public class SDCNN extends SDOps
Modifier and Type | Method and Description |
---|---|
SDVariable |
avgPooling2d(SDVariable input,
Pooling2DConfig Pooling2DConfig)
2D Convolution layer operation - average pooling 2d
|
SDVariable |
avgPooling2d(String name,
SDVariable input,
Pooling2DConfig Pooling2DConfig)
2D Convolution layer operation - average pooling 2d
|
SDVariable |
avgPooling3d(SDVariable input,
Pooling3DConfig Pooling3DConfig)
3D convolution layer operation - average pooling 3d
|
SDVariable |
avgPooling3d(String name,
SDVariable input,
Pooling3DConfig Pooling3DConfig)
3D convolution layer operation - average pooling 3d
|
SDVariable |
batchToSpace(SDVariable x,
int[] blocks,
int[] croppingTop,
int... croppingBottom)
Convolution 2d layer batch to space operation on 4d input.
Reduces input batch dimension by rearranging data into a larger spatial dimensions |
SDVariable |
batchToSpace(String name,
SDVariable x,
int[] blocks,
int[] croppingTop,
int... croppingBottom)
Convolution 2d layer batch to space operation on 4d input.
Reduces input batch dimension by rearranging data into a larger spatial dimensions |
SDVariable |
col2Im(SDVariable in,
Conv2DConfig Conv2DConfig)
col2im operation for use in 2D convolution operations.
|
SDVariable |
col2Im(String name,
SDVariable in,
Conv2DConfig Conv2DConfig)
col2im operation for use in 2D convolution operations.
|
SDVariable |
conv1d(SDVariable input,
SDVariable weights,
Conv1DConfig Conv1DConfig)
Conv1d operation.
|
SDVariable |
conv1d(SDVariable input,
SDVariable weights,
SDVariable bias,
Conv1DConfig Conv1DConfig)
Conv1d operation.
|
SDVariable |
conv1d(String name,
SDVariable input,
SDVariable weights,
Conv1DConfig Conv1DConfig)
Conv1d operation.
|
SDVariable |
conv1d(String name,
SDVariable input,
SDVariable weights,
SDVariable bias,
Conv1DConfig Conv1DConfig)
Conv1d operation.
|
SDVariable |
conv2d(SDVariable layerInput,
SDVariable weights,
Conv2DConfig Conv2DConfig)
2D Convolution operation with optional bias
|
SDVariable |
conv2d(SDVariable layerInput,
SDVariable weights,
SDVariable bias,
Conv2DConfig Conv2DConfig)
2D Convolution operation with optional bias
|
SDVariable |
conv2d(String name,
SDVariable layerInput,
SDVariable weights,
Conv2DConfig Conv2DConfig)
2D Convolution operation with optional bias
|
SDVariable |
conv2d(String name,
SDVariable layerInput,
SDVariable weights,
SDVariable bias,
Conv2DConfig Conv2DConfig)
2D Convolution operation with optional bias
|
SDVariable |
conv3d(SDVariable input,
SDVariable weights,
Conv3DConfig Conv3DConfig)
Convolution 3D operation with optional bias
|
SDVariable |
conv3d(SDVariable input,
SDVariable weights,
SDVariable bias,
Conv3DConfig Conv3DConfig)
Convolution 3D operation with optional bias
|
SDVariable |
conv3d(String name,
SDVariable input,
SDVariable weights,
Conv3DConfig Conv3DConfig)
Convolution 3D operation with optional bias
|
SDVariable |
conv3d(String name,
SDVariable input,
SDVariable weights,
SDVariable bias,
Conv3DConfig Conv3DConfig)
Convolution 3D operation with optional bias
|
SDVariable |
deconv2d(SDVariable layerInput,
SDVariable weights,
DeConv2DConfig DeConv2DConfig)
2D deconvolution operation with optional bias
|
SDVariable |
deconv2d(SDVariable layerInput,
SDVariable weights,
SDVariable bias,
DeConv2DConfig DeConv2DConfig)
2D deconvolution operation with optional bias
|
SDVariable |
deconv2d(String name,
SDVariable layerInput,
SDVariable weights,
DeConv2DConfig DeConv2DConfig)
2D deconvolution operation with optional bias
|
SDVariable |
deconv2d(String name,
SDVariable layerInput,
SDVariable weights,
SDVariable bias,
DeConv2DConfig DeConv2DConfig)
2D deconvolution operation with optional bias
|
SDVariable |
deconv3d(SDVariable input,
SDVariable weights,
DeConv3DConfig DeConv3DConfig)
3D CNN deconvolution operation with or without optional bias
|
SDVariable |
deconv3d(SDVariable input,
SDVariable weights,
SDVariable bias,
DeConv3DConfig DeConv3DConfig)
3D CNN deconvolution operation with or without optional bias
|
SDVariable |
deconv3d(String name,
SDVariable input,
SDVariable weights,
DeConv3DConfig DeConv3DConfig)
3D CNN deconvolution operation with or without optional bias
|
SDVariable |
deconv3d(String name,
SDVariable input,
SDVariable weights,
SDVariable bias,
DeConv3DConfig DeConv3DConfig)
3D CNN deconvolution operation with or without optional bias
|
SDVariable |
depthToSpace(SDVariable x,
int blockSize,
DataFormat dataFormat)
Convolution 2d layer batch to space operation on 4d input.
