yun-liu / bing Goto Github PK
View Code? Open in Web Editor NEWBING: Binarized Normed Gradients for Objectness Estimation at 300fps
License: Other
BING: Binarized Normed Gradients for Objectness Estimation at 300fps
License: Other
Hi @yun-liu thank you for your great contribution, I could run the program successfully, but the results(same with the results from baiduyun) contain many rectangles for a single image:
1956
-0.35554, 1, 1, 353, 500
-0.373066, 1, 257, 353, 500
-0.403119, 1, 33, 353, 288
-0.404356, 97, 1, 352, 500
-0.450455, 1, 161, 353, 416
-0.545393, 33, 257, 288, 500
-0.595107, 65, 1, 320, 256
-0.595382, 97, 161, 352, 416
-0.606441, 1, 1, 256, 500
-0.733434, 1, 161, 256, 416
-0.834451, 161, 1, 288, 256
-0.837465, 49, 225, 176, 480
-0.849703, 113, 161, 240, 416
.........................................................
my question is:
1.what is the meaning of the float value, for example -0.35554 before the 1, 1, 353, 500
2.which rectangle is the ideal one for objects in this image, it is obvious that there are not so much objects in a single image.
thank you
Hey, I saw the codes only implement DATAVOC class, could I train the model using COCO dataset? Have you tried that, if so, is it as good as in VOC-07.
I have successfully installed opencv3 and extracted the data following the instructions, but got these error(I ran successfully for another opencv project removeRedEyes.cpp):
Load annotations finished
Dataset:'../VOC2007/' with 2501 training and 4952 testing
WinRecall.m Base = 2, W = 8, NSS = 2, perSz = 130
OpenCV Error: Assertion failed (0 <= roi.x && 0 <= roi.width && roi.x + roi.width <= m.cols && 0 <= roi.y && 0 <= roi.height && roi.y + roi.height <= m.rows) in Mat, file /build/opencv-zcaJjh/opencv-3.2.0+dfsg/modules/core/src/matrix.cpp, line 522
OpenCV Error: Assertion failed (0 <= roi.x && 0 <= roi.width && roi.x + roi.width <= m.cols && 0 <= roi.y && 0 <= roi.height && roi.y + roi.height <= m.rows) in Mat, file /build/opencv-zcaJjh/opencv-3.2.0+dfsg/modules/core/src/matrix.cpp, line 522
OpenCV Error: Assertion failed (0 <= roi.x && 0 <= roi.width && roi.x + roi.width <= m.cols && 0 <= roi.y && 0 <= roi.height && roi.y + roi.height <= m.rows) in Mat, file /build/opencv-zcaJjh/opencv-3.2.0+dfsg/modules/core/src/matrix.cpp, line 522
OpenCV Error: Assertion failed (0 <= roi.x && 0 <= roi.width && roi.x + roi.width <= m.cols && 0 <= roi.y && 0 <= roi.height && roi.y + roi.height <= m.rows) in Mat, file /build/opencv-zcaJjh/opencv-3.2.0+dfsg/modules/core/src/matrix.cpp, line 522
terminate called after throwing an instance of 'terminate called after throwing an instance of 'cv::Exception'
terminate called recursively
cv::Exception'
terminate called recursively
Aborted (core dumped)
Could you please tell me what is wrong?
Thanks!
@yun-liu
hi,when i run i got a runtime exception
Load annotations finished
Dataset:'/Users/ziyan/VOCdevkit/VOC2007/' with 1 training and 1 testing
WinRecall.m Base = 2, W = 8, NSS = 2, perSz = 130
Learning stage I takes 0.067738 seconds...
OpenCV Error: Assertion failed (d == 2 && (sizes[0] == 1 || sizes[1] == 1 || sizes[0]*sizes[1] == 0)) in create, file /tmp/opencv-20170825-90583-1pdhamg/opencv-3.3.0/modules/core/src/matrix.cpp, line 2581
libc++abi.dylib: terminating with uncaught exception of type cv::Exception: /tmp/opencv-20170825-90583-1pdhamg/opencv-3.3.0/modules/core/src/matrix.cpp:2581: error: (-215) d == 2 && (sizes[0] == 1 || sizes[1] == 1 || sizes[0]*sizes[1] == 0) in function create
A declarative, efficient, and flexible JavaScript library for building user interfaces.
🖖 Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.
TypeScript is a superset of JavaScript that compiles to clean JavaScript output.
An Open Source Machine Learning Framework for Everyone
The Web framework for perfectionists with deadlines.
A PHP framework for web artisans
Bring data to life with SVG, Canvas and HTML. 📊📈🎉
JavaScript (JS) is a lightweight interpreted programming language with first-class functions.
Some thing interesting about web. New door for the world.
A server is a program made to process requests and deliver data to clients.
Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.
Some thing interesting about visualization, use data art
Some thing interesting about game, make everyone happy.
We are working to build community through open source technology. NB: members must have two-factor auth.
Open source projects and samples from Microsoft.
Google ❤️ Open Source for everyone.
Alibaba Open Source for everyone
Data-Driven Documents codes.
China tencent open source team.