- Add PoseNet support
- Add an asynch option to offload the TfLite run from the UI thread
- Add Deeplab support
- Add pix2pix support
- Make number of detections dynamic in Android
- Add detectObjectOnBinary
- Add runModelOnFrame
- Add detectObjectOnFrame
- Support Object Detection with SSD MobileNet and Tiny Yolov2.
- Updated to TensorFlow Lite API v1.12.0.
- No longer accepts parameter
inputSize
andnumChannels
. They will be retrieved from input tensor. numThreads
is moved toTflite.loadModel
.
- Support byte list: runModelOnBinary
- Support Swift based project
- Pass error message in channel in Android.
- Use non hard coded label size in iOS.
- Fixed link.
- Initial release.