device- specifies which device will be used for infer (
gpu_0and so on).
model- path to prototxt file with Caffe model for your topology. (Optional, if not provided the search of model will be performed)
weights- path to caffemodel file with weights for your topology. (Optional, if not provided, the search of caffemodel will be performed in the same directory where prototxt located)
adapter- approach how raw output will be converted to representation of dataset problem, some adapters can be specific to framework. You can find detailed instruction how to use adapters here.
You also can specify batch size for your model using
batch and allow to reshape input layer to data shape, using specific parameter:
allow_reshape_input (default value is False).
In case when you model has several inputs you should provide list of input layers in launcher config section using key
inputs. Each input description should has following info:
name- input layer name in network
type- type of input values, it has impact on filling policy. Available options:
CONST_INPUT- input will be filled using constant provided in config. It also requires to provide
IMAGE_INFO- specific key for setting information about input shape to layer (used in Faster RCNN based topologies). You do not need provide
value, because it will be calculated in runtime. Format value is
Nx[H, W, S], where
Nis batch size,
H- original image height,
W- original image width,
S- scale of original image (default 1).
ORIG_IMAGE_INFO- specific key for setting information about original image size before preprocessing.
INPUT- network input for main data stream (e. g. images). If you have several data inputs, you should provide regular expression for identifier as
valuefor specifying which one data should be provided in specific input.
IGNORE_INPUT- input which should be stayed empty during evaluation. Optionally you can determine
shapeof input (actually does not used, Caffe launcher uses info given from network),
layoutin case when your model was trained with non-standard data layout (For Caffe default layout is
FP16- signed shot,
U8- unsigned char,
U16- unsigned short int,
I8- signed char,
I16- short int,
I64- long int).
Caffe launcher config example: