/// <summary>
/// Reshape the bottom (input) and top (output) blobs.
/// </summary>
/// <param name="colBottom">Specifies the collection of bottom (input) Blobs.</param>
/// <param name="colTop">Specifies the collection of top (output) Blobs.</param>
public override void Reshape(BlobCollection <T> colBottom, BlobCollection <T> colTop)
{
BiasParameter p = m_param.bias_param;
Blob <T> blobBias = (colBottom.Count > 1) ? colBottom[1] : m_colBlobs[0];
// Always set axis == 0 in special case where bias is a scalar
// (num_axes == 0. Mathematically eqiuvalent for any choice of axis, os the
// actual setting can be safely ignored; and computation is most efficient
// with axis == 0 and (therefore) outer_dim == 1.
int nAxis = (blobBias.num_axes == 0) ? 0 : colBottom[0].CanonicalAxisIndex(p.axis);
m_log.CHECK_GE(colBottom[0].num_axes, nAxis + blobBias.num_axes, "bias blob's shape extends past bottom[0]'s shape when applied starting with bottom[0] axis = " + nAxis.ToString());
for (int i = 0; i < blobBias.num_axes; i++)
{
m_log.CHECK_EQ(colBottom[0].shape(nAxis + i), blobBias.shape(i), "dimension mismatch between bottom[0]->shape(" + (nAxis + i).ToString() + ") and bias->shape(" + i.ToString() + ")");
}
m_nOuterDim = colBottom[0].count(0, nAxis);
m_nBiasDim = blobBias.count();
m_nInnerDim = colBottom[0].count(nAxis + blobBias.num_axes);
m_nDim = m_nBiasDim * m_nInnerDim;
if (colBottom[0] != colTop[0])
{
colTop[0].ReshapeLike(colBottom[0]);
}
m_blobBiasMultiplier.Reshape(new List <int>()
{
m_nInnerDim
});
m_blobBiasMultiplier.SetData(1.0);
}
/// <summary>
/// Setup the layer.
/// </summary>
/// <param name="colBottom">Specifies the collection of bottom (input) Blobs.</param>
/// <param name="colTop">Specifies the collection of top (output) Blobs.</param>
public override void LayerSetUp(BlobCollection <T> colBottom, BlobCollection <T> colTop)
{
if (colBottom.Count == 1 && m_colBlobs.Count > 0)
{
m_log.WriteLine("Skipping parameter initialization.");
}
else if (colBottom.Count == 1)
{
// bias is a learned parameter; initialize it.
BiasParameter p = m_param.bias_param;
int nAxis = colBottom[0].CanonicalAxisIndex(p.axis);
int nNumAxes = p.num_axes;
m_log.CHECK_GE(nNumAxes, -1, "num_axes must be non-negative, or -1 to extend to end of bottom[0].");
if (nNumAxes >= 0)
{
m_log.CHECK_GE(colBottom[0].num_axes, nAxis + nNumAxes, "bias blob's shape extends past bottom[0]'s shape when applied starting with bottom[0] axis = " + nAxis.ToString());
}
m_colBlobs = new BlobCollection <T>();
List <int> rgBiasShape = new List <int>();
int nStart = nAxis;
int nEnd = (nNumAxes == -1) ? colBottom[0].shape().Count : nStart + nNumAxes;
for (int i = nStart; i < nEnd; i++)
{
rgBiasShape.Add(colBottom[0].shape(i));
}
Blob <T> blobBias = new Blob <T>(m_cuda, m_log);
blobBias.Name = m_param.name + " bias";
blobBias.type = BLOB_TYPE.INTERNAL;
blobBias.type = BLOB_TYPE.WEIGHT;
if (!shareParameter(blobBias, rgBiasShape))
{
blobBias.Reshape(rgBiasShape);
FillerParameter fp = p.filler;
if (fp == null)
{
fp = new FillerParameter("constant", 0.0);
}
Filler <T> filler = Filler <T> .Create(m_cuda, m_log, fp);
filler.Fill(blobBias);
}
m_colBlobs.Add(blobBias);
}
m_rgbParamPropagateDown = new DictionaryMap <bool>(m_colBlobs.Count, true);
}
