File size: 1,694 Bytes
88147e5 |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 |
import os
import cv2
import torch
import albumentations as A
import config as CFG
class CLIPDataset(torch.utils.data.Dataset):
def __init__(self, image_filenames, captions, tokenizer, transforms):
"""
image_filenames and cpations must have the same length; so, if there are
multiple captions for each image, the image_filenames must have repetitive
file names
"""
self.image_filenames = image_filenames
self.captions = list(captions)
self.encoded_captions = tokenizer(
list(captions), padding=True, truncation=True, max_length=CFG.max_length
)
self.transforms = transforms
def __getitem__(self, idx):
item = {
key: torch.tensor(values[idx])
for key, values in self.encoded_captions.items()
}
image = cv2.imread(f"{CFG.image_path}/{self.image_filenames[idx]}")
image = cv2.cvtColor(image, cv2.COLOR_BGR2RGB)
image = self.transforms(image=image)['image']
item['image'] = torch.tensor(image).permute(2, 0, 1).float()
item['caption'] = self.captions[idx]
return item
def __len__(self):
return len(self.captions)
def get_transforms(mode="train"):
if mode == "train":
return A.Compose(
[
A.Resize(CFG.size, CFG.size, always_apply=True),
A.Normalize(max_pixel_value=255.0, always_apply=True),
]
)
else:
return A.Compose(
[
A.Resize(CFG.size, CFG.size, always_apply=True),
A.Normalize(max_pixel_value=255.0, always_apply=True),
]
)
|