Comments (6)
I want to build my own dataset's window file, when I run the matlab scripts,an error thrown, shown below:
`Error using VOCxml2struct>gettag (line 73)
expected tag
Error in VOCxml2struct>parse (line 20)
[tag,ind]=gettag(xml,ind);
Error in VOCxml2struct>parse (line 24)
[sub,ind]=parse(xml,ind,tag);
Error in VOCxml2struct (line 5)
[res,xml]=parse(xml,1,[]);
Error in VOCreadxml (line 10)
rec=VOCxml2struct(xml);
Error in VOCreadrecxml (line 3)
x=VOCreadxml(path);
Error in PASreadrecord (line 10)
rec=VOCreadrecxml(path);
Error in voc_window_file (line 40)
R=PASreadrecord(f); object=R.objects;`
I have tried the scripts on the real VOC2007 dataset, it went well. Maybe there are some format differences between my datasets and real VOC2007.
from cascade-rcnn.
Why didn't it work? As long as you set up VOC dataset and VOCdevkit correctly, it should be working. They are all standard setting. If you just want to work on VOC, you can simply use the window files I provide. If you want to work on your own dataset, you may need to generate your own window files having the same structure.
from cascade-rcnn.
@zhaoweicai I find my problem and solve it! Thank you very much!(^▽^)
from cascade-rcnn.
need python scripts =。=
from cascade-rcnn.
python scripts by myself, please don't laugh at my pool code =. =
https://github.com/moyans/My_TOOLS/blob/master/cascade_tools/voc_window_file.py
from cascade-rcnn.
@jjprincess when I run the matlab scripts,an error thrown the same sa yours, can you tell me how to solve it thanks very much~
from cascade-rcnn.
Related Issues (20)
- have you try stage with IoU thr = 0.8 HOT 1
- Decodebbox layer
- cascade rcnn真的增加了正样本的数量吗 HOT 1
- Where can I find a information about stage weight in the original paper? HOT 1
- hello HOT 1
- rpn foreground accuracy is always 0 HOT 3
- Any Dockerfile?
- inference process HOT 1
- Check failed: error == cudaSuccess (8 vs. 0) invalid device function
- Message type "caffe.LayerParameter" has no field named "box_group_output_param". HOT 2
- model size HOT 1
- problem when compile the code.
- how to test one img with c++
- Where is your cascade loss function?
- trianing res101-15s-800-fpn-cascade problem·
- How much memory of GPU is needed for inference?
- bbox_std value in different stages
- When do the test inference, does the model hold the proposals from all the three stage output,or just take the output from the last stage headers?
- loss不下降 HOT 4
- how to download pretrained model ?
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 cascade-rcnn.