public class Conv2D extends Convolution
The input to a Conv2D
is an NDList
with a single 4-D NDArray
. The layout of the NDArray
must be "NCHW". The
shapes are
data: (batch_size, channel, height, width)
weight: (num_filter, channel, kernel[0], kernel[1])
bias: (num_filter,)
out: (batch_size, num_filter, out_height, out_width)
out_height = f(height, kernel[0], pad[0], stride[0], dilate[0])
out_width = f(width, kernel[1], pad[1], stride[1], dilate[1])
where f(x, k, p, s, d) = floor((x + 2 * p - d * (k - 1) - 1)/s) + 1
Both weight
and bias
are learn-able parameters.
Modifier and Type | Class and Description |
---|---|
static class |
Conv2D.Builder
|
Convolution.ConvolutionBuilder<T extends Convolution.ConvolutionBuilder>
bias, dilate, includeBias, kernel, numFilters, numGroups, pad, stride, weight
inputNames, inputShapes
Modifier and Type | Method and Description |
---|---|
static Conv2D.Builder |
builder()
Creates a builder to build a
Conv2D . |
protected LayoutType[] |
getExpectedLayout()
Returns the expected layout of the input.
|
protected java.lang.String |
getStringLayout()
Returns the string representing the layout of the input.
|
protected int |
numDimensions()
Returns the number of dimensions of the input.
|
beforeInitialize, forward, getDirectParameters, getOutputShapes, getParameterShape, loadParameters, saveParameters
getChildren, initialize, toString
cast, clear, describeInput, getParameters, isInitialized, readInputShapes, saveInputShapes, setInitializer, setInitializer
clone, equals, finalize, getClass, hashCode, notify, notifyAll, wait, wait, wait
forward, validateLayout
protected LayoutType[] getExpectedLayout()
getExpectedLayout
in class Convolution
protected java.lang.String getStringLayout()
getStringLayout
in class Convolution
protected int numDimensions()
numDimensions
in class Convolution
public static Conv2D.Builder builder()
Conv2D
.