I am currently working on patch based super-resolution. Most of the papers divide an image into smaller patches and then use the patches as input to the models. I completed the coding to create patches using custom dataloader. The code is given below:
import torch.utils.data as data
from torchvision.transforms import CenterCrop, ToTensor, Compose, ToPILImage, Resize, RandomHorizontalFlip, RandomVerticalFlip
from os import listdir
from os.path import join
from PIL import Image
import random
import os
import numpy as np
import torch
def is_image_file(filename):
return any(filename.endswith(extension) for extension in [".png", ".jpg", ".jpeg", ".bmp"])
class TrainDatasetFromFolder(data.Dataset):
def __init__(self, dataset_dir, patch_size, is_gray, stride):
super(TrainDatasetFromFolder, self).__init__()
self.imageHrfilenames = []
self.imageHrfilenames.extend(join(dataset_dir, x)
for x in sorted(listdir(dataset_dir)) if is_image_file(x))
self.is_gray = is_gray
self.patchSize = patch_size
self.stride = stride
def _load_file(self, index):
filename = self.imageHrfilenames[index]
hr = Image.open(self.imageHrfilenames[index])
downsizes = (1, 0.7, 0.45)
downsize = 2
w_ = int(hr.width * downsizes[downsize])
h_ = int(hr.height * downsizes[downsize])
aug = Compose([Resize([h_, w_], interpolation=Image.BICUBIC),
RandomHorizontalFlip(),
RandomVerticalFlip()])
hr = aug(hr)
rv = random.randint(0, 4)
hr = hr.rotate(90*rv, expand=1)
filename = os.path.splitext(os.path.split(filename)[-1])[0]
return hr, filename
def _patching(self, img):
img = ToTensor()(img)
LR_ = Compose([ToPILImage(), Resize(self.patchSize//2, interpolation=Image.BICUBIC), ToTensor()])
HR_p, LR_p = [], []
for i in range(0, img.shape[1] - self.patchSize, self.stride):
for j in range(0, img.shape[2] - self.patchSize, self.stride):
temp = img[:, i:i + self.patchSize, j:j + self.patchSize]
HR_p += [temp]
LR_p += [LR_(temp)]
return torch.stack(LR_p),torch.stack(HR_p)
def __getitem__(self, index):
HR_, filename = self._load_file(index)
LR_p, HR_p = self._patching(HR_)
return LR_p, HR_p
def __len__(self):
return len(self.imageHrfilenames)
Suppose the batch size is 1, it takes an image and gives an output of size [x,3,patchsize,patchsize]. When batch size is 2, I will have two different outputs of size[x,3,patchsize,patchsize] (for example image 1 may give[50,3,patchsize,patchsize], image 2 may give[75,3,patchsize,patchsize] ). To handle this a custom collate function was required. The collate function is given below:
def my_collate(batch):
data = torch.cat([item[0] for item in batch],dim = 0)
target = torch.cat([item[1] for item in batch],dim = 0)
return [data, target]
This collate function concatenates along x (From the above example, I finally get[125,3,patchsize,pathsize].
Next, I need to train the model using a minibatch size of say 25. Can anyone help me build a sampler which I can use to directly get an output of size [25 , 3, patchsize, pathsize] from dataloader. I saw Batchsampling recently. Any idea how to incorporate that?
Thank you.