andy
7bc4dffd8b
Affected files: STEM/AI/Neural Networks/CNN/Examples.md STEM/AI/Neural Networks/CNN/FCN/FCN.md STEM/AI/Neural Networks/CNN/FCN/ResNet.md STEM/AI/Neural Networks/CNN/FCN/Skip Connections.md STEM/AI/Neural Networks/CNN/GAN/DC-GAN.md STEM/AI/Neural Networks/CNN/GAN/GAN.md STEM/AI/Neural Networks/CNN/Interpretation.md STEM/AI/Neural Networks/CNN/UpConv.md STEM/AI/Neural Networks/Deep Learning.md STEM/AI/Neural Networks/MLP/MLP.md STEM/AI/Neural Networks/Properties+Capabilities.md STEM/AI/Neural Networks/SLP/Least Mean Square.md STEM/AI/Neural Networks/SLP/SLP.md STEM/AI/Neural Networks/Transformers/Transformers.md STEM/AI/Properties.md STEM/CS/Language Binding.md STEM/CS/Languages/dotNet.md STEM/Signal Proc/Image/Image Processing.md
35 lines
1.1 KiB
Markdown
35 lines
1.1 KiB
Markdown
- Fractionally strided convolution
|
|
- Transposed [Convolution](../../../Signal%20Proc/Convolution.md)
|
|
- Like a deep interpolation
|
|
- Convolution with a fractional input stride
|
|
- Up-sampling is convolution 'in reverse'
|
|
- Not an actual inverse convolution
|
|
- For scaling up by a factor of $f$
|
|
- Consider as a [Convolution](../../../Signal%20Proc/Convolution.md) of stride $1/f$
|
|
- Could specify kernel
|
|
- Or learn
|
|
- Can have multiple upconv layers
|
|
- Separated by [ReLu](../Activation%20Functions.md#ReLu)
|
|
- For non-linear up-sampling conv
|
|
- Interpolation is linear
|
|
|
|
|
|
|
|
# Convolution Matrix
|
|
Normal
|
|
|
|
|
|
|
|
- Equivalent operation with a flattened input
|
|
- Row per kernel location
|
|
- Many-to-one operation
|
|
|
|
|
|
|
|
[Understanding transposed convolutions](https://www.machinecurve.com/index.php/2019/09/29/understanding-transposed-convolutions/)
|
|
|
|
## Transposed
|
|
|
|
- One-to-many
|
|
|
|
 |