Reduces input channels dimension by rearranging data into a larger spatial dimensions Example: if input has shape [mb, 8, 2, 2] and block size is 2, then output size is [mb, 8/(2*2), 2*2, 2*2] = [mb, 2, 4, 4] |
SDVariable |
depthToSpace(String name,
SDVariable x,
int blockSize,
DataFormat dataFormat)
Convolution 2d layer batch to space operation on 4d input.
Reduces input channels dimension by rearranging data into a larger spatial dimensions Example: if input has shape [mb, 8, 2, 2] and block size is 2, then output size is [mb, 8/(2*2), 2*2, 2*2] = [mb, 2, 4, 4] |
SDVariable |
depthWiseConv2d(SDVariable layerInput,
SDVariable depthWeights,
Conv2DConfig Conv2DConfig)
Depth-wise 2D convolution operation with optional bias
|
SDVariable |
depthWiseConv2d(SDVariable layerInput,
SDVariable depthWeights,
SDVariable bias,
Conv2DConfig Conv2DConfig)
Depth-wise 2D convolution operation with optional bias
|
SDVariable |
depthWiseConv2d(String name,
SDVariable layerInput,
SDVariable depthWeights,
Conv2DConfig Conv2DConfig)
Depth-wise 2D convolution operation with optional bias
|
SDVariable |
depthWiseConv2d(String name,
SDVariable layerInput,
SDVariable depthWeights,
SDVariable bias,
Conv2DConfig Conv2DConfig)
Depth-wise 2D convolution operation with optional bias
|
SDVariable |
dilation2D(SDVariable df,
SDVariable weights,
int[] strides,
int[] rates,
boolean isSameMode)
TODO doc string
|
SDVariable |
dilation2D(String name,
SDVariable df,
SDVariable weights,
int[] strides,
int[] rates,
boolean isSameMode)
TODO doc string
|
SDVariable |
extractImagePatches(SDVariable input,
int kH,
int kW,
int sH,
int sW,
int rH,
int rW,
boolean sameMode)
Extract image patches
|
SDVariable |
extractImagePatches(String name,
SDVariable input,
int kH,
int kW,
int sH,
int sW,
int rH,
int rW,
boolean sameMode)
Extract image patches
|
SDVariable |
im2Col(SDVariable in,
Conv2DConfig Conv2DConfig)
im2col operation for use in 2D convolution operations.
|
SDVariable |
im2Col(String name,
SDVariable in,
Conv2DConfig Conv2DConfig)
im2col operation for use in 2D convolution operations.
|
SDVariable |
localResponseNormalization(SDVariable input,
LocalResponseNormalizationConfig LocalResponseNormalizationConfig)
2D convolution layer operation - local response normalization
|
SDVariable |
localResponseNormalization(String name,
SDVariable input,
LocalResponseNormalizationConfig LocalResponseNormalizationConfig)
2D convolution layer operation - local response normalization
|
SDVariable |
maxPooling2d(SDVariable input,
Pooling2DConfig Pooling2DConfig)
2D Convolution layer operation - max pooling 2d
|
SDVariable |
maxPooling2d(String name,
SDVariable input,
Pooling2DConfig Pooling2DConfig)
2D Convolution layer operation - max pooling 2d
|
SDVariable |
maxPooling3d(SDVariable input,
Pooling3DConfig Pooling3DConfig)
3D convolution layer operation - max pooling 3d operation.
|
SDVariable |
maxPooling3d(String name,
SDVariable input,
Pooling3DConfig Pooling3DConfig)
3D convolution layer operation - max pooling 3d operation.
|
SDVariable[] |
maxPoolWithArgmax(SDVariable input,
Pooling2DConfig Pooling2DConfig)
2D Convolution layer operation - Max pooling on the input and outputs both max values and indices
|
SDVariable[] |
maxPoolWithArgmax(String[] names,
SDVariable input,
Pooling2DConfig Pooling2DConfig)
2D Convolution layer operation - Max pooling on the input and outputs both max values and indices
|
SDVariable |
separableConv2d(SDVariable layerInput,
SDVariable depthWeights,
SDVariable pointWeights,
Conv2DConfig Conv2DConfig)
Separable 2D convolution operation with optional bias
|
SDVariable |
separableConv2d(SDVariable layerInput,
SDVariable depthWeights,
SDVariable pointWeights,
SDVariable bias,
Conv2DConfig Conv2DConfig)
Separable 2D convolution operation with optional bias
|
SDVariable |
separableConv2d(String name,
SDVariable layerInput,
SDVariable depthWeights,
SDVariable pointWeights,
Conv2DConfig Conv2DConfig)
Separable 2D convolution operation with optional bias
|
SDVariable |
separableConv2d(String name,
SDVariable layerInput,
SDVariable depthWeights,
SDVariable pointWeights,
SDVariable bias,
Conv2DConfig Conv2DConfig)
Separable 2D convolution operation with optional bias
|
SDVariable |
spaceToBatch(SDVariable x,
int[] blocks,
int[] paddingTop,
int... paddingBottom)
Convolution 2d layer space to batch operation on 4d input.
