Fix graphic [d2l-en/img/vgg.svg]

d2l-ai / d2l-en

Interactive deep learning book with multi-framework code, math, and discussions. Adopted at 500 universities from 70 countries including Stanford, MIT, Harvard, and Cambridge.

https://D2L.ai

Other

23.92k stars 4.36k forks source link

Fix graphic [d2l-en/img/vgg.svg] #798

Closed paulaurel closed 4 years ago

paulaurel commented 4 years ago

The VGG network uses a MaxPooling layer with a 2x2 kernel not a 3x3 kernel.

goldmermaid commented 4 years ago

Hi @paulaurel , great catch! Thanks for @cuongvng corrected the text. I made the plot changes as well at PR https://github.com/d2l-ai/d2l-en/pull/881.

Please close this issue if it fits your thoughts. :)

astonzhang commented 4 years ago

Thanks. Closing since it's fixed