Let's say I have a (7,7,3) image with 3 channels.
How can I create a matrix A using the image such that the each row consist of just the pairwise connections of the neighbouring pixel? I know this can be done easily in python with for loops but how can we do this within a tensorflow graph?
Example of matrix A:
[[pixel1 pixel2],
[pixel1 pixel3],
[pixel1 pixel4],
.....so on ]]
You can do this using some matrix algebra. To illustrate the idea, suppose you wanted to do this for a 1D vector.
You can stack the vector with a shifted version of itself to get pairs of neighbors
n = 5
a = tf.range(n)
left = tf.stack([a[1:], a[:n-1]])
left = tf.transpose(left)
By chopping off the tails and repeating for different offset you can get left neighbors and right neighbors
right = tf.stack([a[:n-1], a[1:]])
right = tf.transpose(right)
To ignore edge effects you can chop off the ends and stack again into rank-3 matrix
stacked_neighbors = tf.stack([left[:-1], right[1:]])
Now to interleave the neighbors we can use a trick with transpose and reshape.
stacked_neighbors = tf.transpose(stacked_neighbors, [1, 0, 2])
Since data storage is in row-major order, reshaping into less dimensions than original, reshape flattens excess dimensions on the left
stacked_neighbors = tf.reshape(stacked_neighbors, [6,2])
Related
I am trying to reconstruct the following matrix of shape (256 x 256 x 2) with SVD components as
U.shape = (256, 256, 256)
s.shape = (256, 2)
vh.shape = (256, 2, 2)
I have already tried methods from documentation of numpy and scipy to reconstruct the original matrix but failed multiple times, I think it maybe 3D matrix has a different way of reconstruction.
I am using numpy.linalg.svd for decompostion.
From np.linalg.svd's documentation:
"... If a has more than two dimensions, then broadcasting rules apply, as explained in :ref:routines.linalg-broadcasting. This means that SVD is
working in "stacked" mode: it iterates over all indices of the first
a.ndim - 2 dimensions and for each combination SVD is applied to the
last two indices."
This means that you only need to handle the s matrix (or tensor in general case) to obtain the right tensor. More precisely, what you need to do is pad s appropriately and then take only the first 2 columns (or generally, the number of rows of vh which should be equal to the number of columns of the returned s).
Here is a working code with example for your case:
import numpy as np
mat = np.random.randn(256, 256, 2) # Your matrix of dim 256 x 256 x2
u, s, vh = np.linalg.svd(mat) # Get the decomposition
# Pad the singular values' arrays, obtain diagonal matrix and take only first 2 columns:
s_rep = np.apply_along_axis(lambda _s: np.diag(np.pad(_s, (0, u.shape[1]-_s.shape[0])))[:, :_s.shape[0]], 1, s)
mat_reconstructed = u # s_rep # vh
mat_reconstructed equals to mat up to precision error.
I have two 2d point clouds (oldPts and newPts) which I whish to combine. They are mx2 and nx2 numpyinteger arrays with m and n of order 2000. newPts contains many duplicates or near duplicates of oldPts and I need to remove these before combining.
So far I have used the histogram2d function to produce a 2d representation of oldPts (H). I then compare each newPt to an NxN area of H and if it is empty I accept the point. This last part I am currently doing with a python loop which i would like to remove. Can anybody show me how to do this with broadcasting or perhaps suggest a completely different method of going about the problem. the working code is below
npzfile = np.load(path+datasetNo+'\\temp.npz')
arrs = npzfile.files
oldPts = npzfile[arrs[0]]
newPts = npzfile[arrs[1]]
# remove all the negative values
oldPts = oldPts[oldPts.min(axis=1)>=0,:]
newPts = newPts[newPts.min(axis=1)>=0,:]
# round to integers
oldPts = np.around(oldPts).astype(int)
newPts = newPts.astype(int)
# put the oldPts into 2d array
H, xedg,yedg= np.histogram2d(oldPts[:,0],oldPts[:,1],
bins = [xMax,yMax],
range = [[0, xMax], [0, yMax]])
finalNewList = []
N = 5
for pt in newPts:
if not H[max(0,pt[0]-N):min(xMax,pt[0]+N),
max(0,pt[1]- N):min(yMax,pt[1]+N)].any():
finalNewList.append(pt)
finalNew = np.array(finalNewList)
The right way to do this is to use linear algebra to compute the distance between each pair of 2-long vectors, and then accept only the new points that are "different enough" from each old point: using scipy.spatial.distance.cdist:
import numpy as np
oldPts = np.random.randn(1000,2)
newPts = np.random.randn(2000,2)
from scipy.spatial.distance import cdist
dist = cdist(oldPts, newPts)
print(dist.shape) # (1000, 2000)
okIndex = np.max(dist, axis=0) > 5
print(np.sum(okIndex)) # prints 1503 for me
finalNew = newPts[okIndex,:]
print(finalNew.shape) # (1503, 2)
Above I use the Euclidean distance of 5 as the threshold for "too close": any point in newPts that's farther than 5 from all points in oldPts is accepted into finalPts. You will have to look at the range of values in dist to find a good threshold, but your histogram can guide you in picking the best one.
