- --> Loading model
- W Warning: Axis may need to be adjusted according to original model shape.
- W Warning: Axis may need to be adjusted according to original model shape.
- W Unhandle status: the input shape of reshape layer mbox_conf_reshape_116 is not 4-D
- done
- --> Building model
- W Warning: Axis may need to be adjusted according to original model shape.
- W Warning: Axis may need to be adjusted according to original model shape.
- W Unhandle status: the input shape of reshape layer mbox_conf_reshape_116 is not 4-D
- done
- --> Init runtime environment
- W [RK_nn_softmax_compute:45]Softmax's beta is 0. Set beta to 1
- done
- --> Running model
- done
复制代码
Devin 发表于 2020-2-26 18:23
1. 模型转换是在PC的Ubuntu虚拟机上做的,rknn-toolkit的版本是1.2.0;
2. rknn-api的版本为1.2.0,driver驱 ...
Devin 发表于 2020-2-26 18:23
1. 模型转换是在PC的Ubuntu虚拟机上做的,rknn-toolkit的版本是1.2.0;
2. rknn-api的版本为1.2.0,driver驱 ...
troy 发表于 2020-2-27 14:59
关于第三点,你说的rknn_test::load_model中new的变量没有释放,你是指output_size吗?如果是,在load_mo ...
Devin 发表于 2020-2-27 17:19
谢谢版主。前面已经有释放了,那里确实不用。您指的是load_model里的output_size[0]和output_size[1]的大 ...
troy 发表于 2020-2-28 08:53
1.确定caffemodel实际的输出形状,你可以用https://lutzroeder.github.io/netron/加载caffe模型,查看你 ...
欢迎光临 Toybrick (https://t.rock-chips.com/) | Powered by Discuz! X3.3 |