Comments (3)
Thank you for kind words!
While I did not make tests to study this problem, theoretically because of the way how YOLO detection works you do not need any images without the object to train good model - all the pictures can contain object and it will train well.
YOLO v2 has a number of outputs for each box in the grid cell:
- parameters for the boundary box (x,y, w, h)
- box confidence score (objectness)
- class probabilities
When training it learns to make box confidence score low for the boxes in grid that DO NOT contain objects. For example
In this picture there will still be prediction made for grid cells that have tree and floor in the center, but their box confidence scores will be very low.
So, the model learns still learns the negative examples from these pictures, even despite one instance of the object is present.
from axelerate.
Oh and as a side note - INRIA nowadays can be considered "a toy dataset' for pedestrian detection. The number of positive samples is quite few (for modern days standards) and there are some instances where not all people present in the image are annotated - you can see it if you browse through dataset with labeling tool. Which worsens the performance of the model (prediction made on a person NOT included annotation, but present in the image considered to be false positive and will be penalized by loss function).
I did want to make BetterINRIA dataset, with all people annotated and more images added from PASCAL-VOC, but sadly no time for this now.
from axelerate.
Thank you very much for the explanation.
I also tought that no images without person were needed but as the performances didn't improve like with your dataset did, I had this doubt because I saw that you have provided some images without the person.
For the dataset, I'm working on it, if I get good result maybe I can give it to you.
Thank you again, I'll close the issue!
from axelerate.
Related Issues (20)
- 是否支持把没有目标的空背景和标签输入训练? HOT 2
- Does training with negative samples(pictures without objects of interest) increase accuracy? HOT 6
- Can the aXeleRate support the format? HOT 1
- k210 segnet HOT 1
- json.decoder.JSONDecodeError: Expecting ',' delimiter: line 35 column 2 (char 1325) HOT 5
- Run in Sipeed Maix Bit HOT 6
- Cannot convert tf to onnx in object detection HOT 2
- Training person detector with pascal_20_detection dataset error HOT 9
- tensorflow 2.5 error! HOT 1
- Support for custom input_size no work in kmodel HOT 4
- [unstable branch] validation frequency adding to config.json HOT 1
- [unstable branch] yolo training quantize or not can be switched by config.json HOT 1
- [unstable branch] yolo k210 converter failed while nncase compile and YOLOv3 convert incorrectly HOT 1
- Threads Error HOT 1
- The loss is not converge when training detector on VOC 2012 HOT 2
- When class names more than one, the mAP is false? HOT 5
- How calculate anchors by kmeans? HOT 2
- Multi Object Detect Is Wrong! HOT 2
- Loading kmodel on MaixPy crashing device HOT 25
- ValueError: Invalid value for argument filters. Expected a strictly positive value. Received filters=0. HOT 2
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 axelerate.