Deep Learning HDL Toolbox™ supports multiple frame mode enabling you to write multiple images into the double data rate (DDR) memory and read back multiple results at the same time. To improve the performance of your deployed deep learning networks, use multiple frame mode.
To format input images to meet the multiple frame input DDR format, you must have:
The start address of the input data for the DDR
The DDR offset for a single input image frame
You can also specify the maximum number of input frames as an optional argument in the
For more information, see Generate DDR Memory Offsets Based On Number of Input Frames.
This graphic shows the format of the input area of the DDR for multiple input images.
To retrieve the results for multiple image inputs from the output area of the DDR, you must have:
The start address of the output area of the DDR
The DDR offset of a single result
The output results must be formatted as a multiple of the FC output feature size. The
information and formatting are generated by the
For more information on the generated DDR address offsets, see External Memory Address Map.
This graphic shows the formatting of the output area of the DDR memory.
After the deep learning network has been deployed, you can manually enable the multiple frame mode by writing the number of frames through a network configuration (NC) port. To manually enter the multiple frame mode at the MATLAB® command line enter:
addrMap('FrameCount') returns the AXI register address for
FrameCount, 15 is the number of images, and hT represents the
that contains the board definition and board interface definition. For more information
about the AXI register addresses, see Deep Learning Processor Register Map.