Hi,
Is there a reason there is no camera demo?
Just due to complexity or because of some kind of limitation?
I am also wondering why this works, when I can't find any Object Detection models from TF that have been converted to coreml anywhere.
For example these: ssd_mobilenet_v1_coco, ssd_inception_v2_coco, faster_rcnn_resnet101_coco
It seems on the TensorFlow repo there is discussion about how the model is not supported in TFLite yet.
Hi, Is there a reason there is no camera demo? Just due to complexity or because of some kind of limitation?
I am also wondering why this works, when I can't find any Object Detection models from TF that have been converted to coreml anywhere. For example these: ssd_mobilenet_v1_coco, ssd_inception_v2_coco, faster_rcnn_resnet101_coco
It seems on the TensorFlow repo there is discussion about how the model is not supported in TFLite yet.
https://github.com/tensorflow/tensorflow/issues/14670
Meanwhile on the tfcoreml repo there is an example script for converting the SSD android model: https://github.com/tf-coreml/tf-coreml/blob/master/examples/ssd_example.ipynb
I assume until TensorFlow Lite is stable it might be better to switch to using CoreML Models?