Object Detection toolkit based on PaddlePaddle. It supports object detection, instance segmentation, multiple object tracking and real-time multi-person keypoint detection.
Apache License 2.0
12.86k
stars
2.9k
forks
source link
树莓派上部署pphuman,转化模型时报错Error: This model is not supported, because 2 ops are not supported on 'arm'. These unsupported ops are: 'hard_sigmoid, swish'. #8176
[X] 我已经搜索过问题,但是没有找到解答。I have searched the question and found no related answer.
请提出你的问题 Please ask your question
您好,我准备在树莓派上部署pphuman,转化模型mot_ppyoloe_l_36e_pipeline时,代码为
import paddlelite.lite as lite
a=lite.Opt()
a.set_model_file("output_inference/mot_ppyoloe_l_36e_pipeline/model.pdmodel")
a.set_param_file("output_inference/mot_ppyoloe_l_36e_pipeline/model.pdiparams")
a.set_optimize_out("model_opt")
a.set_valid_places("arm")
a.run()
报错Error: This model is not supported, because 2 ops are not supported on 'arm'. These unsupported ops are: 'hard_sigmoid, swish'.
请问可以怎么解决呢?
问题确认 Search before asking
请提出你的问题 Please ask your question
您好,我准备在树莓派上部署pphuman,转化模型mot_ppyoloe_l_36e_pipeline时,代码为 import paddlelite.lite as lite a=lite.Opt() a.set_model_file("output_inference/mot_ppyoloe_l_36e_pipeline/model.pdmodel") a.set_param_file("output_inference/mot_ppyoloe_l_36e_pipeline/model.pdiparams") a.set_optimize_out("model_opt") a.set_valid_places("arm")
a.run() 报错Error: This model is not supported, because 2 ops are not supported on 'arm'. These unsupported ops are: 'hard_sigmoid, swish'. 请问可以怎么解决呢?