(One good way to visualize dist is to use matplotlib.pyplot.imshow(dist).)
This is a more refined version of what you were doing with the histogram. In fact, you ought to be able to get the exact same answer as the histogram by passing in metric='minkowski', p=1 keyword arguments to cdist, assuming your histogram bin widths are the same in both dimensions, and using 5 again as the threshold.
(PS. If you're interested in another useful function in scipy.spatial.distance, check out my answer that uses pdist to find unique rows/columns in an array.)
I have a situation similar to the following:
import numpy as np
a = np.random.rand(55, 1, 3)
b = np.random.rand(55, 626, 3)
Here the shapes represent the number of observations, then the number of time slices per observation, then the number of dimensions of the observation at the given time slice. So b is a full representation of 3 dimensions for each of the 55 observations at one new time interval.
I'd like to stack a and b into an array with shape 55, 627, 3. How can one accomplish this in numpy? Any suggestions would be greatly appreciated!
To follow up on Divakar's answer above, the axis argument in numpy is the index of a given dimension within an array's shape. Here I want to stack a and b by virtue of their middle shape value, which is at index = 1:
import numpy as np
a = np.random.rand(5, 1, 3)
b = np.random.rand(5, 100, 3)
# create the desired result shape: 55, 627, 3
stacked = np.concatenate((b, a), axis=1)
# validate that a was appended to the end of b
print(stacked[:, -1, :], '\n\n\n', a.squeeze())
This returns:
[[0.72598529 0.99395887 0.21811998]
[0.9833895 0.465955 0.29518207]
[0.38914048 0.61633291 0.0132326 ]
[0.05986115 0.81354865 0.43589306]
[0.17706517 0.94801426 0.4567973 ]]
[[0.72598529 0.99395887 0.21811998]
[0.9833895 0.465955 0.29518207]
[0.38914048 0.61633291 0.0132326 ]
[0.05986115 0.81354865 0.43589306]
[0.17706517 0.94801426 0.4567973 ]]
A purist might use instead np.all(stacked[:, -1, :] == a.squeeze()) to validate this equivalence. All glory to #Divakar!
Strictly for the curious, the use case for this concatenation is a kind of wonky data preparation pipeline for a Long Short Term Memory Neural Network. In that kind of network, the training data shape should be number_of_observations, number_of_time_intervals, number_of_dimensions_per_observation. I am generating new predictions of each object at a new time interval, so those predictions have shape number_of_observations, 1, number_of_dimensions_per_observation. To visualize the sequence of observations' positions over time, I want to add the new positions to the array of previous positions, hence the question above.
For each location in the result matrix, instead of storing the dot product of the corresponding row and column in the argument matrices, I would like like to store the element wise product, which will be a vector extending into a third dimension.
One idea would be to convert the argument matrices to vectors with vector entries, and then take their outer product, but I'm not sure how to do this either.
EDIT:
I figured it out before I saw there was a reply. Here is my solution:
def newdot(A, B):
A = A.reshape((1,) + A.shape)
B = B.reshape((1,) + B.shape)
A = A.transpose(2, 1, 0)
B = B.transpose(1, 0, 2)
return A * B
What I am doing is taking apart each row and column pair that will have their outer product taken, and forming two lists of them, which then get their contents matrix multiplied together in parallel.
