MiniBullLab/easy_ai

classnet,denet,segnet网络输入输出层名固定

Closed this issue · 6 comments

  • 1.classnet,denet,segnet onnx网络输出层名固定
  • 2.修改下位机代码,与下位机联调(另建Issue处理)

层名已经固定,代码修改完成

task 输入层名称 输出层名称
classnet cls_input cls_output
DeNet det_input det_output0,det_output1,det_output2
segnet seg_input seg_output

classnet

classnet在easy_tools下进行训练,得到的onnx网络通过网页显示,发现输入层名称为cls_input,输出层名称为cls_output。

转换结果可以得到classnet.bin文件,但是后面的inference还需要进一步测试。
注意的是,在转换过程中打印一些warning:

perl: warning: Setting locale failed.
perl: warning: Please check that your locale settings:
	LANGUAGE = (unset),
	LC_ALL = (unset),
	LANG = "C.utf8"
    are supported and installed on your system.
perl: warning: Falling back to the standard locale ("C").

@lpj0822

segnet

segnet在easy_tools下进行训练,得到的onnx网络通过网页显示,发现输入层名称为seg_input,输出层名称为seg_output。

转换结果可以得到segnet.bin文件,但是后面的inference还需要进一步测试。

warning目前先忽略

转换的shell脚本需要修改,1. log的路径需要修改 2. outputLayerName="o: 后面的输出层名称需要修改。

denet


degnet在easy_tools下进行训练,得到的prototxt的输入层名称为data,输出层分别为det_output0,det_output1,det_output2。
denet转换出错,错误如下:

Traceback (most recent call last):
  File "/usr/local/amba-cv-tools-2.1.7-20190815.ubuntu-18.04/cv2/tv2/release/AmbaCnnUtils/cv2.1.7.408/parser/caffe/caffeparser.py", line 29, in <module>
    import io_nodes
  File "/usr/local/amba-cv-tools-2.1.7-20190815.ubuntu-18.04/cv2/tv2/release/AmbaCnnUtils/cv2.1.7.408/parser/caffe/io_nodes.py", line 26, in <module>
    import caffe_common as cfc
  File "/usr/local/amba-cv-tools-2.1.7-20190815.ubuntu-18.04/cv2/tv2/release/AmbaCnnUtils/cv2.1.7.408/parser/caffe/caffe_common.py", line 23, in <module>
    from caffe import Net
  File "/opt/caffe/python/caffe/__init__.py", line 1, in <module>
    from .pycaffe import Net, SGDSolver, NesterovSolver, AdaGradSolver, RMSPropSolver, AdaDeltaSolver, AdamSolver, NCCL, Timer
  File "/opt/caffe/python/caffe/pycaffe.py", line 13, in <module>
    from ._caffe import Net, SGDSolver, NesterovSolver, AdaGradSolver, \
ImportError: libglog.so.0.3.5: cannot open shared object file: No such file or directory

@lpj0822

该问题在easy_ai代码中已经修改

已经测试成功并获得denet.bin。