Where communities thrive


  • Join over 1.5M+ people
  • Join over 100K+ communities
  • Free without limits
  • Create your own community
People
Activity
    Swapnil
    @swaptr06_twitter
    Okay so on a second read, this is the best I could come up with. I would still recommend you to contact someone in the org, probably an admin, also in line with the direction to not email the mentors personally. I think to answer your preliminary question, yes you would have to use predefined libraries. They ask you to make a model, and not the algorithm itself so I think any one from PyTorch or Keras should do, maybe even sklearn but I can't comment on its scope for this task.
    Also peeking on the dataset does give me an intuition to read this file as a txt, a starting point for you would be to use the numpy.genfromtxt('file.csv', delimiter=',') coz obv its comma separated. This should give you enough to get started with some EDA.
    Ishita Mehta
    @ishitamehta028
    Okay. Thank you so much!
    Archil Srivastava
    @archilk

    Hi, in the DeepLense common task, we're given two sets: train and val. Can we do hyperparameter tuning on val (assuming our solution will be tested on an external set not given to us) or should we consider the existing val set as the test set and do hyperparameter tuning on a subset of the train set?
    For now I'm getting an AUC of 99% on the train set and 98.5% on the val set (without any hyperparameter tuning). Is this enough for the common task?

    Also, how will the submissions be judged? Based on AUC? Code clarity? Code structure?

    2 replies
    Abhinav Venkatadri
    @Abhinavvenkatadri

    Hi everyone. Absolutely newcomer to ML4SCI community

    I am currently a final year undergraduate student at Veermata Jijabai Technological Institute, India. I have experience in real-time object detection, classification, and tracking algorithms. I am also doing a research internship on a topic related to leaf classification and disease detection using fewer computational resources.

    I came across the project list for this year’s Google Summer of Code and found the project titled “Vision Transformers for End-to-End Particle Reconstruction for the CMS Experiment” quite interesting to me as my final year project is on similar lines where we are aiming to detect deepfakes, by using an ensemble of low latency algorithms followed by temporal feature extraction by using optical flow and vision transformers

    I am currently working on the tasks that are given.

    Ayush Raj
    @ayu1729
    Hi .I am Ayush. I am working on the deep lense common task right now. There two sets of data train and val are provided. At last of the gdoc it is mentioned we have to to do train test split 90:10 . So on which data do we have to give the evaluation metric .On Splitted testing data from the train test or on the validation set? 2 @PyJedi
    1 reply
    sakshamt133
    @sakshamt133

    @Shra1-25 I was trying to solve the given tasks for the project - 'graph neural network for end to end particle identification with CMS experiment'

    • while solving the 1st task I am facing problem while training the dataset, I have given the command for more than 12 hours. Is it any other way to do the same?

    • For the 2nd task, I am unable to read the dataset
      This is showing - "ArrowMemoryError: malloc of size 13602000000 failed"

    I would be glad if anyone can help to resolve my doubts so that I can proceed in solving these doubts.

    Mriganka Nath
    @mrinath123
    for the lens finding dataset, there are many missing .fits files? so how to handle them? anyone fixed it?
    Archil Srivastava
    @archilk
    @mrinath123 I just assumed that they are part of the external dataset and ignored them.Also, the other columns in the file classifications.csv (like einstein's area, num pixels of lens, etc) are useless for our puspose, right?
    I'm only picking is_lens column from classifications.csv for the labels
    Mriganka Nath
    @mrinath123
    Yeah I am doing it same
    Gopal Ramesh Dahale
    @Gopal-Dahale
    As I am interested in the Quantum CNN project, I found the previous year's work on this project by Eraraya Ricardo Muten. I wanted to how this year's project is different from the previous year as he also implemented a QCNN using TensorFlow quantum.
    sakshamt133
    @sakshamt133
    hi everyone, My name is Saksham Thakur , I am junior at NIT Hamirpur, my major is in computer science. I am a passionate about automation and machine learning. I am interested in the project - 'Vision Transformers for End-to-End Particle Reconstruction for the CMS Experiment'. I would be really grateful to get any initial instructions. - https://github.com/sakshamt133
    LinkedIn - https://www.linkedin.com/in/saksham-thakur-704182212
    Leetcode - https://leetcode.com/Saksham18363/
    I have experience in Python, Pytorch, huggingface, matplotlib, Data Structure and Algorithms, Scikit learn and other machine learning libraries
    Gopal Ramesh Dahale
    @Gopal-Dahale

    As I am interested in the Quantum CNN project, I found the previous year's work on this project by Eraraya Ricardo Muten. I wanted to how this year's project is different from the previous year as he also implemented a QCNN using TensorFlow quantum.

    Mentors please resolve this confusion.

