如何将自定义数据集拆分为训练数据集和测试数据集? [英] How do I split a custom dataset into training and test datasets?

问题描述

import pandas as pd
import numpy as np
import cv2
from torch.utils.data.dataset import Dataset

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):
        pixels = self.data['pixels'].tolist()
        faces = []
        for pixel_sequence in pixels:
            face = [int(pixel) for pixel in pixel_sequence.split(' ')]
            # print(np.asarray(face).shape)
            face = np.asarray(face).reshape(self.width, self.height)
            face = cv2.resize(face.astype('uint8'), (self.width, self.height))
            faces.append(face.astype('float32'))
        faces = np.asarray(faces)
        faces = np.expand_dims(faces, -1)
        return faces, self.labels

    def __len__(self):
        return len(self.data)

这是我可以通过使用来自其他存储库的引用来实现的.但是，我想将此数据集拆分为训练和测试.

This is what I could manage to do by using references from other repositories. However, I want to split this dataset into train and test.

我怎样才能在这个班级里做到这一点?或者我需要创建一个单独的类来做到这一点?

How can I do that inside this class? Or do I need to make a separate class to do that?

推荐答案

使用 Pytorch 的 SubsetRandomSampler:

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):
        # ...

这篇关于如何将自定义数据集拆分为训练数据集和测试数据集?的文章就介绍到这了，希望我们推荐的答案对大家有所帮助，也希望大家多多支持IT屋！