Hello everyone.
Recently I've been working on conversion from onnx to quantized dlc.
But I had some problem during this command. snpe-dlc-quantize
This is error message
Command Line Error: Invalid argument passed --input_dlc.
Appreciate on any help
Thanks
Opinions expressed in the content posted here are the personal opinions of the original authors, and do not necessarily reflect those of Qualcomm Incorporated or its subsidiaries (“Qualcomm”). The content is provided for informational purposes only and is not meant to be an endorsement or representation by Qualcomm or any other party. This site may also provide links or references to non-Qualcomm sites and resources. Qualcomm makes no representations, warranties, or other commitments whatsoever about any non-Qualcomm sites or third-party resources that may be referenced, accessible from, or linked to this site.
Dear developer,
Could you please share the commands you used to us? This will help us to assist you better.
Br.
Yunxiang
I have the same issue with snpe-2.10.0.4541. CMD:
snpe-dlc-quantize --input_dlc=ADAROUND_QUANTSIM.onnx.dlc --input_list=/snpe_quant_data/quant_input.txt --log-file ADAROUND_QUANTSIM.onnx.quant8bit.run --output_dlc=ADAROUND_QUANTSIM.onnx.quant8bit.dlc --override_params=runs/train/yolov7-tiny-neat_384_2/weights/quantsim/ADAROUND_QUANTSIM.encodings' [INFO] Setting ONNX_HOME=/usr/local/lib/python3.6/dist-packages [WARNING] Can't find ANDROID_NDK_ROOT or ndk-build. SNPE needs android ndk to build the NativeCppExample Command Line Error: Invalid argument passed --input_dlc=ADAROUND_QUANTSIM.onnx.dlc. Command Line Options: [ -h, --help ] Displays this help message.
I can confirm that snpe-1.68.0.3932 and older has worked fine.
Please advice.
The same for v2.9. In fact it is a general issue with reading in argument. I am runnign in a docker container. Let me know if you need my Docker file.
This is most likely because of wrong arguments in my command.
I can confirm that snpe-1.68.0.3932 and older has worked fine.