ObjectDetector

Performs object detection on images.

The API expects a TFLite model with TFLite Model Metadata..

The API supports models with one image input tensor and four output tensors. To be more specific, here are the requirements.

• Input image tensor (kTfLiteUInt8/kTfLiteFloat32)
  • image input of size [batch x height x width x channels].
  • batch inference is not supported (batch is required to be 1).
  • only RGB inputs are supported (channels is required to be 3).
  • if type is kTfLiteFloat32, NormalizationOptions are required to be attached to the metadata for input normalization.
• Output tensors must be the 4 outputs of a DetectionPostProcess op, i.e:
  • Location tensor (kTfLiteFloat32):
    • tensor of size [1 x num_results x 4], the inner array representing bounding boxes in the form [top, left, right, bottom].
    • BoundingBoxProperties are required to be attached to the metadata and must specify type=BOUNDARIES and coordinate_type=RATIO.
  • Classes tensor (kTfLiteFloat32):
    • tensor of size [1 x num_results], each value representing the integer index of a class.
    • if label maps are attached to the metadata as TENSOR_VALUE_LABELS associated files, they are used to convert the tensor values into labels.
  • scores tensor (kTfLiteFloat32):
    • tensor of size [1 x num_results], each value representing the score of the detected object.
  • Number of detection tensor (kTfLiteFloat32):
    • integer num_results as a tensor of size [1].

An example of such model can be found on TensorFlow Hub..