You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
However, I'd love to get a yolox version working with that android project.
I can see that they modify the shape of the output when converting to tflite.
I'm quite new to this so I'm struggling figure it out.
I noticed using ultralytics the output shape is converted to float32[1,61,8400]
My yolox onnx model shows [1,8400,62]
Even an example of how to run inference on a tflite file made from yolox in python would be very useful as I haven't managed to get that working either, but inference on the onnx model works following the example in yolox
reacted with thumbs up emoji reacted with thumbs down emoji reacted with laugh emoji reacted with hooray emoji reacted with confused emoji reacted with heart emoji reacted with rocket emoji reacted with eyes emoji
-
I'm trying to convert my yolox model to tflite, but having some difficulty.
I had been using ultralytics for this with yolov8 and their conversion to tflite works for me and I can use it in this sample android project:
https://github.com/AarohiSingla/Object-Detection-Android-App
However, I'd love to get a yolox version working with that android project.
I can see that they modify the shape of the output when converting to tflite.
I'm quite new to this so I'm struggling figure it out.
I noticed using ultralytics the output shape is converted to float32[1,61,8400]
My yolox onnx model shows [1,8400,62]
Even an example of how to run inference on a tflite file made from yolox in python would be very useful as I haven't managed to get that working either, but inference on the onnx model works following the example in yolox
Beta Was this translation helpful? Give feedback.
All reactions