About patch_size

Hi,
Thanks for sharing your code! I have a question and hope to get your answer.

I found that the image crop into patch_size to training, the initial value of px and py is randomly determined by random.randrange. In this random case, how to ensure that the entire picture can be fully trained?

DeepDeblur-PyTorch/src/data/common.py

Line 32 in e92dc7c

py = random.randrange(0, h-ps+1)

Looking forward to your reply!

Hi @Brightlcz,

There is no guarantee that every pixel is accessed during training and the model is optimized perfectly.
However, by training for enough epochs, we expect the network could generalize to diverse inputs in training data.
In many ways deep learning utilizes/relies on randomness.

@SeungjunNah Thanks. The answer really helped.