    Swapnil
    @swaptr06_twitter
    @PyJedi I had submitted my Deeplense evaluation results earlier, now I have been working on the Vision Transformers task and wish to submit the solution, can i send another mail with the submission? In case I can, do i need to send a brand new mail with all the evaluation results or just the ViT one?
    ‪Karim Negm‬‏
    @Kareem-negm
    This message was deleted
    ‪Karim Negm‬‏
    @Kareem-negm
    Hello , Is there anyone here who has sent his task and the mentor has responded?
    Because I sent my task 20 days ago and I have not received a response yet
    Khushboo2724
    @Khushboo2724
    Hello there. My name is Khushboo Chaudhari and I am in my Freshman year currently. I am a completely newbie to this entire thing. Although I do know Python and I am very much more intrested in 'Deep Regression Techniques for Decoding Dark Matter with Strong Gravitational Lensing' project.It would be of a really great help if anyone of you can actually help me out with this. Thank you!
    Shinibaig
    @Shinibaig
    Hello! I'm Roshnik, is there anyone working on the messenger moon challange?
    2 replies
    Ashutosh Kumar
    @ashutoshkumar_kim:matrix.org
    [m]
    Hello ! is any_one there I need some help
    Anna-ray
    @Anna-ray
    here
    Ahmed Omar
    @ahmedo42
    how many didn't receive their evaluation results yet?
    Arpit Kumar Singh
    @ArpitKRS
    Hey everyone, I'm a new open source enthusiast, I came across ML4SCI's GSoC2022 project list and took interest in a projects. Where can I send my proposal for review before submitting it to GSoC page??
    also, I have some experience with machine learning and deep learning but any resources that will help me understand GSoC projects better with help me a lot. Please share some valuable resources with me .
    And if there is a particular format for proposals, please share it with me too.
    Tanisha Banik
    @26tanishabanik
    Hello everyone,
    I am Tanisha Banik, a B.tech final year student from KIIT University, I am a new member contributing to the google summer of code. Looking forward to learn a lot in the process.
    Github Handle: https://github.com/26tanishabanik
    Linkedin Handle: https://www.linkedin.com/in/tanisha-banik-04b511173/
    Though, I have few questions regarding the project on Machine Learning Model for the Albedo of MercuryMachine Learning Model for the Albedo of Mercury
    Tanisha Banik
    @26tanishabanik
    Will we have to submit the tasks mentioned here as part of the submit proposal https://drive.google.com/file/d/1QoxSdeL0JOqJJKCea75AwIyaujIV8gxB/view ?
    devender000
    @devender000
    Yes
    I am also working on that
    You can share your ideas here
    1 reply
    Tanisha Banik
    @26tanishabanik
    is anyone working on this project: https://ml4sci.org/gsoc/2022/proposal_LOX2.html ?
    devender000
    @devender000
    👍
    1 reply
    Ahmed Omar
    @ahmedo42
    has anyone been able to access the dataset for E2E regression project?
    Hrithik Shah
    @HrithikShah
    Hello everyone,
    is anyone working on Machine Learning Model for the Albedo of Mercury?
    2 replies
    devender000
    @devender000
    Hey Hrithik
    1 reply
    I am wokiy
    *working
    devender000
    @devender000
    My whattsapp 7981160755
    Tanisha Banik
    @26tanishabanik
    I had mailed my mentors regarding the draft for proposal and they haven't replied yet, I know they are busy, but is it okay, if I submit my proposal without being in contact with them?
    2 replies
    Ankit Kumar
    @Anky209e
    If anyone need help with resnets or cnn m up.I am also a student though i submitted my results for Exploring transformers with 99.48% accuracy.
    10 replies
    Michael
    @thavens
    Is anyone else having trouble getting the 0.8 AUC score for electron-photon classification? The research papers also seem to barely hit.
    1 reply
    Tanisha Banik
    @26tanishabanik
    How can I know what the size of the project is?
    2 replies
    Aditya Morolia
    @TheCharmingSociopath
    Hey, can we directly submit the proposal and email the test submission or do I have to contact the mentors before submitting the proposal? I found out about this just 2 days back and don't have enough time to get the test graded before submitting the proposal.
    Ishita Mehta
    @ishitamehta028
    Did anyone receive their Evaluation results for Mercury Albedo?
    1 reply
    Sanchet09
    @Sanchet09
    Hey, I had a small query regarding submission deadline.
    Is some delay in the test submission mailing permissible after the contributor registration deadline on the official GSoC page?
    manikanta-72
    @manikanta-72
    Hi, I am a graduate student at UCI. I am interested to be part of this organization. I am afraid I am late to start here. Can anyone help me? I am passionate about machine learning and its application.
    3 replies
    manikanta-72
    @manikanta-72
    Even if I dont make it gsoc I would be glad to contribute to this organization with some help.
    Harshavardhan_B
    @BayavarapuHarshavardhan
    Anyone can u specify me which skills do I need to learn so that I can take part in the projects more efficiently, i am familiar with c++, python, some python libraries like numpy, pandas, seaborn. Some part of data analysis