 batch, with 3X2 mat in each batch
and b = [2,3] # a constant matrix to be multiplied with each sample
then let def fn(a,x):
return tf.matmul(x,b)
initializer = tf.Variable(tf.random_number(3,3))
h = tf.scan(fn,outputs,initializer)
this h will store all the outputs.