Hacker News
new
|
past
|
comments
|
ask
|
show
|
jobs
|
submit
login
king_magic
on April 11, 2021
|
parent
|
context
|
favorite
| on:
A common mistake when NumPy’s RNG with PyTorch
Aside from the infuriating clickbait title (which I shall not dignify with an upvote), this is part of why I preprocess augmented images. I don't like too much magic in my custom derived (PyTorch) Dataset objects.
Guidelines
|
FAQ
|
Lists
|
API
|
Security
|
Legal
|
Apply to YC
|
Contact
Search: