public class NDNN extends Object
Constructor and Description |
---|
NDNN() |
Modifier and Type | Method and Description |
---|---|
INDArray |
batchNorm(INDArray input,
INDArray mean,
INDArray variance,
INDArray gamma,
INDArray beta,
double epsilon,
int... axis)
|
INDArray |
biasAdd(INDArray input,
INDArray bias,
boolean nchw)
Bias addition operation: a special case of addition, typically used with CNN 4D activations and a 1D bias vector
|
INDArray |
dotProductAttention(INDArray queries,
INDArray keys,
INDArray values,
INDArray mask,
boolean scaled)
This operation performs dot product attention on the given timeseries input with the given queries
out = sum(similarity(k_i, q) * v_i) similarity(k, q) = softmax(k * q) where x * q is the dot product of x and q Optionally with normalization step: similarity(k, q) = softmax(k * q / sqrt(size(q)) See also "Attention is all you need" (https://arxiv.org/abs/1706.03762, p. |
INDArray |
dropout(INDArray input,
double inputRetainProbability)
Dropout operation
|
INDArray |
elu(INDArray x)
Element-wise exponential linear unit (ELU) function:
out = x if x > 0 out = a * (exp(x) - 1) if x <= 0 with constant a = 1.0 |
INDArray |
gelu(INDArray x)
GELU activation function - Gaussian Error Linear Units
For more details, see Gaussian Error Linear Units (GELUs) - https://arxiv.org/abs/1606.08415 This method uses the sigmoid approximation |
INDArray |
hardSigmoid(INDArray x)
Element-wise hard sigmoid function:
out[i] = 0 if in[i] <= -2.5 out[1] = 0.2*in[i]+0.5 if -2.5 < in[i] < 2.5 out[i] = 1 if in[i] >= 2.5 |
INDArray |
hardTanh(INDArray x)
Element-wise hard tanh function:
out[i] = -1 if in[i] <= -1 out[1] = in[i] if -1 < in[i] < 1 out[i] = 1 if in[i] >= 1 |
INDArray |
hardTanhDerivative(INDArray x)
Derivative (dOut/dIn) of the element-wise hard Tanh function - hardTanh(INDArray)
|
INDArray |
layerNorm(INDArray input,
INDArray gain,
boolean channelsFirst,
int... dimensions)
Apply Layer Normalization
y = gain * standardize(x) + bias |
INDArray |
layerNorm(INDArray input,
INDArray gain,
INDArray bias,
boolean channelsFirst,
int... dimensions)
Apply Layer Normalization
y = gain * standardize(x) + bias |
INDArray |
leakyRelu(INDArray x,
INDArray alpha)
Element-wise leaky ReLU function:
out = x if x >= 0.0 out = alpha * x if x < cutoff Alpha value is most commonly set to 0.01 |
INDArray |
leakyReluDerivative(INDArray x,
INDArray alpha)
Leaky ReLU derivative: dOut/dIn given input.
|
INDArray |
linear(INDArray input,
INDArray weights,
INDArray bias)
Linear layer operation: out = mmul(in,w) + bias
Note that bias array is optional |
INDArray |
logSigmoid(INDArray x)
Element-wise sigmoid function: out[i] = log(sigmoid(in[i]))
|
INDArray |
logSoftmax(INDArray x)
Log softmax activation
|
INDArray |
logSoftmax(INDArray x,
int dimension)
Log softmax activation
|
INDArray |
multiHeadDotProductAttention(INDArray queries,
INDArray keys,
INDArray values,
INDArray Wq,
INDArray Wk,
INDArray Wv,
INDArray Wo,
INDArray mask,
boolean scaled)
This performs multi-headed dot product attention on the given timeseries input
out = concat(head_1, head_2, ..., head_n) * Wo head_i = dot_product_attention(Wq_i*q, Wk_i*k, Wv_i*v) Optionally with normalization when calculating the attention for each head. See also "Attention is all you need" (https://arxiv.org/abs/1706.03762, pp. |
INDArray |
prelu(INDArray input,
INDArray alpha,
int... sharedAxes)
PReLU (Parameterized Rectified Linear Unit) operation.
