深度学习文字识别 的 一系列bug

https://github.com/bear63/sceneReco

--------------------------测试----------------------

环境：anaconda+python2.7

 

No module named cv2

pip install opencv-python

 

No module named caffe

pip install caffe

 

No module named cpu_nms

cpu_nms改写成python文件

 

No module named torch

pip install torch

 

No module named torchvision.transforms

pip install torchvison

 

No module named lmdb

pip install lmdb

 

No module named mahotas

pip install mahotas

 

Xshell  unknown command yum、rz

协议：SSH

 

 

Net('/home/yang/sceneReco/CTPN/models/deploy.prototxt', 1, weights='/home/yang/sceneReco/CTPN/models/ctpn_trained_model.caffemodel')
[libprotobuf ERROR google/protobuf/text_format.cc:245] Error parsing text-format caffe.NetParameter: 387:19: Message type "caffe.LayerParameter" has no field named "transpose_param".
F0128 15:30:29.198107 2556 upgrade_proto.cpp:88] Check failed: ReadProtoFromTextFile(param_file, param) Failed to parse NetParameter file: /home/yang/sceneReco/CTPN/models/de