How do I split a custom dataset into training and test datasets?
Starting in PyTorch 0.4.1 you can use random_split
:
train_size = int(0.8 * len(full_dataset))
test_size = len(full_dataset) - train_size
train_dataset, test_dataset = torch.utils.data.random_split(full_dataset, [train_size, test_size])
Using Pytorch's SubsetRandomSampler
:
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):
self.data = pd.read_csv(csv_path)
self.labels = pd.get_dummies(self.data['emotion']).as_matrix()
self.height = 48
self.width = 48
self.transform = transform
def __getitem__(self, index):
# This method should return only 1 sample and label
# (according to "index"), not the whole dataset
# So probably something like this for you:
pixel_sequence = self.data['pixels'][index]
face = [int(pixel) for pixel in pixel_sequence.split(' ')]
face = np.asarray(face).reshape(self.width, self.height)
face = cv2.resize(face.astype('uint8'), (self.width, self.height))
label = self.labels[index]
return face, label
def __len__(self):
return len(self.labels)
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):
# ...