Class UNet
java.lang.Object
ai.beestream.jitnn.nn.Module
ai.beestream.jitnn.nn.models.UNet
- All Implemented Interfaces:
AutoCloseable
A small U-Net (Ronneberger et al., 2015) for 28x28 inputs with two down-sampling levels:
double 3x3 convolutions with ReLU, max pooling, a bottleneck, then one level up through a
stride-2 transposed convolution and one through bilinear upsampling and a 1x1 convolution,
each concatenated with the encoder's features of that size; a 1x1 convolution gives one logit
per pixel. Convolutions are seeded in construction order (encoder, bottleneck, decoder, head).
-
Constructor Summary
ConstructorsConstructorDescriptionUNet(int in, int width, long seed) A U-Net over images ofinchannels,widthchannels at the first level (doubling at each level down), initialised fromseed. -
Method Summary
Methods inherited from class Module
buffer, buffers, child, close, isClosed, isTraining, loadStateDict, parameter, parameterCount, parameters, stateDict, train, zeroGrad
-
Constructor Details
-
UNet
public UNet(int in, int width, long seed) A U-Net over images ofinchannels,widthchannels at the first level (doubling at each level down), initialised fromseed.
-
-
Method Details
-
forward
-