Comments (8)
Q1: Yes.
2: Whether to use 1000 most frequent categories is up to you. Maybe using all 3850 categories will perform better? 😄
3: Whether to use thresh > 0.005 and whether to divide into 12 splits are up to you.
Q2: Yes. (If you are wondering center-x center-y
---- because darknet YOLOv2 did this.)
4: You don't have ground truth of testset. If you test on testset, you cannot run python3 detection_perf.py
, but you can upload the results to evaluation server.
from ctw-baseline.
Thanks for your reply ! :)
I just use val set as test set, train+val set as train set.
And when I run cd ../judge && python3 detection_perf.py
, I got this ...
...... and finally an ERROR:
This really confused me ......
from ctw-baseline.
fixed in f9c70fc .
from ctw-baseline.
Thanks for your code again. :)
And Can you tell me how long( or how many max_batches) and the number of gpus did you train yolov2 with CTW in origin paper ? If that's okay with you...
Thanks.
from ctw-baseline.
NVIDIA GTX TITAN X (PASCAL) * 1, 3.0 sec/step, 38 hours in total.
from ctw-baseline.
@yuantailing Hi,
I'm confused by this two passages in Appendix of tutorial Part 3:
Q1: How to choose c0
? Why sometimes nums(TPs) + nums(FNs) > nums(GTs)
? (Why nums(GT matched with detected box) + nums(GT unmatched with detected box) != nums(GTs)? )
Q2: How to compute AP? Does it means when c0 is given, all boxes with score < c0
will be filtered out, then many recall 0, recall 1, ..., recall n
are given, and the AP is the mean value of max precisions under each recall ?
Like this :
from ctw-baseline.
Q1. Sorry, I made a mistake. It should be ''we take a minimum confidence score
To compute the recall rates, for each image in the testing set, denoting the number of annotated character instances as n, we select n recognized character instances with the highest confidences as output of YOLOv2.
The mistake is fixed in ff97954.
Q2. Yes, and I think it's the equivalent to the AP in PASCAL VOC. For every real number c0, we can compute a recall (The `recall' is not recall metric mentioned in the paper) and a precision. So, there are (M + 1) kinds of c0 levels to compute (M + 1) recalls and (M + 1) precisions.
We use max precisions where (r' > r) to compute AP, it's also the same.
ctw-baseline/cppapi/eval_tools.hpp
Lines 145 to 146 in ff97954
from ctw-baseline.
Thanks for your patience and quick reply. :)
from ctw-baseline.
Related Issues (20)
- Some question about test in detection HOT 1
- Error on CodaLab (CTW dataset classification) HOT 2
- Dataset weiyun download link failed. HOT 4
- Question when running detection_perf.py HOT 3
- restore the weight of Inception_v4 HOT 6
- 检测的时候怎么提取一行字符或者一列的区域 yolo例子下面那个只能提取单个字符的区域 HOT 5
- Where can I locate the 'learning' module? HOT 2
- Very slow training speed. Is this expected for my system setup? HOT 4
- How to deal with negative values in the coordinates of polygon regions HOT 1
- images-test miss some images HOT 2
- 使用yolov3算法需要在哪些方面做出调整呢 HOT 4
- 您好,请问在训练和测试的时候裁剪图片是如何裁剪的? HOT 1
- 有人有训练好的模型吗
- 如何将jsonl格式的注释转换为txt格式?
- Aspect ratio of the anchor boxes HOT 2
- 请问您在原始yolov2基础上修改了哪些东西,如果换成Yolov3该怎么去修改呢 HOT 1
- 如何获取行文本图像和标签? HOT 2
- Problem when reproducing the classification performance HOT 2
- Problem of CodaLab HOT 1
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 ctw-baseline.