Value::Value(const NDArrayViewPtr& data, const NDMaskPtr& mask)
: m_data(data), m_mask(mask)
{
if (mask != nullptr)
{
auto dataShape = data->Shape();
auto maskShape = mask->Shape();
if (maskShape.NumAxes() > dataShape.NumAxes())
InvalidArgument("The number of axes of the mask of a Value object cannot exceed the number of axes of the data NDArrayView object");
if (dataShape.SubShape(dataShape.NumAxes() - maskShape.NumAxes()) != maskShape)
InvalidArgument("Invalid Value object; the data and mask are incompatible. The trailing dimensions of the data do not match the dimensions of the mask");
}
}
Value::Value(const NDArrayViewPtr& data, const NDMaskPtr& mask)
: m_data(data), m_mask(mask)
{
if (mask != nullptr)
{
auto dataShape = data->Shape();
auto maskShape = mask->Shape();
if (maskShape.Rank() > dataShape.Rank())
InvalidArgument("The rank (%d) of the mask of a Value object cannot exceed the rank (%d) of the data NDArrayView object", (int)maskShape.Rank(), (int)dataShape.Rank());
if (dataShape.SubShape(dataShape.Rank() - maskShape.Rank()) != maskShape)
InvalidArgument("Invalid Value object; the data and mask are incompatible. The trailing dimensions of the data with shape %S do not match the dimensions of the mask with shape %S", AsStringForErrorReporting(dataShape).c_str(), AsStringForErrorReporting(maskShape).c_str());
}
}
/*static*/ ValuePtr Value::Create(const NDShape& sampleShape, const std::vector<std::vector<ElementType>>& sequences, const DeviceDescriptor& device, bool readOnly/* = false*/)
{
size_t sampleSize = sampleShape.TotalSize();
NDMaskPtr deviceValueMask = CreateMask(sampleSize, sequences, device);
size_t maxSequenceLength = (deviceValueMask == nullptr) ? sequences[0].size() : deviceValueMask->Shape()[0];
size_t numSequences = sequences.size();
NDShape valueDataShape = sampleShape.AppendShape({ maxSequenceLength, numSequences });
NDArrayViewPtr valueData(new NDArrayView(AsDataType<ElementType>(), valueDataShape, DeviceDescriptor::CPUDevice()), [](ReferenceCount* ptr) { delete ptr; });
ElementType* dataBuffer = valueData->WritableDataBuffer<ElementType>();
for (size_t i = 0; i < numSequences; ++i)
std::copy(sequences[i].data(), sequences[i].data() + sequences[i].size(), dataBuffer + (maxSequenceLength * i * sampleSize));
NDArrayViewPtr deviceValueData;
if (device == DeviceDescriptor::CPUDevice())
{
if (readOnly)
deviceValueData = valueData->Alias(true);
else
deviceValueData = valueData;
}
else
{
deviceValueData = NDArrayViewPtr(new NDArrayView(AsDataType<ElementType>(), valueDataShape, device), [](ReferenceCount* ptr) { delete ptr; });
deviceValueData->CopyFrom(*valueData);
if (readOnly)
deviceValueData = deviceValueData->Alias(true);
}
return ValuePtr(new Value(deviceValueData, deviceValueMask), [](ReferenceCount* ptr) { delete ptr; });
}
/*static*/ ValuePtr Value::Create(size_t vocabularySize, const std::vector<std::vector<size_t>>& oneHotSequences, const DeviceDescriptor& device, bool readOnly/* = false*/)
{
NDMaskPtr deviceValueMask = CreateMask(1, oneHotSequences, device);
size_t maxSequenceLength = (deviceValueMask == nullptr) ? oneHotSequences[0].size() : deviceValueMask->Shape()[0];
size_t numSequences = oneHotSequences.size();
NDShape sampleShape = { vocabularySize };
NDShape valueDataShape = sampleShape.AppendShape({ maxSequenceLength, numSequences });
size_t numCSCCols = valueDataShape.SubShape(1).TotalSize() + 1;
std::vector<SparseIndexType> colStarts(numCSCCols);
std::vector<ElementType> nonZeroValues;
std::vector<SparseIndexType> rowIndices;
for (size_t i = 0; i < numSequences; ++i)
{
size_t currentSequenceLength = oneHotSequences[i].size();
size_t j = 0;
for (; j < currentSequenceLength; ++j)
{
colStarts[(i * maxSequenceLength) + j] = (SparseIndexType)nonZeroValues.size();
nonZeroValues.push_back(1);
rowIndices.push_back((SparseIndexType)(oneHotSequences[i][j]));
}
for (; j < maxSequenceLength; ++j)
colStarts[(i * maxSequenceLength) + j] = (SparseIndexType)(nonZeroValues.size());
}
colStarts[numSequences * maxSequenceLength] = (SparseIndexType)(nonZeroValues.size());
NDArrayViewPtr deviceValueData(new NDArrayView(valueDataShape, colStarts.data(), rowIndices.data(), nonZeroValues.data(), nonZeroValues.size(), device, readOnly), [](ReferenceCount* ptr) { delete ptr; });
return ValuePtr(new Value(deviceValueData, deviceValueMask), [](ReferenceCount* ptr) { delete ptr; });
}