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

0 vote295 views1 answer
Kivy display PIL image
Python
3 votes282 views1 answer
Discord py on ready
Python
24 votes313 views6 answers
Pd.read_excel
Python
0 vote292 views1 answer
Django MESSAGE_TAGS
Python
8 votes266 views3 answers
Isnumeric python
Python
0 vote325 views1 answer
Django Signup urls.py
Python
7 votes282 views4 answers
Pytorch save model
Python
18 votes303 views2 answers
Import local module python
Python
4 votes294 views1 answer
Python windows hide files
Python
0 vote302 views1 answer
Django auth user model
Python Django