ambirpatel / Object-Localization-using-Deep-Reinforcement-Learning Public

Notifications You must be signed in to change notification settings
Fork 1
Star 8

We have trained an intelligent agent that draws bounding boxes around an object in the image. This implementation combines CNN, DQN, and SVM to detect an object in an image. The algorithm extract features from CNN which are fed to DQN to train an agent to localize the object and this localized object is categorized using the SVM model.

8 stars 1 fork Branches Tags Activity

Notifications

Name		Name	Last commit message	Last commit date
Latest commit History 39 Commits
figs		figs
README.md		README.md
config.py		config.py
extract_data.py		extract_data.py
q_learning.py		q_learning.py
requirements.txt		requirements.txt
svm_pred.py		svm_pred.py
utils.py		utils.py

Repository files navigation

Object-Localization-using-Deep-Reinforcement-Learning

About

We have trained an intelligent agent that draws bounding boxes around an object in the image. This implementation combines CNN, DQN, and SVM to detect an object in an image. The algorithm extract features from CNN which are fed to DQN to train an agent to localize the object and this localized object is categorized using the SVM model.

deep-reinforcement-learning dqn

Report repository

Releases

No releases published

Packages

No packages published

Contributors 2

Languages

Python 100.0%