Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Fix VGG dropout probability #272

Merged
merged 4 commits into from
Jan 18, 2024
Merged

Fix VGG dropout probability #272

Changes from 3 commits
Commits
Show all changes
4 commits
Select commit Hold shift + click to select a range
3f6f607
Fix VGG Dropout probability
adrhill Jan 15, 2024
69b34c3
Remove kwarg `dropout_prob`
adrhill Jan 16, 2024
be19ebf
Remove kwarg `dropout_prob` from docstring
adrhill Jan 16, 2024
01bb4ad
Increment patch version number to 0.9.3
adrhill Jan 17, 2024
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
5 changes: 3 additions & 2 deletions src/convnets/vgg.jl
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -109,7 +109,7 @@ Create a VGG style model with specified `depth`.
([reference](https://arxiv.org/abs/1409.1556v6)).

!!! warning

`VGG` does not currently support pretrained weights for the `batchnorm = true` option.

# Arguments
Expand All @@ -130,7 +130,8 @@ end
function VGG(depth::Integer; pretrain::Bool = false, batchnorm::Bool = false,
inchannels::Integer = 3, nclasses::Integer = 1000)
_checkconfig(depth, keys(VGG_CONFIGS))
layers = vgg((224, 224); config = VGG_CONFIGS[depth], batchnorm, inchannels, nclasses)
layers = vgg((224, 224); config = VGG_CONFIGS[depth], batchnorm, inchannels, nclasses,
dropout_prob = 0.5)
model = VGG(layers)
if pretrain
artifact_name = string("vgg", depth)
Expand Down
Loading