Open abhisheks008 opened 1 year ago
I would like to work on this, frankly I don't know much but I will learn and do. I am a newbie(first year UG student). I want to learn and grow. please give me the opportunity to learn and experience
Please do not to spam in every single issue. This might cause escalation as you are breaching Code of Conduct and Contribution Guidelines.
@rafiya2003
Full name : Om Achrekar GitHub Profile Link : achrekarom12 Email ID : achrekarom@gmail.com Approach for this Project : Although I have never practically implemented any video classification model but I am sure with the knowledge I've gained from my last contributions will surely help me in this. It would be great if you assign me this issue! What is your participant role? SSoC '23 Contributor
Issue assigned to you @achrekarom12
Hey @abhisheks008 , I wanted to reach out and inform you that unfortunately, I am unable to continue working on the current issue at hand. It has come to my attention that this particular project demands significant computational expenses. Even when attempting to preprocess just 10 videos simultaneously, it results in the kernel crashing. To add to the challenge, there are a total of 5421 clips requiring processing. Regrettably, even with 16GB of memory, it proves to be insufficient for the task at hand. I have made sincere efforts to explore alternative options, such as utilizing Colab, Kaggle Notebooks and free TPUs available with them. However, these platforms also encounter similar limitations, with all available RAM being swiftly exhausted. So, I kindly request that you unassign this issue and allow me to raise a new issue. Sorry for the inconvenience!
Sure. No problem @achrekarom12
Full name : Gudimella Saketa Sri Ramacharyulu GitHub Profile Link : https://github.com/SaketGudimella Email ID : radhasaket38@gmail.com Approach for this Project :For the Bundesliga Video Classification project, I will use three deep learning algorithms for object detection. The chosen algorithms are the Single Shot MultiBox Detector (SSD), Faster R-CNN (Region-based Convolutional Neural Networks), and YOLO (You Only Look Once). These algorithms are known for their efficiency, accuracy, and real-time performance in detecting objects. And by comparing these algorithms I will determine the most effective approach. What is your participant role? (Mention the Open Source program) - Contributor SSoC'23
@abhisheks008 Please assign me this issue to under the SSoC'23 label.
Issue assigned to you @SaketGudimella
Thank you
Full name : Routhu Manoj Sitaram GitHub Profile Link : https://github.com/Manoj-Routhu Email ID : manojrouthu26@gmail.com Participant ID (if applicable): NA Approach for this Project : :For the Bundesliga Video Classification project, I will use some DL algorithms which I know and find the which works better. some of the algorithms I would try are CNN with quantizing the data as mentioned above the data needs more resources, LSTM, 3D CNN's, Temporal Segment Networks. What is your participant role? (Mention the Open Source program) GSSoC'24
Assigned @Manoj-Routhu
Deep Learning Simplified Repository (Proposing new issue)
:red_circle: Project Title : Bundesliga Video Classification :red_circle: Aim : Create a DL model which will identify the videos from the german top tier football league Bundesliga. :red_circle: Dataset : https://www.kaggle.com/datasets/alejopaullier/dfl-clips :red_circle: Approach : Try to use 3-4 algorithms to implement the models and compare all the algorithms to find out the best fitted algorithm for the model by checking the accuracy scores. Also do not forget to do a exploratory data analysis before creating any model.
📍 Follow the Guidelines to Contribute in the Project :
requirements.txt
- This file will contain the required packages/libraries to run the project in other machines.Model
folder, theREADME.md
file must be filled up properly, with proper visualizations and conclusions.:red_circle::yellow_circle: Points to Note :
:white_check_mark: To be Mentioned while taking the issue :
Happy Contributing 🚀
All the best. Enjoy your open source journey ahead. 😎