It's a little convoluted (and difficult to explain) but this function should get you what you're looking for:
def f(m1, m2):
return (m2.A.T * m1.A.reshape(m1.shape[0],1,m1.shape[1]))
m3 = m1 * m2
m3_el = f(m1, m2)
m3[i,j] == sum(m3_el[i,j,:])
m3 == m3_el.sum(2)
The basic idea is to turn the matrices into arrays and do element-by-element multiplication. One of the arrays gets reshaped to have a size of one in its middle dimension, and array broadcasting rules expand this dimension out to match the height of the other array.
I am looking for algorithm to solve the following problem :
I have two sets of vectors, and I want to find the matrix that best approximate the transformation from the input vectors to the output vectors.
vectors are 3x1, so matrix is 3x3.
This is the general problem. My particular problem is I have a set of RGB colors, and another set that contains the desired color. I am trying to find an RGB to RGB transformation that would give me colors closer to the desired ones.
There is correspondence between the input and output vectors, so computing an error function that should be minimized is the easy part. But how can I minimize this function ?
This is a classic linear algebra problem, the key phrase to search on is "multiple linear regression".
I've had to code some variation of this many times over the years. For example, code to calibrate a digitizer tablet or stylus touch-screen uses the same math.
Here's the math:
Let p be an input vector and q the corresponding output vector.
The transformation you want is a 3x3 matrix; call it A.
For a single input and output vector p and q, there is an error vector e
e = q - A x p
The square of the magnitude of the error is a scalar value:
eT x e = (q - A x p)T x (q - A x p)
(where the T operator is transpose).
What you really want to minimize is the sum of e values over the sets:
E = sum (e)
This minimum satisfies the matrix equation D = 0 where
D(i,j) = the partial derivative of E with respect to A(i,j)
Say you have N input and output vectors.
Your set of input 3-vectors is a 3xN matrix; call this matrix P.
The ith column of P is the ith input vector.
So is the set of output 3-vectors; call this matrix Q.
When you grind thru all of the algebra, the solution is
A = Q x PT x (P x PT) ^-1
(where ^-1 is the inverse operator -- sorry about no superscripts or subscripts)
Here's the algorithm:
Create the 3xN matrix P from the set of input vectors.
Create the 3xN matrix Q from the set of output vectors.
Matrix Multiply R = P x transpose (P)
Compute the inverseof R
Matrix Multiply A = Q x transpose(P) x inverse (R)
using the matrix multiplication and matrix inversion routines of your linear algebra library of choice.
However, a 3x3 affine transform matrix is capable of scaling and rotating the input vectors, but not doing any translation! This might not be general enough for your problem. It's usually a good idea to append a "1" on the end of each of the 3-vectors to make then a 4-vector, and look for the best 3x4 transform matrix that minimizes the error. This can't hurt; it can only lead to a better fit of the data.
You don't specify a language, but here's how I would approach the problem in Matlab.
v1 is a 3xn matrix, containing your input colors in vertical vectors
v2 is also a 3xn matrix containing your output colors
You want to solve the system
M*v1 = v2
M = v2*inv(v1)
However, v1 is not directly invertible, since it's not a square matrix. Matlab will solve this automatically with the mrdivide operation (M = v2/v1), where M is the best fit solution.
eg:
>> v1 = rand(3,10);
>> M = rand(3,3);
>> v2 = M * v1;
>> v2/v1 - M
ans =
1.0e-15 *
0.4510 0.4441 -0.5551
0.2220 0.1388 -0.3331
0.4441 0.2220 -0.4441
>> (v2 + randn(size(v2))*0.1)/v1 - M
ans =
0.0598 -0.1961 0.0931
-0.1684 0.0509 0.1465
-0.0931 -0.0009 0.0213
This gives a more language-agnostic solution on how to solve the problem.
Some linear algebra should be enough :
Write the average squared difference between inputs and outputs ( the sum of the squares of each difference between each input and output value ). I assume this as definition of "best approximate"
This is a quadratic function of your 9 unknown matrix coefficients.
To minimize it, derive it with respect to each of them.
