ObjectDetector
Related Doc:
package infer
Path prefix from where to load the model artifacts. These include the symbol, parameters, and synset.txt. Example: file://model-dir/ssd_resnet50_512 (containing ssd_resnet50_512-symbol.json, ssd_resnet50_512-0000.params, and synset.txt)
Descriptors defining the input node names, shape, layout and type parameters
Device contexts on which you want to run inference. Defaults to CPU.
Model epoch to load; defaults to 0
To classify batch of input images according to the provided model
To classify batch of input images according to the provided model
Input array of buffered images
Number of result elements to return, sorted by probability
List of list of tuples of (class, probability)
Detects objects and returns bounding boxes with corresponding class/label
Detects objects and returns bounding boxes with corresponding class/label
Path prefix of the input image
Number of result elements to return, sorted by probability
List of list of tuples of (class, [probability, xmin, ymin, xmax, ymax])
Takes input images as NDArrays.
Takes input images as NDArrays. Useful when you want to perform multiple operations on the input array, or when you want to pass a batch of input images.
Indexed Sequence of NDArrays
(Optional) How many top_k (sorting will be based on the last axis) elements to return. If not passed, returns all unsorted output.
List of list of tuples of (class, [probability, xmin, ymin, xmax, ymax])
The ObjectDetector class helps to run ObjectDetection tasks where the goal is to find bounding boxes and corresponding labels for objects in a image.