Numpy multidimensional indexing

# Let's say you have a batch of 256 inputs, each one has a set of 64 points.
x.shape --> (256, 64, 3)

# Now assume you want to index each image and draw 128 samples of those points,
# with an indices matrix.
idx.shape --> (256, 128)

# Do
y = x[np.arange(x.shape[0]), idx.T].reshape((1, 0, 2))
y.shape --> (256, 128, 3)

Similar codes

3 votes264 views1 answer
Colab cuda version
Python
1 vote330 views2 answers
Python file basename
Python
5 votes333 views3 answers
Iterating with index in for loops python
Python
0 vote315 views1 answer
Remove prefix in python 3.6
Python
1 vote342 views3 answers
Copy a list to another list python
Python
0 vote317 views1 answer
Pytorch reduce dataset dataloader
Python
0 vote327 views1 answer
A int and float. python
Python
12 votes270 views3 answers
List insert
Python
0 vote314 views1 answer
How to see if something is in a class in python
Python
4 votes338 views3 answers
ArrayField in Django
Python