NumPy-style broadcasting for R TensorFlow customers

By
Radouane
-
0
7
NumPy-style broadcasting for R TensorFlow customers



NumPy-style broadcasting for R TensorFlow customers

We develop, practice, and deploy TensorFlow fashions from R. However that doesn’t imply we don’t make use of documentation, weblog posts, and examples written in Python. We glance up particular performance within the official TensorFlow API docs; we get inspiration from different individuals’s code.

Relying on how snug you’re with Python, there’s an issue. For instance: You’re presupposed to know the way broadcasting works. And maybe, you’d say you’re vaguely conversant in it: So when arrays have totally different shapes, some components get duplicated till their shapes match and … and isn’t R vectorized anyway?

Whereas such a worldwide notion may match basically, like when skimming a weblog put up, it’s not sufficient to grasp, say, examples within the TensorFlow API docs. On this put up, we’ll attempt to arrive at a extra precise understanding, and test it on concrete examples.

Talking of examples, listed here are two motivating ones.

Broadcasting in motion

The primary makes use of TensorFlow’s matmul to multiply two tensors. Would you wish to guess the outcome – not the numbers, however the way it comes about basically? Does this even run with out error – shouldn’t matrices be two-dimensional (rank-2 tensors, in TensorFlow converse)?

a <- tf$fixed(keras::array_reshape(1:12, dim = c(2, 2, 3)))
a 
# tf.Tensor(
# [[[ 1.  2.  3.]
#   [ 4.  5.  6.]]
# 
#  [[ 7.  8.  9.]
#   [10. 11. 12.]]], form=(2, 2, 3), dtype=float64)

b <- tf$fixed(keras::array_reshape(101:106, dim = c(1, 3, 2)))
b  
# tf.Tensor(
# [[[101. 102.]
#   [103. 104.]
#   [105. 106.]]], form=(1, 3, 2), dtype=float64)

c <- tf$matmul(a, b)

Second, here’s a “actual instance” from a TensorFlow Likelihood (TFP) github situation. (Translated to R, however preserving the semantics).
In TFP, we are able to have batches of distributions. That, per se, isn’t a surprise. However take a look at this:

library(tfprobability)
d <- tfd_normal(loc = c(0, 1), scale = matrix(1.5:4.5, ncol = 2, byrow = TRUE))
d
# tfp.distributions.Regular("Regular", batch_shape=[2, 2], event_shape=[], dtype=float64)

We create a batch of 4 regular distributions: every with a distinct scale (1.5, 2.5, 3.5, 4.5). However wait: there are solely two location parameters given. So what are their scales, respectively?
Fortunately, TFP builders Brian Patton and Chris Suter defined the way it works: TFP really does broadcasting – with distributions – identical to with tensors!

We get again to each examples on the finish of this put up. Our essential focus might be to clarify broadcasting as completed in NumPy, as NumPy-style broadcasting is what quite a few different frameworks have adopted (e.g., TensorFlow).

Earlier than although, let’s shortly assessment a couple of fundamentals about NumPy arrays: The way to index or slice them (indexing usually referring to single-element extraction, whereas slicing would yield – properly – slices containing a number of components); the way to parse their shapes; some terminology and associated background.
Although not difficult per se, these are the sorts of issues that may be complicated to rare Python customers; but they’re typically a prerequisite to efficiently making use of Python documentation.

Said upfront, we’ll actually limit ourselves to the fundamentals right here; for instance, we gained’t contact superior indexing which – identical to tons extra –, will be regarded up intimately within the NumPy documentation.

Few details about NumPy

Primary slicing

For simplicity, we’ll use the phrases indexing and slicing kind of synonymously any longer. The essential machine here’s a slice, specifically, a begin:cease construction indicating, for a single dimension, which vary of components to incorporate within the choice.

