---------------------------------------------------------------------------
Usage: konduit config [-m] [-o <output-file>] -p <config> [-pr <value>] [-y]
A helper command for creating boilerplate json/yaml for inference configuration
This command is a utility to create boilerplate json/yaml configurations that can be conveniently modified to start konduit servers.
-- FOR SEQUENCE PIPELINES--
- Prints 'logging -> tensorflow -> logging' config in pretty format:
$ konduit config -p logging,tensorflow,logging
- Prints 'logging -> tensorflow -> logging' config with gRPC protocol
$ konduit config -p logging,tensorflow,logging -pr grpc
- Prints 'dl4j -> logging' config in minified format:
$ konduit config -p dl4j,logging -m
- Saves 'dl4j -> logging' config in a 'config.json' file:
$ konduit config -p dl4j,logging -o config.json
- Saves 'dl4j -> logging' config in a 'config.yaml' file:
$ konduit config -p dl4j,logging -y -o config.json
-- FOR GRAPH PIPELINES --
- Generates a config that logs the input(1) then flow them through two
tensorflow models(2,3) and merges the output(4):
1=logging(input),2=tensorflow(1),3=tensorflow(1),4=merge(2,3)
- Generates a config that logs the input(1) then channels(2) them through one
of the two tensorflow models(3,4) and then selects the output(5) based
on the value of the selection integer field 'select'
1=logging(input),[2_1,2_2]=switch(int,select,1),3=tensorflow(2_1),4=tensorflow(2_2),5=any(3,4)
- Generates a config that logs the input(1) then channels(2) them through one
of the two tensorflow models(3,4) and then selects the output(5) based
on the value of the selection string field 'select' in the selection map
$ konduit config -p 1=logging(input),[2_1,2_2]=switch(string,select,x:0,y:1,1),3=tensorflow(2_1),4=tensorflow(2_2),5=any(3,4)
-m,--minified If set, the output json will be printed in a
single line, without indentations. (Ignored
-o,--output <output-file> Optional: If set, the generated json/yaml will
be saved here. Otherwise, it's printed on the
-p,--pipeline <config> A comma-separated list of sequence/graph
steps to create boilerplate configuration
sequences, allowed values are: [crop_grid,
crop_fixed_grid, dl4j, keras,
Draw_bounding_box, draw_fixed_grid, draw_grid,
draw_segmentation,extract_bounding_box,
Camera_frame_capture, video_frame_capture,
Image_to_ndarray, logging,
ssd_to_bounding_box, samediff, show_image,
tensorflow, nd4jtensorflow, python, onnx].
For graphs, the list item should be in the
'<output>=<type>(<inputs>)' or
'[outputs]=switch(<inputs>)' for switches. The
pre-defined root input is named, 'input'.
'a=tensorflow(input),b=dl4j(input)' Merge
'c=merge(a,b)' Switch Step (int):
'[d1,d2,d3]=switch(int,select,input)' Switch
'[d1,d2,d3]=switch(string,select,x:1,y:2,z:3,input)'
'Any Step: 'e=any(d1,d2,d3)' See the examples
above for more usage information.
-pr,--protocol <value> Protocol to use with the server. Allowed
-y,--yaml Set if you want the output to be a yaml
---------------------------------------------------------------------------