|
INDArray |
relu(INDArray x,
double cutoff)
Element-wise rectified linear function with specified cutoff:
out[i] = in[i] if in[i] >= cutoff out[i] = 0 otherwise |
INDArray |
relu6(INDArray x,
double cutoff)
Element-wise "rectified linear 6" function with specified cutoff:
out[i] = min(max(in, cutoff), 6) |
INDArray |
reluLayer(INDArray input,
INDArray weights,
INDArray bias)
ReLU (Rectified Linear Unit) layer operation: out = relu(mmul(in,w) + bias)
Note that bias array is optional |
INDArray |
selu(INDArray x)
Element-wise SeLU function - Scaled exponential Lineal Unit: see Self-Normalizing Neural Networks
out[i] = scale * alpha * (exp(in[i])-1) if in[i]>0, or 0 if in[i] <= 0 Uses default scale and alpha values. |
INDArray |
sigmoid(INDArray x)
Element-wise sigmoid function: out[i] = 1.0/(1+exp(-in[i]))
|
INDArray |
sigmoidDerivative(INDArray x,
INDArray wrt)
Element-wise sigmoid function derivative: dL/dIn given input and dL/dOut
|
INDArray |
softmax(INDArray x,
int dimension)
Softmax activation, along the specified dimension
|
INDArray |
softmaxDerivative(INDArray x,
INDArray wrt,
int dimension)
Softmax derivative function
|
INDArray |
softplus(INDArray x)
Element-wise softplus function: out = log(exp(x) + 1)
|
INDArray |
softsign(INDArray x)
Element-wise softsign function: out = x / (abs(x) + 1)
|
INDArray |
softsignDerivative(INDArray x)
Element-wise derivative (dOut/dIn) of the softsign function softsign(INDArray)
|
INDArray |
swish(INDArray x)
Element-wise "swish" function: out = x * sigmoid(b*x) with b=1.0
See: https://arxiv.org/abs/1710.05941 |
public INDArray batchNorm(INDArray input, INDArray mean, INDArray variance, INDArray gamma, INDArray beta, double epsilon, int... axis)
input
- Input variable. (NUMERIC type)mean
- Mean value. For 1d axis, this should match input.size(axis) (NUMERIC type)variance
- Variance value. For 1d axis, this should match input.size(axis) (NUMERIC type)gamma
- Gamma value. For 1d axis, this should match input.size(axis) (NUMERIC type)beta
- Beta value. For 1d axis, this should match input.size(axis) (NUMERIC type)epsilon
- Epsilon constant for numerical stability (to avoid division by 0)axis
- For 2d CNN activations: 1 for NCHW format activations, or 3 for NHWC format activations.
For 3d CNN activations: 1 for NCDHW format, 4 for NDHWC
For 1d/RNN activations: 1 for NCW format, 2 for NWC (Size: AtLeast(min=1))public INDArray biasAdd(INDArray input, INDArray bias, boolean nchw)
input
- 4d input variable (NUMERIC type)bias
- 1d bias (NUMERIC type)nchw
- The format - nchw=true means [minibatch, channels, height, width] format; nchw=false - [minibatch, height, width, channels].
Unused for 2d inputspublic INDArray dotProductAttention(INDArray queries, INDArray keys, INDArray values, INDArray mask, boolean scaled)
queries
- input 3D array "queries" of shape [batchSize, featureKeys, queryCount]
or 4D array of shape [batchSize, numHeads, featureKeys, queryCount] (NUMERIC type)keys
- input 3D array "keys" of shape [batchSize, featureKeys, timesteps]
or 4D array of shape [batchSize, numHeads, featureKeys, timesteps] (NUMERIC type)values
- input 3D array "values" of shape [batchSize, featureValues, timesteps]
or 4D array of shape [batchSize, numHeads, featureValues, timesteps] (NUMERIC type)mask
- OPTIONAL; array that defines which values should be skipped of shape [batchSize, timesteps] (NUMERIC type)scaled
- normalization, false -> do not apply normalization, true -> apply normalizationpublic INDArray dropout(INDArray input, double inputRetainProbability)
input
- Input array (NUMERIC type)inputRetainProbability
- Probability of retaining an input (set to 0 with probability 1-p)public INDArray elu(INDArray x)
x
- Input variable (NUMERIC type)public INDArray gelu(INDArray x)
x
- Input variable (NUMERIC type)public INDArray hardSigmoid(INDArray x)
x
- Input variable (NUMERIC type)public INDArray hardTanh(INDArray x)
x
- Input variable (NUMERIC type)public INDArray hardTanhDerivative(INDArray x)
x
- Input variable (NUMERIC type)public INDArray layerNorm(INDArray input, INDArray gain, INDArray bias, boolean channelsFirst, int... dimensions)
input
- Input variable (NUMERIC type)gain
- Gain (NUMERIC type)bias
