Image Classification Using Vision Transformer | ViTs on Google Colab

Поделиться
HTML-код
  • Опубликовано: 12 янв 2025

Комментарии • 33

  • @swatimishra1555
    @swatimishra1555 28 дней назад

    Thank you for creating this video.

  • @soravsingla6574
    @soravsingla6574 Месяц назад

    What an amazing video

  • @Sunil-ez1hx
    @Sunil-ez1hx Месяц назад

    Very well done maam

  • @arnavthakur5409
    @arnavthakur5409 Месяц назад

    Excellent video with superb way of explaination

  • @hamidraza1584
    @hamidraza1584 Месяц назад +1

    Well done, Lots of love from Lahore Pakistan , this video is long awsited

    • @CodeWithAarohi
      @CodeWithAarohi  Месяц назад

      Thank you so much! I'm glad you liked it.

  • @princekhunt1
    @princekhunt1 Месяц назад

    Nice explanation

  • @HarshDewangan-kl9ur
    @HarshDewangan-kl9ur Месяц назад

    Thankyou so much, ma'am Nice video

    • @CodeWithAarohi
      @CodeWithAarohi  Месяц назад

      Thank you! Glad you found it helpful. 😊

  • @jeffg4686
    @jeffg4686 Месяц назад

    much thanks, great explanations. thx for providing the code.

  • @soravsingla8782
    @soravsingla8782 Месяц назад

    Excellent video

  • @pifordtechnologiespvtltd5698
    @pifordtechnologiespvtltd5698 Месяц назад

    Nice videos

  • @ahmadkelixo7243
    @ahmadkelixo7243 Месяц назад

    permission to learn Mom. thank you

    • @CodeWithAarohi
      @CodeWithAarohi  Месяц назад

      You're welcome! Happy to help you learn. 😊

  • @swatimishra1555
    @swatimishra1555 43 минуты назад

    Can we add convolution layers or any pre trained model before the VIT for image classification. plz reply and how? can you post any link for this

  • @alisson_pina
    @alisson_pina Месяц назад

    Great job! Is it possible to apply ViT to segmentation cases?

    • @CodeWithAarohi
      @CodeWithAarohi  Месяц назад +1

      Yes, ViTs can be applied to segmentation tasks by using architectures like SegFormer.

  • @adityabala3743
    @adityabala3743 28 дней назад

    Really loved the explanation
    I am getting train ccuracy of 26% for the classification model i built with 800 images for each class, can you please tell on how to improve it

    • @CodeWithAarohi
      @CodeWithAarohi  19 дней назад

      800 images per class is a good choice but model's accuracy is very low. Make sure your images are of good quality and you have used data preprocessing steps properly. Also, if you are working on complex classes then you can also try to increase the dataset and train the model for more epochs . You can also fine tune the hyperparameters.

  • @mostofakamalshaon1558
    @mostofakamalshaon1558 5 дней назад

    should I use this for skin cancer classification?

  • @fatima-arbab
    @fatima-arbab Месяц назад

    Ma'am please make a video on
    Copy Move Forgery Detection in video using Machine Learning
    Using yolo model and casia V1 , V2 dataset

  • @vidhyajeyachandran2704
    @vidhyajeyachandran2704 Месяц назад

    Is it possible to apply ViT for video classification?

    • @CodeWithAarohi
      @CodeWithAarohi  Месяц назад +1

      Yes, ViTs can be applied to video classification tasks, but you have to modify the code of ViT in such a way that it can handle both spatial and temporal dimensions.

    • @vidhyajeyachandran2704
      @vidhyajeyachandran2704 Месяц назад

      @CodeWithAarohi Thank u so much, can u make a video on how to handle video ?