Hemanth-Jonnala

Thanks for sharing the details.. wondering do you have any CPU tflite model with same width and heght?

I used [detect_poses](https://github.com/google-coral/coralmicro/blob/main/examples/detect_poses/detect_poses.cc#L44) script with your test image to test 324x324 and 353x481 edgetpu models on Dev Board Micro. The bin file got generated with the below snippet: ``` python3...

Hi, I have reported this issue to the internal team. Unfortuantley, as of now they don't have any bandwidth to look into this..Thanks!

> matches the input tensor. i.e. input: 1x256x256x3, output: 1x256x256x3 > > However all the examples expect there to be an output per-label per-pixel. i.e. input: 1x256x256x3, output: 1x256x256x21 Coral...

The issue is not happenning on my Linux machine. Are you running on a virtual machine? If so, please try the same thing on native OS. ``` :uname -a Linux...

can you please share the inference time results for USB port pass through vs USB PCI card pass through. Thanks!!

Feel free to replace the [identity](https://github.com/google-coral/project-posenet/blob/master/gstreamer.py#L358) with other methods mentioned at: https://gstreamer.freedesktop.org/documentation/video/gstvideo.html?gi-language=c#GstVideoOrientationMethod. I think, 180 would work.

Have you tried any other methods mentioned at: https://gstreamer.freedesktop.org/documentation/video/gstvideo.html?gi-language=c#GstVideoOrientationMethod ?

Hmm..does just changing the pose detections without persons form pose camera works for you? 1. `mkdir images` 2. Initialize` i=1 `at: https://github.com/google-coral/project-posenet/blob/master/pose_camera.py#L132 3. https://github.com/hjonnala/snippets/blob/main/posenet/pose_camera.py#L145 4. and add the below lines...

> ... INFO: Build completed successfully, 708 total actions mkdir -p /workspace/pycoral/pybind mkdir: cannot create directory '/workspace/pycoral/pybind': Permission denied ... Please add the sudo before docker command and try to...