com.intel.analytics.zoo.pipeline.inference
create an InferenceModel with specified autoScalingEnabled, supportedConcurrentNum and maxConcurrentNum
create an InferenceModel with specified autoScalingEnabled, supportedConcurrentNum and maxConcurrentNum
if auto-scaling is enabled
the concurrentNum of the InferenceModel
a specified InferenceModel
create an auto-scaling disabled InferenceModel with supportedConcurrentNum
create an auto-scaling disabled InferenceModel with supportedConcurrentNum
the concurrentNum of the InferenceModel
an auto-scaling disabled InferenceModel
default constructor, will create a InferenceModel with auto-scaling enabled.
default constructor, will create a InferenceModel with auto-scaling enabled.
an auto-scaling enabled InferenceModel
loads a bigdl, analytics-zoo model
loads a bigdl, analytics-zoo model
the file path of the model
the file path of the weights
loads a caffe model
loads a caffe model
the path of the prototxt file
the path of the caffemodel file
loads a openvino IR
loads a openvino IR
the path of openvino ir xml file
the path of openvino ir bin file
loads a openvino IR Int8
loads a openvino IR Int8
the path of openvino ir xml file
the path of openvino ir bin file
load TF model as OpenVINO IR
load TF model as OpenVINO IR
the path of the tensorflow model
the type of the tensorflow model
the path of the tensorflow checkpoint file
input shape that should be fed to an input node(s) of the model
the boolean value of if need reverse input channels. switch the input channels order from RGB to BGR (or vice versa).
all input values coming from original network inputs will be divided by this value.
the scale value, to be used for the input image per channel.
loads a TF model as OpenVINO
loads a TF model as OpenVINO
the path of the tensorflow model
the type of the tensorflow model, please refer to ModelType e.g. faster_rcnn_resnet101_coco, mask_rcnn_inception_v2_coco, rfcn_resnet101_coco, ssd_inception_v2_coco
the path of the pipeline configure file
the path of the extensions configure file
loads a TF model as OpenVINO
loads a TF model as OpenVINO
the path of the tensorflow model
the path of the pipeline configure file
the path of the extensions configure file
loads a TF model as OpenVINO
loads a TF model as OpenVINO
the path of the tensorflow model
the type of the tensorflow model, please refer to ModelType e.g. faster_rcnn_resnet101_coco, mask_rcnn_inception_v2_coco, rfcn_resnet101_coco, ssd_inception_v2_coco
loads a TF model as TFNet
loads a TF model as TFNet
the path of the tensorflow model
the num of intraOpParallelismThreads
the num of interOpParallelismThreads
whether to perSessionThreads
loads a TF model as TFNet
loads a TF model as TFNet
the path of the tensorflow model file
load TF model as Calibrated OpenVINO IR
load TF model as Calibrated OpenVINO IR
the path of the tensorflow model
the type of the tensorflow model
the path of the tensorflow checkpoint file
input shape that should be fed to an input node(s) of the model
the boolean value of if need reverse input channels. switch the input channels order from RGB to BGR (or vice versa).
all input values coming from original network inputs will be divided by this value.
the scale value, to be used for the input image per channel.
Type of an inferred network, "C" to calibrate Classification, "OD" to calibrate Object Detection, "RawC" to collect only statistics for Classification, "RawOD" to collect only statistics for Object Detection
Path to a file with validation images
Number of pictures from the whole validation set to create the calibration dataset.
the lib path whwere libopencv_imgcodecs.so.4.0, libopencv_core.so.4.0 and libopencv_imgproc.so.4.0 can be found
predicts the inference result
predicts the inference result
the input activity
the output activity
predicts the inference result
predicts the inference result
the input tensor with batch
the output tensor with batch
predicts int8 the inference result
predicts int8 the inference result
the input activity
the output activity
predicts int8 the inference result
predicts int8 the inference result
the input tensor with batch
the output tensor with batch
reloads the bigdl, analytics-zoo model
reloads the bigdl, analytics-zoo model
the file path of the model
the file path of the weights
release original model and all the cloned ones in the queue