Increases input batch dimension by rearranging data from spatial dimensions into batch dimension |
SDVariable |
spaceToBatch(String name,
SDVariable x,
int[] blocks,
int[] paddingTop,
int... paddingBottom)
Convolution 2d layer space to batch operation on 4d input.
Increases input batch dimension by rearranging data from spatial dimensions into batch dimension |
SDVariable |
spaceToDepth(SDVariable x,
int blockSize,
DataFormat dataFormat)
Convolution 2d layer space to depth operation on 4d input.
Increases input channels (reduced spatial dimensions) by rearranging data into a larger channels dimension Example: if input has shape [mb, 2, 4, 4] and block size is 2, then output size is [mb, 8/(2*2), 2*2, 2*2] = [mb, 2, 4, 4] |
SDVariable |
spaceToDepth(String name,
SDVariable x,
int blockSize,
DataFormat dataFormat)
Convolution 2d layer space to depth operation on 4d input.
Increases input channels (reduced spatial dimensions) by rearranging data into a larger channels dimension Example: if input has shape [mb, 2, 4, 4] and block size is 2, then output size is [mb, 8/(2*2), 2*2, 2*2] = [mb, 2, 4, 4] |
SDVariable |
upsampling2d(SDVariable input,
int scale)
Upsampling layer for 2D inputs.
scale is used for both height and width dimensions. |
SDVariable |
upsampling2d(SDVariable input,
int scaleH,
int scaleW,
boolean nchw)
2D Convolution layer operation - Upsampling 2d
|
SDVariable |
upsampling2d(String name,
SDVariable input,
int scale)
Upsampling layer for 2D inputs.
scale is used for both height and width dimensions. |
SDVariable |
upsampling2d(String name,
SDVariable input,
int scaleH,
int scaleW,
boolean nchw)
2D Convolution layer operation - Upsampling 2d
|
SDVariable |
upsampling3d(SDVariable input,
boolean ncdhw,
int scaleD,
int scaleH,
int scaleW)
3D Convolution layer operation - Upsampling 3d
|
SDVariable |
upsampling3d(String name,
SDVariable input,
boolean ncdhw,
int scaleD,
int scaleH,
int scaleW)
3D Convolution layer operation - Upsampling 3d
|
public SDCNN(SameDiff sameDiff)
public SDVariable avgPooling2d(SDVariable input, Pooling2DConfig Pooling2DConfig)
input
- the input to average pooling 2d operation - 4d CNN (image) activations in NCHW format
(shape [minibatch, channels, height, width]) or NHWC format (shape [minibatch, height, width, channels]) (NUMERIC type)Pooling2DConfig
- Configuration Objectpublic SDVariable avgPooling2d(String name, SDVariable input, Pooling2DConfig Pooling2DConfig)
name
- name May be null. Name for the output variableinput
- the input to average pooling 2d operation - 4d CNN (image) activations in NCHW format
(shape [minibatch, channels, height, width]) or NHWC format (shape [minibatch, height, width, channels]) (NUMERIC type)Pooling2DConfig
- Configuration Objectpublic SDVariable avgPooling3d(SDVariable input, Pooling3DConfig Pooling3DConfig)
input
- the input to average pooling 3d operation - 5d activations in NCDHW format
(shape [minibatch, channels, depth, height, width]) or NDHWC format
(shape [minibatch, depth, height, width, channels]) (NUMERIC type)Pooling3DConfig
- Configuration Objectpublic SDVariable avgPooling3d(String name, SDVariable input, Pooling3DConfig Pooling3DConfig)
name
- name May be null. Name for the output variableinput
- the input to average pooling 3d operation - 5d activations in NCDHW format
(shape [minibatch, channels, depth, height, width]) or NDHWC format
(shape [minibatch, depth, height, width, channels]) (NUMERIC type)Pooling3DConfig
- Configuration Objectpublic SDVariable batchToSpace(SDVariable x, int[] blocks, int[] croppingTop, int... croppingBottom)
x
- Input variable. 4d input (NUMERIC type)blocks
- Block size, in the height/width dimension (Size: Exactly(count=2))croppingTop
- (Size: Exactly(count=2))croppingBottom
- (Size: Exactly(count=2))public SDVariable batchToSpace(String name, SDVariable x, int[] blocks, int[] croppingTop, int... croppingBottom)
name
- name May be null. Name for the output variablex
- Input variable. 4d input (NUMERIC type)blocks
- Block size, in the height/width dimension (Size: Exactly(count=2))croppingTop
- (Size: Exactly(count=2))croppingBottom
- (Size: Exactly(count=2))public SDVariable col2Im(SDVariable in, Conv2DConfig Conv2DConfig)
in
- Input - rank 6 input with shape [minibatch, inputChannels, kernelHeight, kernelWidth, outputHeight, outputWidth] (NUMERIC type)Conv2DConfig
- Configuration Objectpublic SDVariable col2Im(String name, SDVariable in, Conv2DConfig Conv2DConfig)
name
- name May be null. Name for the output variablein
- Input - rank 6 input with shape [minibatch, inputChannels, kernelHeight, kernelWidth, outputHeight, outputWidth] (NUMERIC type)Conv2DConfig
- Configuration Objectpublic SDVariable conv1d(SDVariable input, SDVariable weights, SDVariable bias, Conv1DConfig Conv1DConfig)