In distinction to R, Python indexing is zero-based, and the tip index is unique:

c(4L, 1L))
a
# tf.Tensor(
# [[1.]
#  [1.]
#  [1.]
#  [1.]], form=(4, 1), dtype=float32)

b <- tf$fixed(c(1, 2, 3, 4))
b
# tf.Tensor([1. 2. 3. 4.], form=(4,), dtype=float32)

a + b
# tf.Tensor(
# [[2. 3. 4. 5.]
# [2. 3. 4. 5.]
# [2. 3. 4. 5.]
# [2. 3. 4. 5.]], form=(4, 4), dtype=float32)

And second, once we add tensors with shapes (3, 3) and (3,), the 1-d tensor ought to get added to each row (not each column):

a <- tf$fixed(matrix(1:9, ncol = 3, byrow = TRUE), dtype = tf$float32)
a
# tf.Tensor(
# [[1. 2. 3.]
#  [4. 5. 6.]
#  [7. 8. 9.]], form=(3, 3), dtype=float32)

b <- tf$fixed(c(100, 200, 300))
b
# tf.Tensor([100. 200. 300.], form=(3,), dtype=float32)

a + b
# tf.Tensor(
# [[101. 202. 303.]
#  [104. 205. 306.]
#  [107. 208. 309.]], form=(3, 3), dtype=float32)

Now again to the preliminary matmul instance.

Again to the puzzles

The documentation for matmul says,

The inputs should, following any transpositions, be tensors of rank >= 2 the place the inside 2 dimensions specify legitimate matrix multiplication dimensions, and any additional outer dimensions specify matching batch measurement.

So right here (see code just under), the inside two dimensions look good – (2, 3) and (3, 2) – whereas the one (one and solely, on this case) batch dimension reveals mismatching values 2 and 1, respectively.
A case for broadcasting thus: Each “batches” of a get matrix-multiplied with b.

a <- tf$fixed(keras::array_reshape(1:12, dim = c(2, 2, 3)))
a 
# tf.Tensor(
# [[[ 1.  2.  3.]
#   [ 4.  5.  6.]]
# 
#  [[ 7.  8.  9.]
#   [10. 11. 12.]]], form=(2, 2, 3), dtype=float64)

b <- tf$fixed(keras::array_reshape(101:106, dim = c(1, 3, 2)))
b  
# tf.Tensor(
# [[[101. 102.]
#   [103. 104.]
#   [105. 106.]]], form=(1, 3, 2), dtype=float64)

c <- tf$matmul(a, b)
c
# tf.Tensor(
# [[[ 622.  628.]
#   [1549. 1564.]]
# 
#  [[2476. 2500.]
#   [3403. 3436.]]], form=(2, 2, 2), dtype=float64)

Let’s shortly test this actually is what occurs, by multiplying each batches individually:

tf$matmul(a[1, , ], b)
# tf.Tensor(
# [[[ 622.  628.]
#   [1549. 1564.]]], form=(1, 2, 2), dtype=float64)

tf$matmul(a[2, , ], b)
# tf.Tensor(
# [[[2476. 2500.]
#   [3403. 3436.]]], form=(1, 2, 2), dtype=float64)

Is it too bizarre to be questioning if broadcasting would additionally occur for matrix dimensions? E.g., may we strive matmuling tensors of shapes (2, 4, 1) and (2, 3, 1), the place the 4 x 1 matrix can be broadcast to 4 x 3? – A fast check reveals that no.

To see how actually, when coping with TensorFlow operations, it pays off overcoming one’s preliminary reluctance and really seek the advice of the documentation, let’s strive one other one.

Within the documentation for matvec, we’re advised:

Multiplies matrix a by vector b, producing a * b.
The matrix a should, following any transpositions, be a tensor of rank >= 2, with form(a)[-1] == form(b)[-1], and form(a)[:-2] capable of broadcast with form(b)[:-1].

