https://github.com/pxl-th/resnet.jl
ResNet implementation in Julia
https://github.com/pxl-th/resnet.jl
flux julia neural-networks resnet
Last synced: over 1 year ago
JSON representation
ResNet implementation in Julia
- Host: GitHub
- URL: https://github.com/pxl-th/resnet.jl
- Owner: pxl-th
- License: mit
- Created: 2020-06-23T20:53:27.000Z (about 6 years ago)
- Default Branch: master
- Last Pushed: 2022-02-05T23:25:58.000Z (over 4 years ago)
- Last Synced: 2025-02-17T07:35:13.171Z (over 1 year ago)
- Topics: flux, julia, neural-networks, resnet
- Language: Julia
- Homepage:
- Size: 52.7 KB
- Stars: 11
- Watchers: 3
- Forks: 1
- Open Issues: 0
-
Metadata Files:
- Readme: README.md
- License: LICENSE
Awesome Lists containing this project
README
# ResNet
Create model:
```julia
model = ResNetModel(18; in_channels=3, classes=10)
```
or you can ommit classification layer,
by specifying number of `classes` as `nothing`.
- simple:
```julia
y = x |> model
```
- extract list of features:
```julia
features = model(x, Val(:stages))
```
Number of channels for each element of `features` is in `model.stages`.
Size of the model is in `model.size`.