QBoard » Artificial Intelligence & ML » AI and ML - Conceptual » Kernel size Vs Accuracy
User Dashboard

Kernel size Vs Accuracy

Back To Topics
Tags : None
  • 13
    Does kernel size effect the accuracy of the model?
      August 5, 2021 9:55 PM IST
    0
  • 84
    It depends more on the size of the objects you want to detect or in other words, the size of the receptive field you want to have. Nevertheless, choosing the kernel size was always a challenging decision. That is why the Inception model was created which uses different kernel sizes (1x1, 3x3, 5x5). The creators of this model also went deeper and tried to decompose the convolutional layers into ones with smaller patch size while maintaining the same receptive field to try to speed up the training (ex. 5x5 was decomposed to two 3x3 and 3x3 was decomposed to 3x1 and 1x3) creating different versions of the inception model.
    You can also check the Inception V2 paper for more details https://arxiv.org/abs/1512.00567
      September 7, 2021 11:19 PM IST
    0
  • 346 3
     It depends on the images, if you needed a lot of details from the image you don't need to increase your kernel size. ... Smaller kernel will gives you a lot of details, it can lead you to overfitting, but larger kernel will gives you loss a lot of details, it can lead you to underfitting
      August 21, 2021 11:53 AM IST
    0
  • 67 3
    Kernel size does not effect accuracy, since it is to convolve through given input only matters accuracy is kernel design. Features are extracted by design of kernel
      August 6, 2021 9:05 PM IST
    0
  • 131 2
    I'd say there is no direct relation between the kernel size and the accuracy. If you start using larger kernel you may start loosing details in some smaller features (where 3x3 would detect them better) and in other cases, where your dataset has larger features the 5x5 may start detect features that 3x3 misses
      August 9, 2021 8:28 PM IST
    0