Thanks to visit codestin.com
Credit goes to github.com

Skip to content

Conversation

@rzietal
Copy link

@rzietal rzietal commented Oct 26, 2020

This actually works

@DhairyaLGandhi
Copy link
Owner

DhairyaLGandhi commented Oct 26, 2020

Dup of #9?

@rzietal
Copy link
Author

rzietal commented Oct 26, 2020

Dup of #9?

Almost complete rewrite. Use what you like.

y = reshape(y, rsize..., 1, 1)
x, y

@with_kw mutable struct Dataset
Copy link
Owner

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

This may not scale to how every dataset is stored, depending on the directory layout

return value.i
end

function target_to_onehot(target, nfeatures)
Copy link
Owner

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

This should be using Flux.onehot otherwise it would be slow.

Chain(x->expand_dims(x,2),
BatchNorm(out_ch),
x->squeeze(x))
DoubleConv(in_channels, out_channels; conv_kernel = (3,3), conv_pad = (1,1)) =
Copy link
Owner

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Might be more idiomatic to match the Flux.Conv API

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Labels

None yet

Projects

None yet

Development

Successfully merging this pull request may close these issues.

2 participants