input
- the inputs to conv1d (NUMERIC type)weights
- weights for conv1d op - rank 3 array with shape [kernelSize, inputChannels, outputChannels] (NUMERIC type)bias
- bias for conv1d op - rank 1 array with shape [outputChannels]. May be null. (NUMERIC type)Conv1DConfig
- Configuration Objectpublic SDVariable conv1d(String name, SDVariable input, SDVariable weights, SDVariable bias, Conv1DConfig Conv1DConfig)
name
- name May be null. Name for the output variableinput
- the inputs to conv1d (NUMERIC type)weights
- weights for conv1d op - rank 3 array with shape [kernelSize, inputChannels, outputChannels] (NUMERIC type)bias
- bias for conv1d op - rank 1 array with shape [outputChannels]. May be null. (NUMERIC type)Conv1DConfig
- Configuration Objectpublic SDVariable conv1d(SDVariable input, SDVariable weights, Conv1DConfig Conv1DConfig)
input
- the inputs to conv1d (NUMERIC type)weights
- weights for conv1d op - rank 3 array with shape [kernelSize, inputChannels, outputChannels] (NUMERIC type)Conv1DConfig
- Configuration Objectpublic SDVariable conv1d(String name, SDVariable input, SDVariable weights, Conv1DConfig Conv1DConfig)
name
- name May be null. Name for the output variableinput
- the inputs to conv1d (NUMERIC type)weights
- weights for conv1d op - rank 3 array with shape [kernelSize, inputChannels, outputChannels] (NUMERIC type)Conv1DConfig
- Configuration Objectpublic SDVariable conv2d(SDVariable layerInput, SDVariable weights, SDVariable bias, Conv2DConfig Conv2DConfig)
layerInput
- the input to max pooling 2d operation - 4d CNN (image) activations in NCHW format (NUMERIC type)weights
- Weights for the convolution operation. 4 dimensions with format [kernelHeight, kernelWidth, inputChannels, outputChannels] (NUMERIC type)bias
- Optional 1D bias array with shape [outputChannels]. May be null. (NUMERIC type)Conv2DConfig
- Configuration Objectpublic SDVariable conv2d(String name, SDVariable layerInput, SDVariable weights, SDVariable bias, Conv2DConfig Conv2DConfig)
name
- name May be null. Name for the output variablelayerInput
- the input to max pooling 2d operation - 4d CNN (image) activations in NCHW format (NUMERIC type)weights
- Weights for the convolution operation. 4 dimensions with format [kernelHeight, kernelWidth, inputChannels, outputChannels] (NUMERIC type)bias
- Optional 1D bias array with shape [outputChannels]. May be null. (NUMERIC type)Conv2DConfig
- Configuration Objectpublic SDVariable conv2d(SDVariable layerInput, SDVariable weights, Conv2DConfig Conv2DConfig)
layerInput
- the input to max pooling 2d operation - 4d CNN (image) activations in NCHW format (NUMERIC type)weights
- Weights for the convolution operation. 4 dimensions with format [kernelHeight, kernelWidth, inputChannels, outputChannels] (NUMERIC type)Conv2DConfig
- Configuration Objectpublic SDVariable conv2d(String name, SDVariable layerInput, SDVariable weights, Conv2DConfig Conv2DConfig)
name
- name May be null. Name for the output variablelayerInput
- the input to max pooling 2d operation - 4d CNN (image) activations in NCHW format (NUMERIC type)weights
- Weights for the convolution operation. 4 dimensions with format [kernelHeight, kernelWidth, inputChannels, outputChannels] (NUMERIC type)Conv2DConfig
- Configuration Objectpublic SDVariable conv3d(SDVariable input, SDVariable weights, SDVariable bias, Conv3DConfig Conv3DConfig)
input
- the input to average pooling 3d operation - 5d activations in NCDHW format
(shape [minibatch, channels, depth, height, width]) or NDHWC format
(shape [minibatch, depth, height, width, channels]) (NUMERIC type)weights
- Weights for conv3d. Rank 5 with shape [kernelDepth, kernelHeight, kernelWidth, inputChannels, outputChannels]. (NUMERIC type)bias
- Optional 1D bias array with shape [outputChannels]. May be null. (NUMERIC type)Conv3DConfig
- Configuration Objectpublic SDVariable conv3d(String name, SDVariable input, SDVariable weights, SDVariable bias, Conv3DConfig Conv3DConfig)
name
- name May be null. Name for the output variableinput
- the input to average pooling 3d operation - 5d activations in NCDHW format
(shape [minibatch, channels, depth, height, width]) or NDHWC format
(shape [minibatch, depth, height, width, channels]) (NUMERIC type)weights
- Weights for conv3d. Rank 5 with shape [kernelDepth, kernelHeight, kernelWidth, inputChannels, outputChannels]. (NUMERIC type)bias
- Optional 1D bias array with shape [outputChannels]. May be null. (NUMERIC type)Conv3DConfig
- Configuration Objectpublic SDVariable conv3d(SDVariable input, SDVariable weights, Conv3DConfig Conv3DConfig)
input
- the input to average pooling 3d operation - 5d activations in NCDHW format
