Using DataLoader
The DataLoader class is essential for efficiently handling large datasets. It speeds up training, optimizes memory usage, and stabilizes gradient updates, making deep learning models more effective.
Now, you'll create a PyTorch DataLoader using the dataset from the previous exercise and see it in action.
Questo esercizio fa parte del corso
Introduction to Deep Learning with PyTorch
Istruzioni dell'esercizio
- Import the required module.
- Create a
DataLoaderusingdataset, setting a batch size of two and enabling shuffling. - Iterate through the
DataLoaderand print each batch of inputs and labels.
Esercizio pratico interattivo
Prova a risolvere questo esercizio completando il codice di esempio.
from torch.utils.data import ____
# Create a DataLoader
dataloader = ____
# Iterate over the dataloader
for batch_inputs, batch_labels in dataloader:
print('batch_inputs:', batch_inputs)
print('batch_labels:', batch_labels)