RKNN ML smart search error
Hi everyone，I'm currently using Rk3588 board and encountered some problem on clip features.
After all ml settings are finished. the utilization of NPU is above 0 while doing facing recognition and smart searching processes .
but when I try to use text searching feature , it will showing up immich server error.
here is the immch-machine-learning log
I know that this is because RKNN library miss some operation , but any suggestions on alternative way rather than using cpu?
I RKNN: [03:21:34.838] RKNN Driver Information, version: 0.9.8
I RKNN: [03:21:34.841] RKNN Model Information, version: 6, toolkit version: 2.3.0(compiler version: 2.3.0 (c949ad889d@2024-11-07T11:39:30)), target: RKNPU v2, target platform: rk3588, framework name: ONNX, framework layout: NCHW, model inference type: static_shape
E RKNN: [03:21:35.835] Unsupport CPU op: CumSum in this librknnrt.so
W RKNN: [03:21:35.836] query RKNN_QUERY_INPUT_DYNAMIC_RANGE error, rknn model is static shape type, please export rknn with dynamic_shapes
[03/31/25 03:21:39] I Loaded RKNN model from
/cache/clip/XLM-Roberta-Large-ViT-H-14__frozen_laio
n5b_s13b_b90k/textual/rknpu/rk3588/model.rknn with
3 threads.
[03/31/25 03:22:07] ERROR Worker (pid:10) was sent code 139!
After all ml settings are finished. the utilization of NPU is above 0 while doing facing recognition and smart searching processes .
but when I try to use text searching feature , it will showing up immich server error.
here is the immch-machine-learning log
I know that this is because RKNN library miss some operation , but any suggestions on alternative way rather than using cpu?
I RKNN: [03:21:34.838] RKNN Driver Information, version: 0.9.8
I RKNN: [03:21:34.841] RKNN Model Information, version: 6, toolkit version: 2.3.0(compiler version: 2.3.0 (c949ad889d@2024-11-07T11:39:30)), target: RKNPU v2, target platform: rk3588, framework name: ONNX, framework layout: NCHW, model inference type: static_shape
E RKNN: [03:21:35.835] Unsupport CPU op: CumSum in this librknnrt.so
W RKNN: [03:21:35.836] query RKNN_QUERY_INPUT_DYNAMIC_RANGE error, rknn model is static shape type, please export rknn with dynamic_shapes
[03/31/25 03:21:39] I Loaded RKNN model from
/cache/clip/XLM-Roberta-Large-ViT-H-14__frozen_laio
n5b_s13b_b90k/textual/rknpu/rk3588/model.rknn with
3 threads.
[03/31/25 03:22:07] ERROR Worker (pid:10) was sent code 139!
