目标检测数据集

下载数据集

%matplotlib inline
import os
import pandas as pd
import torch
import torchvision
from d2l import torch as d2l

#@save
d2l.DATA_HUB['banana-detection'] = (
    d2l.DATA_URL + 'banana-detection.zip',
    '5de26c8fce5ccdea9f91267273464dc968d20d72')

读取数据集

#@save
def read_data_bananas(is_train=True):
    """读取香蕉检测数据集中的图像和标签。"""
    data_dir = d2l.download_extract('banana-detection')
    csv_fname = os.path.join(data_dir,
                             'bananas_train' if is_train else 'bananas_val',
                             'label.csv')
    csv_data = pd.read_csv(csv_fname)
    csv_data = csv_data.set_index('img_name')
    images, targets = [], []
    for img_name, target in csv_data.iterrows():
        images.append(
            torchvision.io.read_image(
                os.path.join(data_dir,
                             'bananas_train' if is_train else 'bananas_val',
                             'images', f'{img_name}')))
        # Here `target` contains (class, upper-left x, upper-left y,
        # lower-right x, lower-right y), where all the images have the same
        # banana class (index 0)
        targets.append(list(target))
    return images, torch.tensor(targets).unsqueeze(1) / 256

自定义dataset

#@save
class BananasDataset(torch.utils.data.Dataset):
    """一个用于加载香蕉检测数据集的自定义数据集。"""
    def __init__(self, is_train):
        self.features, self.labels = read_data_bananas(is_train)
        print('read ' + str(len(self.features)) + (
            f' training examples' if is_train else f' validation examples'))

    def __getitem__(self, idx):
        return (self.features[idx].float(), self.labels[idx])

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

dataloader读取一个iteration

#@save
def load_data_bananas(batch_size):
    """加载香蕉检测数据集。"""
    train_iter = torch.utils.data.DataLoader(BananasDataset(is_train=True),
                                             batch_size, shuffle=True)
    val_iter = torch.utils.data.DataLoader(BananasDataset(is_train=False),
                                           batch_size)
    return train_iter, val_iter

示例

标签的小批量的形状为（批量大小， m ，5），5是类别，左上右下坐标，其中 m 是数据集的任何图像中边界框可能出现的最大数量，当某张图片边界框数量不够m时，填充非法边界框，将类别置为-1。

batch_size, edge_size = 32, 256
train_iter, _ = load_data_bananas(batch_size)
batch = next(iter(train_iter))
batch[0].shape, batch[1].shape # torch.Size([32, 3, 256, 256])，torch.Size([32, 1, 5]) ，中间1是边界框的个数

打印图片

imgs = (batch[0][0:10].permute(0, 2, 3, 1)) / 255 #原先是通道，宽，高->宽，高，通道
axes = d2l.show_images(imgs, 2, 5, scale=2)
for ax, label in zip(axes, batch[1][0:10]):
    d2l.show_bboxes(ax, [label[0][1:5] * edge_size], colors=['w'])