(shape [minibatch, channels, depth, height, width]) or NDHWC format
(shape [minibatch, depth, height, width, channels]) (NUMERIC type)weights
- Weights for conv3d. Rank 5 with shape [kernelDepth, kernelHeight, kernelWidth, inputChannels, outputChannels]. (NUMERIC type)Conv3DConfig
- Configuration Objectpublic SDVariable conv3d(String name, SDVariable input, SDVariable weights, Conv3DConfig Conv3DConfig)
name
- name May be null. Name for the output variableinput
- the input to average pooling 3d operation - 5d activations in NCDHW format
(shape [minibatch, channels, depth, height, width]) or NDHWC format
(shape [minibatch, depth, height, width, channels]) (NUMERIC type)weights
- Weights for conv3d. Rank 5 with shape [kernelDepth, kernelHeight, kernelWidth, inputChannels, outputChannels]. (NUMERIC type)Conv3DConfig
- Configuration Objectpublic SDVariable deconv2d(SDVariable layerInput, SDVariable weights, SDVariable bias, DeConv2DConfig DeConv2DConfig)
layerInput
- the input to deconvolution 2d operation - 4d CNN (image) activations in NCHW format
(shape [minibatch, channels, height, width]) or NHWC format (shape [minibatch, height, width, channels]) (NUMERIC type)weights
- Weights for the 2d deconvolution operation. 4 dimensions with format [inputChannels, outputChannels, kernelHeight, kernelWidth] (NUMERIC type)bias
- Optional 1D bias array with shape [outputChannels]. May be null. (NUMERIC type)DeConv2DConfig
- Configuration Objectpublic SDVariable deconv2d(String name, SDVariable layerInput, SDVariable weights, SDVariable bias, DeConv2DConfig DeConv2DConfig)
name
- name May be null. Name for the output variablelayerInput
- the input to deconvolution 2d operation - 4d CNN (image) activations in NCHW format
(shape [minibatch, channels, height, width]) or NHWC format (shape [minibatch, height, width, channels]) (NUMERIC type)weights
- Weights for the 2d deconvolution operation. 4 dimensions with format [inputChannels, outputChannels, kernelHeight, kernelWidth] (NUMERIC type)bias
- Optional 1D bias array with shape [outputChannels]. May be null. (NUMERIC type)DeConv2DConfig
- Configuration Objectpublic SDVariable deconv2d(SDVariable layerInput, SDVariable weights, DeConv2DConfig DeConv2DConfig)
layerInput
- the input to deconvolution 2d operation - 4d CNN (image) activations in NCHW format
(shape [minibatch, channels, height, width]) or NHWC format (shape [minibatch, height, width, channels]) (NUMERIC type)weights
- Weights for the 2d deconvolution operation. 4 dimensions with format [inputChannels, outputChannels, kernelHeight, kernelWidth] (NUMERIC type)DeConv2DConfig
- Configuration Objectpublic SDVariable deconv2d(String name, SDVariable layerInput, SDVariable weights, DeConv2DConfig DeConv2DConfig)
name
- name May be null. Name for the output variablelayerInput
- the input to deconvolution 2d operation - 4d CNN (image) activations in NCHW format
(shape [minibatch, channels, height, width]) or NHWC format (shape [minibatch, height, width, channels]) (NUMERIC type)weights
- Weights for the 2d deconvolution operation. 4 dimensions with format [inputChannels, outputChannels, kernelHeight, kernelWidth] (NUMERIC type)DeConv2DConfig
- Configuration Objectpublic SDVariable deconv3d(SDVariable input, SDVariable weights, SDVariable bias, DeConv3DConfig DeConv3DConfig)
input
- Input array - shape [bS, iD, iH, iW, iC] (NDHWC) or [bS, iC, iD, iH, iW] (NCDHW) (NUMERIC type)weights
- Weights array - shape [kD, kH, kW, oC, iC] (NUMERIC type)bias
- Bias array - optional, may be null. If non-null, must have shape [outputChannels] (NUMERIC type)DeConv3DConfig
- Configuration Objectpublic SDVariable deconv3d(String name, SDVariable input, SDVariable weights, SDVariable bias, DeConv3DConfig DeConv3DConfig)
name
- name May be null. Name for the output variableinput
- Input array - shape [bS, iD, iH, iW, iC] (NDHWC) or [bS, iC, iD, iH, iW] (NCDHW) (NUMERIC type)weights
- Weights array - shape [kD, kH, kW, oC, iC] (NUMERIC type)bias
- Bias array - optional, may be null. If non-null, must have shape [outputChannels] (NUMERIC type)DeConv3DConfig
- Configuration Objectpublic SDVariable deconv3d(SDVariable input, SDVariable weights, DeConv3DConfig DeConv3DConfig)
input
- Input array - shape [bS, iD, iH, iW, iC] (NDHWC) or [bS, iC, iD, iH, iW] (NCDHW) (NUMERIC type)weights
- Weights array - shape [kD, kH, kW, oC, iC] (NUMERIC type)DeConv3DConfig
- Configuration Objectpublic SDVariable deconv3d(String name, SDVariable input, SDVariable weights, DeConv3DConfig DeConv3DConfig)
name
- name May be null. Name for the output variableinput
- Input array - shape [bS, iD, iH, iW, iC] (NDHWC) or [bS, iC, iD, iH, iW] (NCDHW) (NUMERIC type)weights
- Weights array - shape [kD, kH, kW, oC, iC] (NUMERIC type)DeConv3DConfig
