How to train YOLO-NAS Object Detection on Custom Dataset | step by step Tutorial | Google Colab

Поделиться
HTML-код
  • Опубликовано: 10 янв 2025

Комментарии • 16

  • @mohaliyet
    @mohaliyet 11 месяцев назад +1

    Thank you Sir!

    • @coder_zero
      @coder_zero  10 месяцев назад

      Hi, will do that soon 😀

  • @malikakarmach2856
    @malikakarmach2856 8 месяцев назад +1

    Thank you for the video. I have a question regarding the training phase when I train Moodle on my data I don't notice the summary and mAP 0.50-0.95 ? how can I show it?

    • @coder_zero
      @coder_zero  8 месяцев назад

      you can use "metric_to_watch": 'mAP@0.50:0.95'

    • @malikakarmach2856
      @malikakarmach2856 8 месяцев назад

      @@coder_zero Yes, I've used it but it gives me an error message saying it couldn't find it.

  • @loowaijun2960
    @loowaijun2960 Год назад +2

    Hi Sir, good tutorial. May I know how to check mAP@0.50:0.95 and mAR of the model?

    • @coder_zero
      @coder_zero  8 месяцев назад

      sorry for late reply. you can use "metric_to_watch": 'mAP@0.50:0.95'

  • @thangdaoxuan
    @thangdaoxuan Год назад +2

    I have a YOLO NAS model for animal detection. I ran the model for 25 epochs and have got the best.pth weights. I need to add more epochs, to train it more from where i left off. I have read somewhere that YOLO V5 have such an option. Does YOLO NAS have the same option? If so how can i implement it in colab?
    PS. It took me 10 - 15 hours to train for 25 epochs. So I am tight on time. I am not sure whether I am doing something wrong, but I am training using A100 GPU in Colab and its taking this much time. Please advice. I have 17.8 GB of data which has around 38790 images, so i guess it makes sense to take that much time?
    I tried looking through the YOLO NAS documentation and google searched it, but couldn't get any concrete ideas.

    • @coder_zero
      @coder_zero  Год назад +1

      Hi, you can put checkpoint_path = path of last epoch weight while loading the model. Then run the training code . Check the code that shows how to load model after training in the colab notebook.

    • @thangdaoxuan
      @thangdaoxuan Год назад

      @@coder_zero thanks

  • @АльбертИванов-ц4х

    thanks. 5 epoch enough for training ?

    • @coder_zero
      @coder_zero  Год назад

      Hi, 5 epochs are not enough for training a good model. Please focus on early stopping rather than number of epochs.

  • @fayezchamp9365
    @fayezchamp9365 Год назад

    Hi my group member from SIC

  • @ilapartijharinath4481
    @ilapartijharinath4481 Год назад

    hi sir in visualisation what is data.yaml file

    • @coder_zero
      @coder_zero  Год назад

      Hi, you can remove that data_yaml_path and it will work. I was experimenting something.

    • @amanshaikh9680
      @amanshaikh9680 Год назад

      hi it is data_yaml_path is the required argument. Can you pls share the training path for the yaml file@@coder_zero