Comments (10)
I am very glad to communicate with you. Thank you for your answer .
from csp.
You can use the toolbox from Caltech.
If you run dbBrowser.m with modification of directory, you can get images with annotations.
from csp.
use test_caltech.py and add cv2.rectangle to write the bounding boxes on the image when get the boxes
from csp.
您可以使用加州理工学院的工具箱。
如果在修改目录的情况下运行dbBrowser.m,则可以获得带批注的图像。
You can use the toolbox from Caltech.
If you run dbBrowser.m with modification of directory, you can get images with annotations.
Can you elaborate on that? How to modify the directory? thanks
from csp.
您可以使用加州理工学院的工具箱。
如果在修改目录的情况下运行dbBrowser.m,则可以获得带批注的图像。You can use the toolbox from Caltech.
If you run dbBrowser.m with modification of directory, you can get images with annotations.Can you elaborate on that? How to modify the directory? thanks
Yes, I elaborated on it.
I did like below. I used Kaist dataset rather than caltech.
[pth,sIds,vIds,skip] = dbInfo; % '/home/eungyo/CSP/eval_caltech/data-USA'
pth2 = '/home/eungyo/CSP/output/valresults/kaist/h/off';
% 0 ... 6 7 8 9 10 11 > sIds. set skip =20
%rPth=[pth '/res/ChnFtrs']; % directory containing results
%rPth=[pth '/res/082+city+0.1+VI+512'];
rPth = [pth2 '/082+city+0.1+LWIR+e117'];
from csp.
Thank you very much for your enthusiastic answer,it is good for me. For caltech,we only have one ground truth file named gt-Reasonable.mat. (1)Do you only get one MR for reasonable? Do we need to submit detector results to Piotr Dollár?(2)Another question,where are you setting iou=0.75?
I sincerely hope that receive your answer,extremely grateful!
from csp.
Thank you very much for your enthusiastic answer,it is good for me. For caltech,we only have one ground truth file named gt-Reasonable.mat. (1)Do you only get one MR for reasonable? Do we need to submit detector results to Piotr Dollár?(2)Another question,where are you setting iou=0.75?
I sincerely hope that receive your answer,extremely grateful!
(1) That is the problem. I think there will be codes for generating gt file. I had plans for generating other gts, but nowadays I am not working on pedestrian detection due to my professor. Thus, I have no ideas sorry. In the paper, the author used other gts, such as occluded, so there must be a way. (2) I think it was vbb if I remember correctly.
from csp.
非常感谢您的热情回答,对我有好处。对于Caltech,我们只有一个名为gt-Reasonable.mat的地面真实文件。(1)您只得到一份合理的MR吗?我们是否需要将检测器结果提交给PiotrDollár?(2)另一个问题,您将iou = 0.75设置在哪里?
我衷心希望收到您的答复,万分感谢!(1)这就是问题所在。我认为会有用于生成gt文件的代码。我曾计划生成其他GTS,但是由于我的教授,如今我不从事行人检测。因此,对不起我没有想法。在本文中,作者使用了其他gts(例如遮挡),因此必须有一种方法。(2)如果我没记错的话,我认为是vbb。
hello,I can't find the place to set the iou=0.5/0.75,can you describe it in detail?thank you.
from csp.
Hello, I'm also trying to visualize the results for test_caltech. However, I do not understand the Information in the .txt files, and the author didn't explain. Do you know what the contents mean? Thannks~
from csp.
use test_caltech.py and add cv2.rectangle to write the bounding boxes on the image when get the boxes
hello,i have write the code which can draw bb on the image ,i follow the .txt file that got in result(output/valresutlts/caltech/h/off),but I find there are too many bounding boxes, which is not right ,can you tell me where you get the right bounding boxes' data?
from csp.
Related Issues (20)
- The losses value from train_Caltech are higher than authors
- I have data and need to test my data with this pre-trained model
- An exception occurs when running train_caltech
- Exception cycle HOT 3
- No module named 'nms_wrapper' HOT 1
- windows user how to test caltech? HOT 2
- Is nms postprocess necessary?
- How to run test_wider_ms.py with multiple GPUs
- Python version of dt_txt2json HOT 2
- How to generate the cache file of test subset in wider face?
- Share the code of how to execute the multi-scale training for the citypersons dataset?
- Classification loss - binary_crossentropy (possibly wrong parameters order) HOT 1
- batchsize 16 on one 2080ti cause OOM exception
- it shows me that Dimensions is not equal HOT 2
- where val dataset? i just see the train
- how to run this github
- Does anyone reproduce the caltech result using author's weight?
- how can I get the image with the bounding boxes like this HOT 2
- why the classification is a binary classification? in the cityperson dataset , it have 6 class pedestrian ?
- ImportError: Building module keras_csp.nms.gpu_nms failed: ["distutils.errors.CompileError: command 'gcc' failed with exit status 1\n"]
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 csp.