ItsMeTheBee

@alexanderswerdlow how did you manage to convert the yolo model? I´m using the same config file as you and I managed to run the model with detect.py after quantizing it...

Okay a little something about that: I was able to compile the model after some modifications in core/common.py and convert_tflite.py In core/common.py I changed leaky relu to relu. In convert_tflite.py...

same here but I´m using a tiny yolo v3 model.... confidence is a lot lower and the bounding boxes often don´t really fit... the center seems to be in the...

Thanks a lot for your fast answer! Unfortunately yes since i need to use ROS Foxy (i could build it with a different python version but that will probably lead...

Thanks a lot for all this information! I checked out the commit you linked and added this little [patch](https://github.com/Ed-Swarthout-NXP/tensorflow/commit/7c25249abb0d09a8ec4053fd237576337125c919). Then i modified the Dockerfile in Tensorflow/lite/tools/pip_package like this: `ARG IMAGE...

> Could you check the model that you loaded during inputs? Usually this only happens if you loaded a file that isn't a tflite model. I´m using the getting started...

@Namburger I played around with your files a bit and i´m either missing something completely obvious or the whole thing is a lot more complicated than i thought :D I...

Hey all! What's the status on irregular nesting? If using a polygon as bin shape is supported, I'd appreciate it very much if you could post a code snippet. EDIT:...

Same here, would appreciate any help =)

In TF1 we were able to add ``` graph_rewriter { quantization { delay: 48000 weight_bits: 8 activation_bits: 8 } ``` to the config file. It seems like this is not...