“Ensemble de données Pytorch personnalisé divisé” Réponses codées

Ensemble de données Pytorch personnalisé divisé

import torch
import numpy as np
from torchvision import datasets
from torchvision import transforms
from torch.utils.data.sampler import SubsetRandomSampler

class CustomDatasetFromCSV(Dataset):
    def __init__(self, csv_path, transform=None):
        ....


dataset = CustomDatasetFromCSV(my_path)
batch_size = 16
validation_split = .2
shuffle_dataset = True
random_seed= 42

# Creating data indices for training and validation splits:
dataset_size = len(dataset)
indices = list(range(dataset_size))
split = int(np.floor(validation_split * dataset_size))
if shuffle_dataset :
    np.random.seed(random_seed)
    np.random.shuffle(indices)
train_indices, val_indices = indices[split:], indices[:split]

# Creating PT data samplers and loaders:
train_sampler = SubsetRandomSampler(train_indices)
valid_sampler = SubsetRandomSampler(val_indices)

train_loader = torch.utils.data.DataLoader(dataset, batch_size=batch_size, 
                                           sampler=train_sampler)
validation_loader = torch.utils.data.DataLoader(dataset, batch_size=batch_size,
                                                sampler=valid_sampler)

# Usage Example:
num_epochs = 10
for epoch in range(num_epochs):
    # Train:   
    for batch_index, (faces, labels) in enumerate(train_loader):
        # ...