![]() Number of scales must be equal to the number of input dimensions. Constructor & Destructor Documentation ◆ ~IResizeLayer() Warning Do not inherit from this class, as doing so will break forward-compatibility of the API and ABI. ( ResizeCoordinateTransformation::kHALF_PIXEL, ResizeSelector::kUPPER).( ResizeCoordinateTransformation::kHALF_PIXEL, ResizeSelector::kFORMULA).( ResizeCoordinateTransformation::kHALF_PIXEL, ResizeSelector::kFORMULA, ResizeRoundMode::kHALF_UP).( ResizeCoordinateTransformation::kHALF_PIXEL, ResizeSelector::kFORMULA, ResizeRoundMode::kHALF_DOWN).( ResizeCoordinateTransformation::kASYMMETRIC, ResizeSelector::kFORMULA, ResizeRoundMode::kFLOOR).If executing this layer on DLA, the following combinations of parameters are supported: ![]() Only static resize layer allows setting scales where the scales are known at build-time. Each output dimension is calculated as floor(input dimension * scale). Dynamic resize layer requires output dimensions to be set as one of the input tensors. Static resize layer requires output dimensions to be known at build-time. It can be done for static as well as dynamic resize layer. The resize layer provides two ways to resize tensor dimensions. The default for all ResizeMode settings (nearest, linear, bilinear, etc.) is ResizeCoordinateTransformation::kASYMMETRIC. The coordinates in the output tensor are mapped to coordinates in the input tensor using a function set by calling setCoordinateTransformation().
0 Comments
Leave a Reply. |
AuthorWrite something about yourself. No need to be fancy, just an overview. ArchivesCategories |