I am trying to export a YOLOv10 model to tflite for use in the NPU of an NXP i.MX8M Plus device. I am unable to build the int8 quantized tflite file and I get the following warning: WARNING: This model contains GroupConvolution and is automatically optimized for TFLite, but is not output because sa…

--disable_group_convolution

Toxite October 24, 2024, 1:59pm 3

ultralytics uses onnx2tf to convert from ONNX to TF format. disable_group_convolution is enabled. Are you using the latest ultralytics ?

1 Like

Topic		Replies	Views
Quantization YOLO yolo	11	694	October 30, 2024
False positives after converting YOLOv8 to .tflite YOLO support	6	533	February 26, 2025
Slimming with onnxslim 0.1.50 fails with yolo export on Jetson 6.2 L4T Discussion yolo , troubleshooting , resource	4	56	April 26, 2025
New Release: Ultralytics v8.3.148 Discussion releases , announcements	0	11	June 3, 2025
New Release: Ultralytics v8.3.149 Discussion releases , announcements	0	11	June 4, 2025