d2l-en
d2l-en copied to clipboard
MXNet/PT Non Ideal Results NiN
The loss/accuracy plots are problematic for both MXNet and PyTorch.
@mli @astonzhang http://preview.d2l.ai/d2l-en/master/chapter_convolutional-modern/nin.html
@StevenJokes plz see my comments https://github.com/d2l-ai/d2l-en/pull/1176