How does the size of the patch/kernel impact the result of a convnet?

user_983386 0
Viewed 4673

I am playing around convolutional neural networks at home with tensorflow (btw I have done the udacity deep learning course, so I have the theory basis). What impact has the size of the patch when one runs a convolution? does such size have to change when the image is bigger/smaller?

One of the exercises I did involved the CIFAR-10 databaese of images (32x32 px), then I used convolutions of 3x3 (with a padding of 1), getting decent results.

But lets say now I want to play with images larger than that (say 100x100), should I make my patches bigger? Do I keep them 3x3? Furthermore, what would be the impact of making a patch really big? (Say 50x50).

Normally I would test this at home directly, but running this on my computer is a bit slow (no nvidia GPU!)

So the question should be summarized as

  1. Should I increase/decrease the size of my patches when my input images are bigger/smaller?
  2. What is the impact (in terms of performance/overfitting) of increasing/decreasing my path size?
conv-neural-network machine-learning neural-network image-recognition
2 Answers

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

user_105208510
Related