2

I am trying to train my own network on Caffe, similar to Imagenet model. But I am confused with the crop layer. Till the point I understand about crop layer in Imagenet model, during training it will take random 227x227 image crops and train the network. But during testing it will take the center 227x227 image crop, does not we loose the information from image while we crop the center 227x27 image from 256x256 image? And second question, how can we define the number of crops to be taken during training?

And also, I trained the same network(same number of layers, same convolution size FC neurons will differ obviously), first taking 227x227 crop from 256x256 image, and second time taking 255x255 crop from 256x256 image. According to my intuition, the model with 255x255 crop should give me the best result. But I am getting higher accuracy with 227x227 image, can anyone explain me the intuition behind it, or am i doing something wrong?

Dharma
  • 2,425
  • 3
  • 26
  • 40
  • I think this question should get a broader answer describing how exactly caffe handles "on the fly" data augmentation. Would very like to see an answer to that. – Shai Mar 05 '17 at 07:49
  • @Shai Ya thats fine. – Dharma Mar 05 '17 at 17:41

1 Answers1

0

Your observations are not specific to Caffe.

The sizes of the cropped images during training and testing need to be the same (227x227 in your case), because the upstream network layers (convolutions, etc) need the images to be the same size. Random crops are done during training is because you want data augmentation. However, during testing, you want to test against a standard dataset. Otherwise, the accuracy reported during testing would also depend on a shifting test database.

The crops are made dynamically at each iteration. All images in a training batch are randomly cropped. I hope this answers your second question.

Your intuition is not complete: With a bigger crop (227x227), you have more data augmentation. Data augmentation essentially creates "new" training samples out of nothing. This is vital to prevent overfitting during training. With a smaller crop (255x255), you should expect a better training accuracy but lower test accuracy, since the data is more likely be overfitted.

Of course, cropping can be overdone. Too much cropping and you lose too much information from an image. For image categorization, the ideal crop size is one that does not alter the category of an image, (ie, only background is cropped away).

arnold
  • 106
  • 2