Comments (9)
@mahaling I think you may import other caffe instead of the one we ship. You can use print caffe
after import caffe
to see which caffe you're using. Thank you:-).
from ctpn.
@tianzhi0549 I met the same problem. Please help
from ctpn.
@ld909 Please make sure that you import the correct caffe. Thank you:-).
from ctpn.
@tianzhi0549 You are right. I just had to point the code to the right version of caffe and it worked!.
from ctpn.
@mahaling Already have Caffe installed, do I need to reinstall it with the modified version ??? because I have the same problem
from ctpn.
@mahaling @tianzhi0549 ,would you mind telling me how you set your caffe_root, I set my caffe_root ='/home/jsj/CTPN/caffe/python/caffe' ,and I got the follow error
"Connected to pydev debugger (build 171.4694.38)
WARNING: Logging before InitGoogleLogging() is written to STDERR
<module 'caffe' from '/home/jsj/caffe/python/caffe/init.pyc'>
W0626 13:30:38.482167 12282 _caffe.cpp:122] DEPRECATION WARNING - deprecated use of Python interface
W0626 13:30:38.482203 12282 _caffe.cpp:123] Use this instead (with the named "weights" parameter):
W0626 13:30:38.482208 12282 _caffe.cpp:125] Net('/home/jsj/CTPN/models/deploy.prototxt', 1, weights='/home/jsj/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".
F0626 13:30:38.484434 12282 upgrade_proto.cpp:88] Check failed: ReadProtoFromTextFile(param_file, param) Failed to parse NetParameter file: /home/jsj/CTPN/models/deploy.prototxt
*** Check failure stack trace: ***"
from ctpn.
@sabirdvd Yes you need to point the CAFFE_ROOT to the caffe version that comes along with this code.
@yingning You are doing it right. However, I set the CAFFE_ROOT inside my python code so that it uses that version of caffe. Your code is still referring to the other caffe version that you already have.
from ctpn.
i have the same quetion,and the result of command "print caffe" is <module 'caffe' from 'caffe/init.py'>
from ctpn.
i have the same quetion,and the result of command "print caffe" is <module 'caffe' from 'caffe/init.py'>
ummm, i compile the caffe with cuda8 and cudnn7
from ctpn.
Related Issues (20)
- cuda版本和cudnn版本问题 HOT 4
- Any other implemetation HOT 2
- please reveal details of training ,thanks? HOT 1
- Optimize Convolution layers with MobileNet HOT 2
- Which research paper is used to implement this? HOT 1
- How to generate training labels?
- demo link died HOT 1
- Bath size when training LSTM ? HOT 2
- dimention
- why the result use the author's model is lower the the artical.
- 项目很不友好,编译麻烦 HOT 1
- The text_recs returned has a problem HOT 2
- Can you share your dataset that mentioned in the article? HOT 1
- what is the dataset to get the trained model? HOT 4
- 运行问题 HOT 5
- Issue while running demo.py "Creating layer proposal" HOT 2
- Pytorch vision? HOT 3
- 你好,是否能提供预训练模型下载呢 HOT 1
- error:Check failed: registry.count(type) == 1 (0 vs. 1) Unknown layer type: Python (known types: AbsVal, Accuracy, ArgMax, BNLL, BatchNorm, Concat, ContrastiveLoss, Convolution, Crop, Data, HOT 2
- 请问能提供训练数据集吗
Recommend Projects
-
React
A declarative, efficient, and flexible JavaScript library for building user interfaces.
-
Vue.js
🖖 Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.
-
Typescript
TypeScript is a superset of JavaScript that compiles to clean JavaScript output.
-
TensorFlow
An Open Source Machine Learning Framework for Everyone
-
Django
The Web framework for perfectionists with deadlines.
-
Laravel
A PHP framework for web artisans
-
D3
Bring data to life with SVG, Canvas and HTML. 📊📈🎉
-
Recommend Topics
-
javascript
JavaScript (JS) is a lightweight interpreted programming language with first-class functions.
-
web
Some thing interesting about web. New door for the world.
-
server
A server is a program made to process requests and deliver data to clients.
-
Machine learning
Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.
-
Visualization
Some thing interesting about visualization, use data art
-
Game
Some thing interesting about game, make everyone happy.
Recommend Org
-
Facebook
We are working to build community through open source technology. NB: members must have two-factor auth.
-
Microsoft
Open source projects and samples from Microsoft.
-
Google
Google ❤️ Open Source for everyone.
-
Alibaba
Alibaba Open Source for everyone
-
D3
Data-Driven Documents codes.
-
Tencent
China tencent open source team.
from ctpn.