- Configuration Objectpublic SDVariable depthToSpace(SDVariable x, int blockSize, DataFormat dataFormat)
x
- the input to depth to space pooling 2d operation - 4d activations in NCHW format
(shape [minibatch, channels, height, width]) or NHWC format (shape [minibatch, height, width, channels]) (NUMERIC type)blockSize
- Block size, in the height/width dimensiondataFormat
- Data format: "NCHW" or "NHWC"public SDVariable depthToSpace(String name, SDVariable x, int blockSize, DataFormat dataFormat)
name
- name May be null. Name for the output variablex
- the input to depth to space pooling 2d operation - 4d activations in NCHW format
(shape [minibatch, channels, height, width]) or NHWC format (shape [minibatch, height, width, channels]) (NUMERIC type)blockSize
- Block size, in the height/width dimensiondataFormat
- Data format: "NCHW" or "NHWC"public SDVariable depthWiseConv2d(SDVariable layerInput, SDVariable depthWeights, SDVariable bias, Conv2DConfig Conv2DConfig)
layerInput
- the input to max pooling 2d operation - 4d CNN (image) activations in NCHW format (NUMERIC type)depthWeights
- Depth-wise conv2d weights. 4 dimensions with format [kernelHeight, kernelWidth, inputChannels, depthMultiplier] (NUMERIC type)bias
- Optional 1D bias array with shape [outputChannels]. May be null. (NUMERIC type)Conv2DConfig
- Configuration Objectpublic SDVariable depthWiseConv2d(String name, SDVariable layerInput, SDVariable depthWeights, SDVariable bias, Conv2DConfig Conv2DConfig)
name
- name May be null. Name for the output variablelayerInput
- the input to max pooling 2d operation - 4d CNN (image) activations in NCHW format (NUMERIC type)depthWeights
- Depth-wise conv2d weights. 4 dimensions with format [kernelHeight, kernelWidth, inputChannels, depthMultiplier] (NUMERIC type)bias
- Optional 1D bias array with shape [outputChannels]. May be null. (NUMERIC type)Conv2DConfig
- Configuration Objectpublic SDVariable depthWiseConv2d(SDVariable layerInput, SDVariable depthWeights, Conv2DConfig Conv2DConfig)
layerInput
- the input to max pooling 2d operation - 4d CNN (image) activations in NCHW format (NUMERIC type)depthWeights
- Depth-wise conv2d weights. 4 dimensions with format [kernelHeight, kernelWidth, inputChannels, depthMultiplier] (NUMERIC type)Conv2DConfig
- Configuration Objectpublic SDVariable depthWiseConv2d(String name, SDVariable layerInput, SDVariable depthWeights, Conv2DConfig Conv2DConfig)
name
- name May be null. Name for the output variablelayerInput
- the input to max pooling 2d operation - 4d CNN (image) activations in NCHW format (NUMERIC type)depthWeights
- Depth-wise conv2d weights. 4 dimensions with format [kernelHeight, kernelWidth, inputChannels, depthMultiplier] (NUMERIC type)Conv2DConfig
- Configuration Objectpublic SDVariable dilation2D(SDVariable df, SDVariable weights, int[] strides, int[] rates, boolean isSameMode)
df
- (NUMERIC type)weights
- df (NUMERIC type)strides
- weights (Size: Exactly(count=2))rates
- strides (Size: Exactly(count=2))isSameMode
- isSameModepublic SDVariable dilation2D(String name, SDVariable df, SDVariable weights, int[] strides, int[] rates, boolean isSameMode)
name
- name May be null. Name for the output variabledf
- (NUMERIC type)weights
- df (NUMERIC type)strides
- weights (Size: Exactly(count=2))rates
- strides (Size: Exactly(count=2))isSameMode
- isSameModepublic SDVariable extractImagePatches(SDVariable input, int kH, int kW, int sH, int sW, int rH, int rW, boolean sameMode)
input
- Input array. Must be rank 4, with shape [minibatch, height, width, channels] (NUMERIC type)kH
- Kernel heightkW
- Kernel widthsH
- Stride heightsW
- Stride widthrH
- Rate heightrW
- Rate widthsameMode
- If true: use same mode padding. If falsepublic SDVariable extractImagePatches(String name, SDVariable input, int kH, int kW, int sH, int sW, int rH, int rW, boolean sameMode)
name
- name May be null. Name for the output variableinput
- Input array. Must be rank 4, with shape [minibatch, height, width, channels] (NUMERIC type)kH
- Kernel heightkW
- Kernel widthsH
- Stride heightsW
- Stride widthrH
- Rate heightrW
- Rate widthsameMode
- If true: use same mode padding. If falsepublic SDVariable im2Col(SDVariable in, Conv2DConfig Conv2DConfig)
in
- Input - rank 4 input with shape [minibatch, inputChannels, height, width] (NUMERIC type)Conv2DConfig
- Configuration Objectpublic SDVariable im2Col(String name, SDVariable in, Conv2DConfig Conv2DConfig)
name
- name May be null. Name for the output variablein
- Input - rank 4 input with shape [minibatch, inputChannels, height, width] (NUMERIC type)Conv2DConfig
- Configuration Objectpublic SDVariable localResponseNormalization(SDVariable input, LocalResponseNormalizationConfig LocalResponseNormalizationConfig)
