@jeremyrbrown5 we figured it out, we just changed the name of the model to yolov8n_float16.tflite. Pretty spot on now!

@jeremyrbrown5 we figured it out, we just changed the name of the model to yolov8n_float16.tflite. Pretty spot on now!

@jeremyrbrown5 here is a link to our current model .tflite file

@Zachary-Lowell-0 Yes I have been using the guides linked on the modalai website

@Zachary-Lowell-0

stinger (D0013):/$ voxl-tflite0-server
bash: voxl-tflite0-server: command not found
stinger (D0013):/$ voxl-tflite-server

skip_n_frames: 5

model: /usr/bin/dnn/best_float16.tflite

input_pipe: /run/mpa/hires_misp_color/

delegate: gpu

allow_multiple: false

output_pipe_prefix: mobilenet

existing instance of voxl-tflite-server found, attempting to stop it
WARNING: Unknown model type provided! Defaulting post-process to object detection.
INFO: Created TensorFlow Lite delegate for GPU.

@Zachary-Lowell-0 we are using the yolo predict function inside the voxl-docker. I didn't know about voxl-inspect-detections, so I'll try that.

Hello

We are training a yolov8 model to recognize rasberry pis. We are able to create the .tflite, test it using the predict function with 100% detection and high certainty, and push it to the Voxl 2 mini. However, no matter how we configure the voxl-tflite-server, we can't see it replicated in the voxl portal.

Some notes about our setup

For training we are using 75 images. 50 are for training, 15 are for valid, and 10 are for test

Our model-train.yaml is set to 30 epochs, 5 batchs, and 2 workers

our custom labels.txt for the tflite server is just 0 RasPi

we have used both the tracking_front and the Hires_misp_color cameras, with no such luck.

Inside of the deep learning documentation there is a section about the initialize_model_settings function in the main file. We cannot find this function on the voxl 2 mini. If the steps under 'Implementing your model in voxl-tflite-server' and 'Writing the model class' are critical to our success, we would really appreciate the function/file locations for the voxl 2 mini.

Thank you

@Alex-Kushleyev Apologies for the delayed replied. We have mostly resolved our softap issues. I'm not sure which wifi adapter we are using, I believe its whatever comes in the developer kit. When we run into the error, rebooting the mini doesn't help, the only part that works is factory-resting. As for connection quality, its very much relying on the icons visual bars.

What we determined is that the more changes config files and the more services we have operating at once increases the chance that softap will just not work. Since we have been messing with custom yolov8 models, we have been moving and removing .txt and .tflite files from usr/bin/dnn, and if everything is even a little bit off, we have the issue. Now we are pretty ok though.

So, I guess its resolved, but in a very hand-wavy kind of way.

Hello

We are experiencing issues when connecting via wifi. We setup the voxl-wifi on 5ghz and it will work great for a while. Eventually, after a few days with minimal changes it will stop working. We can ifconfig wlan0 down and up again to get some signal, but it is very weak.

The things we have changed is all on the px4 side and the camera configs, so nothing with softap specifically other then setting it up.

We keep getting to the point where we factory reset the drone and then it works again for a few days. Any advice or assistance would be beneficial.

Thank you

@Robbie-McCue worked, thanks so much!

Hello

We having issues building the docker image. Attached is a picture of the errors we are encountering.

We have tried install the dependencies individually with little luck. Any assistance would be greatly appreciated

Thank you