public CumProd(SameDiff sameDiff, SDVariable x, boolean exclusive, boolean reverse, int... dimension) { super(null, sameDiff, new SDVariable[]{x}); this.sameDiff = sameDiff; this.dimensions = dimension; this.exclusive = exclusive; this.reverse = reverse; addArgs(); }
@Override public Type getOpType() { return opType(); } }
public Variance(INDArray x, boolean biasCorrected) { super(x); this.biasCorrected = biasCorrected; init(x, y, z, n); }
public void addArgs() { addIArgument(reductionMode); addTArgument(labelSmoothing); }
public void addArgs() { addIArgument(reductionMode); addTArgument(labelSmoothing); }
public SDVariable variance(SDVariable i_x, boolean biasCorrected, int... dimensions) { return new Variance(sameDiff(), i_x, dimensions, biasCorrected).outputVariables()[0]; }
public CumSum(SameDiff sameDiff, SDVariable x, boolean exclusive, boolean reverse, int... dimension) { super(null, sameDiff, new SDVariable[]{x}); this.sameDiff = sameDiff; this.dimensions = dimension; this.exclusive = exclusive; this.reverse = reverse; addArgs(); }
public NormalizeMoments(SameDiff sameDiff, SDVariable counts, SDVariable means, SDVariable variances, double shift) { super(null, sameDiff, new SDVariable[] {counts, means, variances}, false); this.shift = shift; addArgs(); }
protected void addArgs() { addIArgument(exclusive ? 1 : 0, reverse ? 1 : 0); if (dimensions != null && dimensions.length > 0) addIArgument(dimensions); }
public SigmoidCrossEntropyLoss(SameDiff sameDiff, SDVariable logits, SDVariable weights, SDVariable labels, int reductionMode, double labelSmoothing) { super(null, sameDiff, new SDVariable[]{logits, weights, labels}, false); this.reductionMode = reductionMode; this.labelSmoothing = labelSmoothing; this.sameDiff = sameDiff; addArgs(); }
private void addArgs() { for (int axis: axes) { addIArgument(axis); } }
public SoftmaxCrossEntropyLoss(SameDiff sameDiff, SDVariable logits, SDVariable weights, SDVariable labels, int reductionMode, double labelSmoothing) { super(null, sameDiff, new SDVariable[]{logits, weights, labels}, false); this.reductionMode = reductionMode; this.labelSmoothing = labelSmoothing; this.sameDiff = sameDiff; addArgs(); }
protected void addArgs() { addIArgument(exclusive ? 1 : 0, reverse ? 1 : 0); if (dimensions != null && dimensions.length > 0) addIArgument(dimensions); }
@Override public float zeroHalf() { return zeroFloat(); }
private void addArgs() { addTArgument(shift); }
public Variance(INDArray x, INDArray y, long n, boolean biasCorrected) { super(x, y, n); this.biasCorrected = biasCorrected; init(x, y, z, n); }
public CumProd(SameDiff sameDiff, SDVariable x, int... dimension) { super(null, sameDiff, new SDVariable[]{x}); this.sameDiff = sameDiff; this.dimensions = dimension; addArgs(); }
public CumSum(SameDiff sameDiff, SDVariable x, int... dimension) { super(null, sameDiff, new SDVariable[]{x}); this.sameDiff = sameDiff; this.dimensions = dimension; addArgs(); }
public Variance(INDArray x, INDArray y, INDArray z, long n, boolean biasCorrected) { super(x, y, z, n); this.biasCorrected = biasCorrected; init(x, y, z, n); }
public Variance(INDArray x, INDArray y, INDArray z, long n) { super(x, y, z, n); init(x, y, z, n); }