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

1 vote142 views1 answer
How to get sum specific columns value in machine learning
Python
1 vote115 views2 answers
Count none in list python
Python
0 vote107 views1 answer
Correlation between images python
Python
0 vote151 views1 answer
Django authenticate with email
Python Django
0 vote131 views3 answers
When was python 3.8 released
Python
0 vote123 views1 answer
Python if type dict
Python
8 votes133 views3 answers
How to set default python version in macos
Python
11 votes119 views1 answer
How to upgrade 3.6 to 3.7 on linux
Python
2 votes111 views2 answers
Make a list in python 3
Python
1 vote125 views1 answer
Python dividing strings by amount of letters
Python