|
本帖最后由 ryanzx 于 2020-5-7 14:25 编辑
请问,3399PRO 在量化人脸识别模型时采用asymmetric-u8以及dynamic-u8量化方式时精度下降非常多有什么办法解决??同时采用dynamic-u16位量化后加载模型就报错的原因是什么??
报错的信息内容如下:
--> Init runtime environment
I NPUTransfer: Starting NPU Transfer Client, Transfer version 1.9.8 (cab3961@2019-12-12T09:54:26)
E RKNNAPI: rknn_init, msg_load_ack fail, ack = 1(ACK_FAIL), expect 0(ACK_SUCC)!
E RKNNAPI: ==============================================
E RKNNAPI: RKNN VERSION:
E RKNNAPI: API: 1.3.0 (c5654ea build: 2019-12-25 12:40:55)
E RKNNAPI: DRV: 1.3.1 (6ebb4d7 build: 2020-01-02 09:37:58)
E RKNNAPI: ==============================================
E Catch exception when init runtime!
E Traceback (most recent call last):
E File "rknn/api/rknn_base.py", line 988, in rknn.api.rknn_base.RKNNBase.init_runtime
E File "rknn/api/rknn_runtime.py", line 320, in rknn.api.rknn_runtime.RKNNRuntime.build_graph
E Exception: RKNN init failed. error code: RKNN_ERR_MODEL_INVALID
Init runtime environment failed
|
|