/** Compute y <- alpha*op(a)*x + beta * y (general matrix vector multiplication) */
public static FloatMatrix gemv(
float alpha, FloatMatrix a, FloatMatrix x, float beta, FloatMatrix y) {
if (false) {
NativeBlas.sgemv(
'N', a.rows, a.columns, alpha, a.data, 0, a.rows, x.data, 0, 1, beta, y.data, 0, 1);
} else {
if (beta == 0.0f) {
for (int i = 0; i < y.length; i++) y.data[i] = 0.0f;
for (int j = 0; j < a.columns; j++) {
float xj = x.get(j);
if (xj != 0.0f) {
for (int i = 0; i < a.rows; i++) y.data[i] += a.get(i, j) * xj;
}
}
} else {
for (int j = 0; j < a.columns; j++) {
float byj = beta * y.data[j];
float xj = x.get(j);
for (int i = 0; i < a.rows; i++) y.data[j] = a.get(i, j) * xj + byj;
}
}
}
return y;
}
public static FloatMatrix conv2d(FloatMatrix input, FloatMatrix kernel, Type type) {
FloatMatrix xShape = new FloatMatrix(1, 2);
xShape.put(0, input.rows);
xShape.put(1, input.columns);
FloatMatrix yShape = new FloatMatrix(1, 2);
yShape.put(0, kernel.rows);
yShape.put(1, kernel.columns);
FloatMatrix zShape = xShape.add(yShape).sub(1);
int retRows = (int) zShape.get(0);
int retCols = (int) zShape.get(1);
ComplexFloatMatrix fftInput = complexDisceteFourierTransform(input, retRows, retCols);
ComplexFloatMatrix fftKernel = complexDisceteFourierTransform(kernel, retRows, retCols);
ComplexFloatMatrix mul = fftKernel.mul(fftInput);
ComplexFloatMatrix retComplex = complexInverseDisceteFourierTransform(mul);
FloatMatrix ret = retComplex.getReal();
if (type == Type.VALID) {
FloatMatrix validShape = xShape.subi(yShape).add(1);
FloatMatrix start = zShape.sub(validShape).div(2);
FloatMatrix end = start.add(validShape);
if (start.get(0) < 1 || start.get(1) < 1)
throw new IllegalStateException("Illegal row index " + start);
if (end.get(0) < 1 || end.get(1) < 1)
throw new IllegalStateException("Illegal column index " + end);
ret =
ret.get(
RangeUtils.interval((int) start.get(0), (int) end.get(0)),
RangeUtils.interval((int) start.get(1), (int) end.get(1)));
}
return ret;
}