You will get a linear system of 9 equations you have to solve to get the solution ( unique or a space variety depending on the input set )
When the difference function is not quadratic, you can do the same but you have to use an iterative method to solve the equation system.
This answer is better for beginners in my opinion:
Have the following scenario:
We don't know the matrix M, but we know the vector In and a corresponding output vector On. n can range from 3 and up.
If we had 3 input vectors and 3 output vectors (for 3x3 matrix), we could precisely compute the coefficients αr;c. This way we would have a fully specified system.
But we have more than 3 vectors and thus we have an overdetermined system of equations.
Let's write down these equations. Say that we have these vectors:
We know, that to get the vector On, we must perform matrix multiplication with vector In.In other words: M · I̅n = O̅n
If we expand this operation, we get (normal equations):
We do not know the alphas, but we know all the rest. In fact, there are 9 unknowns, but 12 equations. This is why the system is overdetermined. There are more equations than unknowns. We will approximate the unknowns using all the equations, and we will use the sum of squares to aggregate more equations into less unknowns.
So we will combine the above equations into a matrix form:
And with some least squares algebra magic (regression), we can solve for b̅:
This is what is happening behind that formula:
Transposing a matrix and multiplying it with its non-transposed part creates a square matrix, reduced to lower dimension ([12x9] · [9x12] = [9x9]).
Inverse of this result allows us to solve for b̅.
Multiplying vector y̅ with transposed x reduces the y̅ vector into lower [1x9] dimension. Then, by multiplying [9x9] inverse with [1x9] vector we solved the system for b̅.
Now, we take the [1x9] result vector and create a matrix from it. This is our approximated transformation matrix.
A python code:
import numpy as np
import numpy.linalg
INPUTS = [[5,6,2],[1,7,3],[2,6,5],[1,7,5]]
OUTPUTS = [[3,7,1],[3,7,1],[3,7,2],[3,7,2]]
def get_mat(inputs, outputs, entry_len):
n_of_vectors = inputs.__len__()
noe = n_of_vectors*entry_len# Number of equations
#We need to construct the input matrix.
#We need to linearize the matrix. SO we will flatten the matrix array such as [a11, a12, a21, a22]
#So for each row we combine the row's variables with each input vector.
X_mat = []
for in_n in range(0, n_of_vectors): #For each input vector
#populate all matrix flattened variables. for 2x2 matrix - 4 variables, for 3x3 - 9 variables and so on.
base = 0
for col_n in range(0, entry_len): #Each original unknown matrix's row must be matched to all entries in the input vector
row = [0 for i in range(0, entry_len ** 2)]
for entry in inputs[in_n]:
row[base] = entry
base+=1
X_mat.append(row)
Y_mat = [item for sublist in outputs for item in sublist]
X_np = np.array(X_mat)
Y_np = np.array([Y_mat]).T
solution = np.dot(np.dot(numpy.linalg.inv(np.dot(X_np.T,X_np)),X_np.T),Y_np)
var_mat = solution.reshape(entry_len, entry_len) #create square matrix
return var_mat
transf_mat = get_mat(INPUTS, OUTPUTS, 3) #3 means 3x3 matrix, and in/out vector size 3
print(transf_mat)
for i in range(0,INPUTS.__len__()):
o = np.dot(transf_mat, np.array([INPUTS[i]]).T)
print(f"{INPUTS[i]} x [M] = {o.T} ({OUTPUTS[i]})")
The output is as such:
[[ 0.13654096 0.35890767 0.09530002]
[ 0.31859558 0.83745124 0.22236671]
[ 0.08322497 -0.0526658 0.4417611 ]]
[5, 6, 2] x [M] = [[3.02675088 7.06241873 0.98365224]] ([3, 7, 1])
[1, 7, 3] x [M] = [[2.93479472 6.84785436 1.03984767]] ([3, 7, 1])
[2, 6, 5] x [M] = [[2.90302805 6.77373212 2.05926064]] ([3, 7, 2])
[1, 7, 5] x [M] = [[3.12539476 7.29258778 1.92336987]] ([3, 7, 2])
You can see, that it took all the specified inputs, got the transformed outputs and matched the outputs to the reference vectors. The results are not precise, since we have an approximation from the overspecified system. If we used INPUT and OUTPUT with only 3 vectors, the result would be exact.