Routine Descriptor

The routine descriptor specifies the method of using command line options.

Usage
usage: DEVICE[:DTYPE][:CH][/LEVEL][/AUX][@INDICES]

Content of each category

Name	Content
DEVICE	The name of the device family; cpu, opencl, cuda etc., can be used.
DTYPE	The data type; float32 (default), float16, qint8 etc., can be used.
CH	The positioning of channels in the tensor; chf (channels-first),
chl (channels-last：default) are available.
LEVEL	Optimization level of routine algorithms; naive, fast (default), and faster are available.
AUX	Additional information; parameters other than LEVELcan be specified.
INDICES	Specifies the layers using indexes; specifying a single index (such as @1), or multiple indexes (as in @1,2, @1..3) is possible.

Examples

• specify 'DEVICE='cpu', DTYPE='float32', CH='chl', LEVEL='faster' and AUX='wg3x3_nxn'

cpu/faster/wg3x3_nxn

• specify DEVICE='opencl', DTYPE='float16', CH='chl', LEVEL='fast' and AUX=''

opencl:float16

• Specify DEVICE='cpu', DTYPE='float32', CH='chf', LEVEL='naive' and AUX=''

cpu:chf/naive

Example commands that use routine descriptors

• run on GPU using OpenCL

$ softneuro run --routine opencl/fast@2..23 --routine cpu@1,24 vgg16.dnn

• tune on CPU with 8-bit quantization

$ softneuro tune --routine cpu:qint8/fast vgg16.dnn vgg16_tuned.dnn