input
- the inputs to lrn (NUMERIC type)LocalResponseNormalizationConfig
- Configuration Objectpublic SDVariable localResponseNormalization(String name, SDVariable input, LocalResponseNormalizationConfig LocalResponseNormalizationConfig)
name
- name May be null. Name for the output variableinput
- the inputs to lrn (NUMERIC type)LocalResponseNormalizationConfig
- Configuration Objectpublic SDVariable[] maxPoolWithArgmax(SDVariable input, Pooling2DConfig Pooling2DConfig)
input
- the input to max pooling 2d operation - 4d CNN (image) activations in NCHW format
(shape [minibatch, channels, height, width]) or NHWC format (shape [minibatch, height, width, channels]) (NUMERIC type)Pooling2DConfig
- Configuration Objectpublic SDVariable[] maxPoolWithArgmax(String[] names, SDVariable input, Pooling2DConfig Pooling2DConfig)
names
- names May be null. Arrays of names for the output variables.input
- the input to max pooling 2d operation - 4d CNN (image) activations in NCHW format
(shape [minibatch, channels, height, width]) or NHWC format (shape [minibatch, height, width, channels]) (NUMERIC type)Pooling2DConfig
- Configuration Objectpublic SDVariable maxPooling2d(SDVariable input, Pooling2DConfig Pooling2DConfig)
input
- the input to max pooling 2d operation - 4d CNN (image) activations in NCHW format
(shape [minibatch, channels, height, width]) or NHWC format (shape [minibatch, height, width, channels]) (NUMERIC type)Pooling2DConfig
- Configuration Objectpublic SDVariable maxPooling2d(String name, SDVariable input, Pooling2DConfig Pooling2DConfig)
name
- name May be null. Name for the output variableinput
- the input to max pooling 2d operation - 4d CNN (image) activations in NCHW format
(shape [minibatch, channels, height, width]) or NHWC format (shape [minibatch, height, width, channels]) (NUMERIC type)Pooling2DConfig
- Configuration Objectpublic SDVariable maxPooling3d(SDVariable input, Pooling3DConfig Pooling3DConfig)
input
- the input to average pooling 3d operation - 5d activations in NCDHW format
(shape [minibatch, channels, depth, height, width]) or NDHWC format
(shape [minibatch, depth, height, width, channels]) (NUMERIC type)Pooling3DConfig
- Configuration Objectpublic SDVariable maxPooling3d(String name, SDVariable input, Pooling3DConfig Pooling3DConfig)
name
- name May be null. Name for the output variableinput
- the input to average pooling 3d operation - 5d activations in NCDHW format
(shape [minibatch, channels, depth, height, width]) or NDHWC format
(shape [minibatch, depth, height, width, channels]) (NUMERIC type)Pooling3DConfig
- Configuration Objectpublic SDVariable separableConv2d(SDVariable layerInput, SDVariable depthWeights, SDVariable pointWeights, SDVariable bias, Conv2DConfig Conv2DConfig)
layerInput
- the input to max pooling 2d operation - 4d CNN (image) activations in NCHW format
(shape [minibatch, channels, height, width]) or NHWC format (shape [minibatch, height, width, channels]) (NUMERIC type)depthWeights
- Separable conv2d depth weights. 4 dimensions with format [kernelHeight, kernelWidth, inputChannels, depthMultiplier] (NUMERIC type)pointWeights
- Point weights, rank 4 with format [1, 1, inputChannels*depthMultiplier, outputChannels]. May be null (NUMERIC type)bias
- Optional bias, rank 1 with shape [outputChannels]. May be null. (NUMERIC type)Conv2DConfig
- Configuration Objectpublic SDVariable separableConv2d(String name, SDVariable layerInput, SDVariable depthWeights, SDVariable pointWeights, SDVariable bias, Conv2DConfig Conv2DConfig)
name
- name May be null. Name for the output variablelayerInput
- the input to max pooling 2d operation - 4d CNN (image) activations in NCHW format
(shape [minibatch, channels, height, width]) or NHWC format (shape [minibatch, height, width, channels]) (NUMERIC type)depthWeights
- Separable conv2d depth weights. 4 dimensions with format [kernelHeight, kernelWidth, inputChannels, depthMultiplier] (NUMERIC type)pointWeights
- Point weights, rank 4 with format [1, 1, inputChannels*depthMultiplier, outputChannels]. May be null (NUMERIC type)bias
- Optional bias, rank 1 with shape [outputChannels]. May be null. (NUMERIC type)Conv2DConfig
- Configuration Objectpublic SDVariable separableConv2d(SDVariable layerInput, SDVariable depthWeights, SDVariable pointWeights, Conv2DConfig Conv2DConfig)
layerInput
- the input to max pooling 2d operation - 4d CNN (image) activations in NCHW format
(shape [minibatch, channels, height, width]) or NHWC format (shape [minibatch, height, width, channels]) (NUMERIC type)depthWeights
- Separable conv2d depth weights. 4 dimensions with format [kernelHeight, kernelWidth, inputChannels, depthMultiplier] (NUMERIC type)pointWeights
