UcefMountacer

I had a similar issue with yolo v4 tiny: ``` tensorflow.lite.python.convert_phase.ConverterError: :0: error: loc("batch_normalization/moving_mean"): is not immutable, try removing mutable variables in your model since mutable variables are currently not...

> For those who following this repo, strongly suggest to stick with the tensorflow2.3.0rc0 version, you could find a docker image from [here](https://hub.docker.com/r/tensorflow/tensorflow/tags?page=1&name=2.3.0rc0) thanks. I installed again tensorflow and seems...

> > did anyone solve this issue? my int8 converted model does not work with the script, > > ``` > > python detect.py --weights ./checkpoints/yolov4-tiny-416-int8.tflite --size 416 --model yolov4...

Hello, I have tried to run the int8 model on the raspberry pi4. I got this error : `RuntimeError: Select TensorFlow op(s), included in the given model, is(are) not supported...

> thanks, it works in my raspi 4, but why the int 8 model run slower than fp16 or 32?? I still not using any accelerator, full cpu. for int8...

> @NickPerezCarletonUniversity @partus over on the Pangolin side the maintainer recommended that for ORB we use tag v0.6. This worked well for me. I've edited the dockerfile above, it builds...

@jahaniam thanks man ! it works.

got the same error with a raspberry pi: `Linux raspberrypi 5.15.32-v7l+ #1538 SMP Thu Mar 31 19:39:41 BST 2022 armv7l GNU/Linux` I was following the coral guide

> I think a quick way around this is to install the dependencies directly and then install picamera2 with the `--no-deps` pip flag. This is working for me (RPi4, raspberry...

yeah, same for my situation. The model output is a mess at some frames. The situation I'm doing it for involves a small object rotating, and a constant scene. Here...