Clara Holoscan v0.2.0
1.0

Class FormatConverter

class nvidia::holoscan::formatconverter::FormatConverter : public gxf::Codelet

Helper codelet for common tensor operations in inference pipelines.

Provides a codelet that provides common video or tensor operations in inference pipelines to change datatypes, resize images, reorder channels, and normalize and scale values.

Public Functions

gxf_result_t start() override

gxf_result_t tick() override

gxf_result_t stop() override

gxf_result_t registerInterface(gxf::Registrar *registrar) override

gxf::Expected<void*> resizeImage(const void *in_tensor_data, const int32_t rows, const int32_t columns, const int16_t channels, const gxf::PrimitiveType primitive_type, const int32_t resize_width, const int32_t resize_height)

gxf_result_t convertTensorFormat(const void *in_tensor_data, void *out_tensor_data, const int32_t rows, const int32_t columns, const int16_t in_channels, const int16_t out_channels)

© Copyright 2022, NVIDIA. Last updated on Jun 28, 2023.