- Point weights, rank 4 with format [1, 1, inputChannels*depthMultiplier, outputChannels]. May be null (NUMERIC type)Conv2DConfig
- Configuration Objectpublic SDVariable separableConv2d(String name, SDVariable layerInput, SDVariable depthWeights, SDVariable pointWeights, Conv2DConfig Conv2DConfig)
name
- name May be null. Name for the output variablelayerInput
- the input to max pooling 2d operation - 4d CNN (image) activations in NCHW format
(shape [minibatch, channels, height, width]) or NHWC format (shape [minibatch, height, width, channels]) (NUMERIC type)depthWeights
- Separable conv2d depth weights. 4 dimensions with format [kernelHeight, kernelWidth, inputChannels, depthMultiplier] (NUMERIC type)pointWeights
- Point weights, rank 4 with format [1, 1, inputChannels*depthMultiplier, outputChannels]. May be null (NUMERIC type)Conv2DConfig
- Configuration Objectpublic SDVariable spaceToBatch(SDVariable x, int[] blocks, int[] paddingTop, int... paddingBottom)
x
- Input variable. 4d input (NUMERIC type)blocks
- Block size, in the height/width dimension (Size: Exactly(count=2))paddingTop
- Optional 2d int[] array for padding the result: values [[pad top, pad bottom], [pad left, pad right]] (Size: Exactly(count=2))paddingBottom
- Optional 2d int[] array for padding the result: values [[pad top, pad bottom], [pad left, pad right]] (Size: Exactly(count=2))public SDVariable spaceToBatch(String name, SDVariable x, int[] blocks, int[] paddingTop, int... paddingBottom)
name
- name May be null. Name for the output variablex
- Input variable. 4d input (NUMERIC type)blocks
- Block size, in the height/width dimension (Size: Exactly(count=2))paddingTop
- Optional 2d int[] array for padding the result: values [[pad top, pad bottom], [pad left, pad right]] (Size: Exactly(count=2))paddingBottom
- Optional 2d int[] array for padding the result: values [[pad top, pad bottom], [pad left, pad right]] (Size: Exactly(count=2))public SDVariable spaceToDepth(SDVariable x, int blockSize, DataFormat dataFormat)
x
- the input to depth to space pooling 2d operation - 4d activations in NCHW format
(shape [minibatch, channels, height, width]) or NHWC format (shape [minibatch, height, width, channels]) (NUMERIC type)blockSize
- Block size, in the height/width dimensiondataFormat
- Data format: "NCHW" or "NHWC"public SDVariable spaceToDepth(String name, SDVariable x, int blockSize, DataFormat dataFormat)
name
- name May be null. Name for the output variablex
- the input to depth to space pooling 2d operation - 4d activations in NCHW format
(shape [minibatch, channels, height, width]) or NHWC format (shape [minibatch, height, width, channels]) (NUMERIC type)blockSize
- Block size, in the height/width dimensiondataFormat
- Data format: "NCHW" or "NHWC"public SDVariable upsampling2d(SDVariable input, int scale)
input
- Input in NCHW format (NUMERIC type)scale
- The scale for both height and width dimensions.public SDVariable upsampling2d(String name, SDVariable input, int scale)
name
- name May be null. Name for the output variableinput
- Input in NCHW format (NUMERIC type)scale
- The scale for both height and width dimensions.public SDVariable upsampling2d(SDVariable input, int scaleH, int scaleW, boolean nchw)
input
- Input in NCHW format (NUMERIC type)scaleH
- Scale to upsample in height dimensionscaleW
- Scale to upsample in width dimensionnchw
- If true: input is in NCHW (minibatch, channels, height, width) format. False: NHWC formatpublic SDVariable upsampling2d(String name, SDVariable input, int scaleH, int scaleW, boolean nchw)
name
- name May be null. Name for the output variableinput
- Input in NCHW format (NUMERIC type)scaleH
- Scale to upsample in height dimensionscaleW
- Scale to upsample in width dimensionnchw
- If true: input is in NCHW (minibatch, channels, height, width) format. False: NHWC formatpublic SDVariable upsampling3d(SDVariable input, boolean ncdhw, int scaleD, int scaleH, int scaleW)
input
- Input in NCHW format (NUMERIC type)ncdhw
- If true: input is in NCDHW (minibatch, channels, depth, height, width) format. False: NDHWC formatscaleD
- Scale to upsample in depth dimensionscaleH
- Scale to upsample in height dimensionscaleW
- Scale to upsample in width dimensionpublic SDVariable upsampling3d(String name, SDVariable input, boolean ncdhw, int scaleD, int scaleH, int scaleW)
name
- name May be null. Name for the output variableinput
- Input in NCHW format (NUMERIC type)ncdhw
- If true: input is in NCDHW (minibatch, channels, depth, height, width) format. False: NDHWC formatscaleD
- Scale to upsample in depth dimensionscaleH
- Scale to upsample in height dimensionscaleW
- Scale to upsample in width dimensionCopyright © 2020. All rights reserved.