LingoQA dataset for pytorch
Project description
LingoQA dataset for pytorch
How to use
from lingoqa_dataset.dataset import LingoQADataset
import torchvision.transforms as transforms
from torch.utils.data import DataLoader
dataset = LingoQADataset(
DatasetType.EVALUATION, transforms=transforms.Resize((256, 512))
)
dataloader = DataLoader(dataset=dataset, batch_size=3, shuffle=True)
for data, question, answer in dataloader:
pass
data
- type: torch.Tensor
- size : torch.Size([batch_size, 3 * number_of_images, height, width])
- description : Images in the target sequences.
question
- type: torch.Tuple(str)
- size: batch_size
- description : Questions in the batch.
answer
- type: torch.Tuple(str)
- size: batch_size
- description : Answers in the batch.
Special thanks
Project details
Release history Release notifications | RSS feed
Download files
Download the file for your platform. If you're not sure which to choose, learn more about installing packages.
Source Distribution
lingoqa_dataset-0.1.1.tar.gz
(2.6 kB
view hashes)
Built Distribution
Close
Hashes for lingoqa_dataset-0.1.1-py3-none-any.whl
Algorithm | Hash digest | |
---|---|---|
SHA256 | 1b9b185d173190c0f2c082f8fb7b9858102f6e0c20a40b1def76e3be9a23206c |
|
MD5 | cc12e9560efa9d4a70cddbf7be0a0f59 |
|
BLAKE2b-256 | 610571907a7514f045e38bc82d049807aab8832ebc6a38c291cba427812b5980 |