In our understanding, given enter tensors of shapes (2, 2, 3) and (2, 3), matvec ought to carry out two matrix-vector multiplications: as soon as for every batch, as listed by every enter’s leftmost dimension. Let’s test this – thus far, there isn’t a broadcasting concerned:

# two matrices
a <- tf$fixed(keras::array_reshape(1:12, dim = c(2, 2, 3)))
a
# tf.Tensor(
# [[[ 1.  2.  3.]
#   [ 4.  5.  6.]]
# 
#  [[ 7.  8.  9.]
#   [10. 11. 12.]]], form=(2, 2, 3), dtype=float64)

b = tf$fixed(keras::array_reshape(101:106, dim = c(2, 3)))
b
# tf.Tensor(
# [[101. 102. 103.]
#  [104. 105. 106.]], form=(2, 3), dtype=float64)

c <- tf$linalg$matvec(a, b)
c
# tf.Tensor(
# [[ 614. 1532.]
#  [2522. 3467.]], form=(2, 2), dtype=float64)

Doublechecking, we manually multiply the corresponding matrices and vectors, and get:

tf$linalg$matvec(a[1,  , ], b[1, ])
# tf.Tensor([ 614. 1532.], form=(2,), dtype=float64)

tf$linalg$matvec(a[2,  , ], b[2, ])
# tf.Tensor([2522. 3467.], form=(2,), dtype=float64)

The identical. Now, will we see broadcasting if b has only a single batch?

b = tf$fixed(keras::array_reshape(101:103, dim = c(1, 3)))
b
# tf.Tensor([[101. 102. 103.]], form=(1, 3), dtype=float64)

c <- tf$linalg$matvec(a, b)
c
# tf.Tensor(
# [[ 614. 1532.]
#  [2450. 3368.]], form=(2, 2), dtype=float64)

Multiplying each batch of a with b, for comparability:

tf$linalg$matvec(a[1,  , ], b)
# tf.Tensor([ 614. 1532.], form=(2,), dtype=float64)

tf$linalg$matvec(a[2,  , ], b)
# tf.Tensor([[2450. 3368.]], form=(1, 2), dtype=float64)

It labored!

Now, on to the opposite motivating instance, utilizing tfprobability.

Broadcasting all over the place

Right here once more is the setup:

library(tfprobability)
d <- tfd_normal(loc = c(0, 1), scale = matrix(1.5:4.5, ncol = 2, byrow = TRUE))
d
# tfp.distributions.Regular("Regular", batch_shape=[2, 2], event_shape=[], dtype=float64)

What’s going on? Let’s examine location and scale individually:

d$loc
# tf.Tensor([0. 1.], form=(2,), dtype=float64)

d$scale
# tf.Tensor(
# [[1.5 2.5]
#  [3.5 4.5]], form=(2, 2), dtype=float64)

Simply specializing in these tensors and their shapes, and having been advised that there’s broadcasting happening, we are able to motive like this: Aligning each shapes on the best and increasing loc’s form by 1 (on the left), we’ve (1, 2) which can be broadcast with (2,2) – in matrix-speak, loc is handled as a row and duplicated.

That means: We’ve two distributions with imply (0) (one in every of scale (1.5), the opposite of scale (3.5)), and likewise two with imply (1) (corresponding scales being (2.5) and (4.5)).

Right here’s a extra direct approach to see this:

d$imply()
# tf.Tensor(
# [[0. 1.]
#  [0. 1.]], form=(2, 2), dtype=float64)

d$stddev()
# tf.Tensor(
# [[1.5 2.5]
#  [3.5 4.5]], form=(2, 2), dtype=float64)

Puzzle solved!

Summing up, broadcasting is straightforward “in idea” (its guidelines are), however might have some practising to get it proper. Particularly along with the truth that capabilities / operators do have their very own views on which components of its inputs ought to broadcast, and which shouldn’t. Actually, there isn’t a method round wanting up the precise behaviors within the documentation.

Hopefully although, you’ve discovered this put up to be a great begin into the subject. Perhaps, just like the creator, you’re feeling such as you may see broadcasting happening anyplace on the earth now. Thanks for studying!