-
-
Notifications
You must be signed in to change notification settings - Fork 347
New issue
Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.
By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.
Already on GitHub? Sign in to your account
[Project Addition] Terrain Recognition #636
Comments
Thank you for creating this issue! We'll look into it as soon as possible. Your contributions are highly appreciated! 😊 |
Assigned @MohanRocks999 |
@abhisheks008 how you assign the task ? i have to find the some short of problem then you assign me that task?? |
Check out the issues with Up for Grabs label and are being opened by me only. |
@abhisheks008 can i make a translator? which translate French to English? |
No dude. These full fledged deep learning projects. For discussion purposes, pleas use the Discord server or the Deep Learning Simplified thread in Project Intro section of the GSSoC server. |
Hello @MohanRocks999! Your issue #636 has been closed. Thank you for your contribution! |
Deep Learning Simplified Repository (Proposing new issue)
🔴 Project Title : Terrain Recognition
🔴 Aim : To create a DL Model based on Pytorch to recognize different types of terrains
🔴 Dataset : https://www.kaggle.com/datasets/arnaud58/landscape-pictures and custom dataset gathered using web scrapers
🔴 Approach : Using ViT (Vision Transformer), Yolov8 and EfficientNet as backbone to classify the type of terrain from the given image and evaluating their performance using a test dataset for choosing the best deep learning model for this particular scenario. The classification is straight foward with image dataset with label corresponding to their terrain class and using a "text class" label mapping during inference to return as output during inference. Also for the frontend i have plans to use either gradio or a custom react js based front-end for the demo app.
✅ To be Mentioned while taking the issue :
The text was updated successfully, but these errors were encountered: