immich/machine-learning/ann/build.sh
Fynn Petersen-Frey 753292956e
feat(ml): ARMNN acceleration (#5667)
* feat(ml): ARMNN acceleration for CLIP

* wrap ANN as ONNX-Session

* strict typing

* normalize ARMNN CLIP embedding

* mutex to handle concurrent execution

* make inputs contiguous

* fine-grained locking; concurrent network execution

---------

Co-authored-by: mertalev <101130780+mertalev@users.noreply.github.com>
2024-01-11 18:26:46 +01:00

2 lines
164 B
Bash

g++ -shared -O3 -o libann.so -fuse-ld=gold -std=c++17 -I$ARMNN_PATH/include -larmnn -larmnnDeserializer -larmnnTfLiteParser -larmnnOnnxParser -L$ARMNN_PATH ann.cpp