QNN model and TFLite model are converted from small scale Depth-Anything ONNX model depth_anything_vits14.onnx.
Prapare qnn-net-run env as in Qualcomm doc. This part is tested under ubuntu20.4, python==3.8, qnn==2.20.0.240223.
Run:
cd qnn_python
python infer.py
Prapare tensorflow, onnx2tf pip package. This part is tested under python==3.10.14, onnx==1.16.1, tensorflow==2.17.0 and onnx2tf==1.25.8. ref:
pip install -U onnx==1.16.1 && pip install -U nvidia-pyindex && pip install -U onnx-graphsurgeon && pip install -U onnxruntime==1.18.1 && pip install -U onnxsim==0.4.33 && pip install -U simple_onnx_processing_tools && pip install -U sne4onnx>=1.0.13 && pip install -U sng4onnx>=1.0.4 && pip install -U tensorflow==2.17.0 && pip install -U protobuf==3.20.3 && pip install -U onnx2tf && pip install -U h5py==3.11.0 && pip install -U psutil==5.9.5 && pip install -U ml_dtypes==0.3.2 && pip install -U tf-keras~=2.16 && pip install flatbuffers>=23.5.26
Run:
cd tflite
python infer.py
https://github.com/fabio-sim/Depth-Anything-ONNX