/// <summary>
/// The ResizeModel method gives the custom trainer the opportunity to resize the model if needed.
/// </summary>
/// <param name="strModel">Specifies the model descriptor.</param>
/// <param name="rgVocabulary">Specifies the vocabulary.</param>
/// <param name="log">Specifies the output log.</param>
/// <returns>A new model discriptor is returned (or the same 'strModel' if no changes were made).</returns>
/// <remarks>Note, this method is called after PreloadData.</remarks>
string IXMyCaffeCustomTrainerRNN.ResizeModel(Log log, string strModel, BucketCollection rgVocabulary)
{
if (rgVocabulary == null || rgVocabulary.Count == 0)
{
return(strModel);
}
int nVocabCount = rgVocabulary.Count;
NetParameter p = NetParameter.FromProto(RawProto.Parse(strModel));
string strEmbedName = "";
EmbedParameter embed = null;
string strIpName = "";
InnerProductParameter ip = null;
foreach (LayerParameter layer in p.layer)
{
if (layer.type == LayerParameter.LayerType.EMBED)
{
strEmbedName = layer.name;
embed = layer.embed_param;
}
else if (layer.type == LayerParameter.LayerType.INNERPRODUCT)
{
strIpName = layer.name;
ip = layer.inner_product_param;
}
}
if (embed != null)
{
if (embed.input_dim != (uint)nVocabCount)
{
log.WriteLine("WARNING: Embed layer '" + strEmbedName + "' input dim changed from " + embed.input_dim.ToString() + " to " + nVocabCount.ToString() + " to accomodate for the vocabulary count.");
embed.input_dim = (uint)nVocabCount;
}
}
if (ip.num_output != (uint)nVocabCount)
{
log.WriteLine("WARNING: InnerProduct layer '" + strIpName + "' num_output changed from " + ip.num_output.ToString() + " to " + nVocabCount.ToString() + " to accomodate for the vocabulary count.");
ip.num_output = (uint)nVocabCount;
}
m_rgVocabulary = rgVocabulary;
RawProto proto = p.ToProto("root");
return(proto.ToString());
}
////////////////////////////////////////////////////////////////////////////////////////////////////
/// <summary> Sets up the inner product. </summary>
///
/// <exception cref="Exception"> Thrown when an exception error condition occurs. </exception>
///
/// <param name="param"> The parameter. </param>
/// <param name="blobs"> The blobs. </param>
/// <param name="name"> The name. </param>
/// <param name="inputNames"> List of names of the inputs. </param>
/// <param name="outputNames"> List of names of the outputs. </param>
///
/// <returns> A Linear. </returns>
////////////////////////////////////////////////////////////////////////////////////////////////////
static Linear SetupInnerProduct(InnerProductParameter param, List <BlobProto> blobs, string name, string[] inputNames, string[] outputNames)
{
if (param.Axis != 1)
{
throw new Exception("Non-default axis in InnerProduct is not supported");
}
int width = GetWidth(blobs[0]);
int height = GetHeight(blobs[0]);
float[] w = blobs[0].Datas;
if (param.BiasTerm)
{
return(new Linear(width, height, !param.BiasTerm, w, blobs[1].Datas, name: name, inputNames: inputNames, outputNames: outputNames));
}
return(new Linear(width, height, !param.BiasTerm, w, name: name));
}
/// <summary>
/// The ResizeModel method gives the custom trainer the opportunity to resize the model if needed.
/// </summary>
/// <param name="strModel">Specifies the model descriptor.</param>
/// <param name="rgVocabulary">Specifies the vocabulary.</param>
/// <returns>A new model discriptor is returned (or the same 'strModel' if no changes were made).</returns>
/// <remarks>Note, this method is called after PreloadData.</remarks>
public string ResizeModel(string strModel, BucketCollection rgVocabulary)
{
if (rgVocabulary == null || rgVocabulary.Count == 0)
{
return(strModel);
}
int nVocabCount = rgVocabulary.Count;
NetParameter p = NetParameter.FromProto(RawProto.Parse(strModel));
EmbedParameter embed = null;
InnerProductParameter ip = null;
foreach (LayerParameter layer in p.layer)
{
if (layer.type == LayerParameter.LayerType.EMBED)
{
embed = layer.embed_param;
}
else if (layer.type == LayerParameter.LayerType.INNERPRODUCT)
{
ip = layer.inner_product_param;
}
}
if (embed != null)
{
embed.input_dim = (uint)nVocabCount;
}
ip.num_output = (uint)nVocabCount;
m_rgVocabulary = rgVocabulary;
RawProto proto = p.ToProto("root");
return(proto.ToString());
}