- Bias (NUMERIC type)channelsFirst
- For 2D input - unused. True for NCHW (minibatch, channels, height, width), false for NHWC datadimensions
- Dimensions to perform layer norm over - dimension=1 for 2d/MLP data, dimension=1,2,3 for CNNs (Size: AtLeast(min=1))public INDArray layerNorm(INDArray input, INDArray gain, boolean channelsFirst, int... dimensions)
input
- Input variable (NUMERIC type)gain
- Gain (NUMERIC type)channelsFirst
- For 2D input - unused. True for NCHW (minibatch, channels, height, width), false for NHWC datadimensions
- Dimensions to perform layer norm over - dimension=1 for 2d/MLP data, dimension=1,2,3 for CNNs (Size: AtLeast(min=1))public INDArray leakyRelu(INDArray x, INDArray alpha)
x
- Input variable (NUMERIC type)alpha
- Cutoff - commonly 0.01 (NUMERIC type)public INDArray leakyReluDerivative(INDArray x, INDArray alpha)
x
- Input variable (NUMERIC type)alpha
- Cutoff - commonly 0.01 (NUMERIC type)public INDArray linear(INDArray input, INDArray weights, INDArray bias)
input
- Input data (NUMERIC type)weights
- Weights variable, shape [nIn, nOut] (NUMERIC type)bias
- Optional bias variable (may be null) (NUMERIC type)public INDArray logSigmoid(INDArray x)
x
- Input variable (NUMERIC type)public INDArray logSoftmax(INDArray x)
x
- (NUMERIC type)public INDArray logSoftmax(INDArray x, int dimension)
x
- Input (NUMERIC type)dimension
- Dimension along which to apply log softmaxpublic INDArray multiHeadDotProductAttention(INDArray queries, INDArray keys, INDArray values, INDArray Wq, INDArray Wk, INDArray Wv, INDArray Wo, INDArray mask, boolean scaled)
queries
- input 3D array "queries" of shape [batchSize, featureKeys, queryCount] (NUMERIC type)keys
- input 3D array "keys" of shape [batchSize, featureKeys, timesteps] (NUMERIC type)values
- input 3D array "values" of shape [batchSize, featureValues, timesteps] (NUMERIC type)Wq
- input query projection weights of shape [numHeads, projectedKeys, featureKeys] (NUMERIC type)Wk
- input key projection weights of shape [numHeads, projectedKeys, featureKeys] (NUMERIC type)Wv
- input value projection weights of shape [numHeads, projectedValues, featureValues] (NUMERIC type)Wo
- output projection weights of shape [numHeads * projectedValues, outSize] (NUMERIC type)mask
- OPTIONAL; array that defines which values should be skipped of shape [batchSize, timesteps] (NUMERIC type)scaled
- normalization, false -> do not apply normalization, true -> apply normalizationpublic INDArray prelu(INDArray input, INDArray alpha, int... sharedAxes)
input
- Input data (NUMERIC type)alpha
- The cutoff variable. Note that the batch dimension (the 0th, whether it is batch or not) should not be part of alpha. (NUMERIC type)sharedAxes
- Which axes to share cutoff parameters along. (Size: AtLeast(min=1))public INDArray relu(INDArray x, double cutoff)
x
- Input (NUMERIC type)cutoff
- Cutoff value for ReLU operation - x > cutoff ? x : 0. Usually 0public INDArray relu6(INDArray x, double cutoff)
x
- Input (NUMERIC type)cutoff
- Cutoff value for ReLU operation. Usually 0public INDArray reluLayer(INDArray input, INDArray weights, INDArray bias)
input
- Input data (NUMERIC type)weights
- Weights variable (NUMERIC type)bias
- Optional bias variable (may be null) (NUMERIC type)public INDArray selu(INDArray x)
x
- Input variable (NUMERIC type)public INDArray sigmoid(INDArray x)
x
- Input variable (NUMERIC type)public INDArray sigmoidDerivative(INDArray x, INDArray wrt)
x
- Input Variable (NUMERIC type)wrt
- Gradient at the output - dL/dOut. Must have same shape as the input (NUMERIC type)public INDArray softmax(INDArray x, int dimension)
x
- Input (NUMERIC type)dimension
- Dimension along which to apply softmaxpublic INDArray softmaxDerivative(INDArray x, INDArray wrt, int dimension)
x
- Softmax input (NUMERIC type)wrt
- Gradient at output, dL/dx (NUMERIC type)dimension
- Softmax dimensionpublic INDArray softplus(INDArray x)
x
- Input variable (NUMERIC type)public INDArray softsign(INDArray x)
x
- Input variable (NUMERIC type)public INDArray softsignDerivative(INDArray x)
x
- Input variable (NUMERIC type)public INDArray swish(INDArray x)
x
- Input variable (NUMERIC type)Copyright © 2019. All rights reserved.