andy
dcc57e2c85
Affected files: .obsidian/graph.json .obsidian/workspace-mobile.json .obsidian/workspace.json Gaming/Steam controllers.md History/Britain.md STEM/AI/Neural Networks/CNN/CNN.md STEM/AI/Neural Networks/CNN/FCN/FCN.md STEM/AI/Neural Networks/CNN/FCN/ResNet.md STEM/AI/Neural Networks/CV/Datasets.md STEM/AI/Neural Networks/Properties+Capabilities.md STEM/AI/Neural Networks/Transformers/Attention.md STEM/AI/Properties.md Tattoo/Engineering.md Tattoo/Sources.md Tattoo/img/snake-coil.png Untitled.canvas
30 lines
785 B
Markdown
30 lines
785 B
Markdown
- Residual networks
|
|
- 152 layers
|
|
- Skips every two layers
|
|
- Residual block
|
|
- Later layers learning the identity function
|
|
- Skips help
|
|
- Deep network should be at least as good as shallower one by allowing some layers to do very little
|
|
- Vanishing gradient
|
|
- Allows shortcut paths for gradients
|
|
- Accuracy saturation
|
|
- Adding more layers to suitably deep network increases training error
|
|
|
|
# Design
|
|
|
|
- Skips across pairs of [[Convolutional Layer|conv layers]]
|
|
- Elementwise addition
|
|
- All layer 3x3 kernel
|
|
- Spatial size halves each layer
|
|
- Filters doubles each layer
|
|
- [[FCN|Fully convolutional]]
|
|
- No fc layer
|
|
- No [[Max Pooling|pooling]]
|
|
- Except at end
|
|
- No dropout
|
|
|
|
[[Datasets#ImageNet|ImageNet]] Error:
|
|
![[imagenet-error.png]]
|
|
|
|
![[resnet-arch.png]]
|
|
![[resnet-arch2.png]] |