- E Catch exception when building RKNN model!
- T Traceback (most recent call last):
- T File "rknn/api/rknn_base.py", line 470, in rknn.api.rknn_base.RKNNBase.build
- T File "rknn/api/rknn_base.py", line 889, in rknn.api.rknn_base.RKNNBase._quantize
- T File "rknn/base/rknnlib/app/tensorzone/workspace.py", line 176, in rknn.base.rknnlib.app.tensorzone.workspace.Workspace.init_image_process
- T File "rknn/base/rknnlib/app/tensorzone/workspace.py", line 185, in rknn.base.rknnlib.app.tensorzone.workspace.Workspace.init_image_process
- T File "rknn/base/rknnlib/app/tensorzone/workspace.py", line 85, in rknn.base.rknnlib.app.tensorzone.workspace.proc_tensor
- T UnboundLocalError: local variable 'scale' referenced before assignment
复制代码
chuyee 发表于 2019-3-27 14:57
does npy in dataset.txt work?
engin 发表于 2019-3-27 17:48
已解决:rknn.config() 不传参数进行调用,量化可以正常。
多谢 raul chuyee
protossw512 发表于 2019-5-2 01:38
你好,请问你4通道输入之后输出的结果正确吗?
engin 发表于 2019-5-4 00:26
传入0~255的图像数据输出是正确的
protossw512 发表于 2019-5-4 08:55
谢谢了,我这边出了点问题,rgbd的数据rgb是-1~1, d是0~1,结果输出结果和用tf直接输出不一样,还在研究 ...
engin 发表于 2019-5-25 16:34
好久没看消息,你的方式成功了吗 -1~1的范围我们这边测试也是失败的,用的caffe模型 ...
欢迎光临 Toybrick (https://t.rock-chips.com/) | Powered by Discuz! X3.3 |