yg-dickson

Results 12 comments of yg-dickson

YOLO11 conversion tflite int8 error ``` Traceback (most recent call last): File "/environment/miniconda3/lib/python3.11/site-packages/onnx2tf/onnx2tf.py", line 1566, in convert tflite_model = converter.convert() ^^^^^^^^^^^^^^^^^^^ File "/environment/miniconda3/lib/python3.11/site-packages/tensorflow/lite/python/lite.py", line 1231, in wrapper return self._convert_and_export_metrics(convert_func, *args,...

RuntimeError: Quantized dimension for tensor property and quantization parameters do not match. Got 3 and 0 respectively. WARNING: INT8 Quantization with int16 activations tflite output failed. W0000 00:00:1728366998.180039 182160 tf_tfl_flatbuffer_helpers.cc:390]...

Is it not integrated into the official version yet?

Is it applicable to yolo11?

I followed the tutorial above, yolo11 cannot convert rknn, yolov8 can convert rknn normally.

When will the official version be released?

Can I export rknn int8?

Hope to support rknn int8

Still under development?