Refine search
@Override public INDArray getActivation(INDArray in, boolean training) { Nd4j.getExecutioner().execAndReturn(new Swish(in)); return in; }
@Override public INDArray getActivation(INDArray in, boolean training) { Nd4j.getExecutioner().execAndReturn(new Tanh(in)); return in; }
@Override public INDArray getActivation(INDArray in, boolean training) { Nd4j.getExecutioner().execAndReturn(new LeakyReLU(in, alpha)); return in; }
@Override public INDArray getActivation(INDArray in, boolean training) { Nd4j.getExecutioner().execAndReturn(new Cube(in)); return in; }
@Override public INDArray getActivation(INDArray in, boolean training) { Nd4j.getExecutioner().execAndReturn(new SoftSign(in)); return in; }
@Override public INDArray getActivation(INDArray in, boolean training) { Nd4j.getExecutioner().execAndReturn(new RectifiedTanh(in)); return in; }
@Override public INDArray getActivation(INDArray in, boolean training) { Nd4j.getExecutioner().execAndReturn(new HardTanh(in)); return in; }
@Override public INDArray getActivation(INDArray in, boolean training) { Nd4j.getExecutioner().execAndReturn(new OldSoftMax(in)); return in; }
@Override public INDArray getActivation(INDArray in, boolean training) { Nd4j.getExecutioner().execAndReturn(new Relu6(in)); return in; }
@Override public INDArray getActivation(INDArray in, boolean training) { Nd4j.getExecutioner().execAndReturn(new RationalTanh(in)); return in; }
@Override public INDArray getActivation(INDArray in, boolean training) { Nd4j.getExecutioner().execAndReturn(new HardSigmoid(in)); return in; }
@Override public INDArray getActivation(INDArray in, boolean training) { Nd4j.getExecutioner().execAndReturn(new RectifedLinear(in)); return in; }
@Override public INDArray getActivation(INDArray in, boolean training) { Nd4j.getExecutioner().execAndReturn(new Sigmoid(in)); return in; }
/** * Broadcast element-wise multiply op. See: {@link BroadcastMulOp} */ public static INDArray mul(INDArray x, INDArray y, INDArray z, int... dimensions) { if(dimensions == null) { return Nd4j.getExecutioner().execAndReturn(new OldMulOp(x,y,z,x.length())); } return Nd4j.getExecutioner().execAndReturn(new BroadcastMulOp(x,y,z,dimensions)); }
/** * Apply the given elementwise op * * @param op the factory to create the op * @return the new ndarray */ private static INDArray exec(TransformOp op) { if (op.x().isCleanedUp()) throw new IllegalStateException("NDArray already freed"); return Nd4j.getExecutioner().execAndReturn(op); }
/** * Sin function * @param in * @param copy * @return */ public static INDArray sin(INDArray in, boolean copy) { return Nd4j.getExecutioner().execAndReturn(new Sin((copy ? in.dup() : in))); }
/** * Sin function * @param in * @param copy * @return */ public static INDArray atanh(INDArray in, boolean copy) { return Nd4j.getExecutioner().execAndReturn(new ATanh((copy ? in.dup() : in))); }
/** * Cosine similarity * * @param d1 the first vector * @param d2 the second vector * @return the cosine similarities between the 2 arrays * */ public static double cosineSim(@NonNull INDArray d1, @NonNull INDArray d2) { return Nd4j.getExecutioner().execAndReturn(new CosineSimilarity(d1, d2, d1.length())).getFinalResult() .doubleValue(); }
/** * * @param in * @param copy * @return */ public static INDArray cosh(INDArray in, boolean copy) { return Nd4j.getExecutioner().execAndReturn(new Cosh((copy ? in.dup() : in))); }
@Override public void init(INDArray x, INDArray y, INDArray z, long n) { super.init(x, y, z, n); if (Nd4j.executionMode == OpExecutioner.ExecutionMode.JAVA) { if (biasCorrected) this.bias = Nd4j.getExecutioner().execAndReturn(new Bias(x)).getFinalResult().doubleValue(); mean = Nd4j.getExecutioner().execAndReturn(new Mean(x)).getFinalResult().doubleValue(); } }