我正在尝试使用PyTorch创建一个简单的图像分类器。 这就是我将数据加载到数据集和dataLoader中的方式:
batch_size = 64
validation_split = 0.2
data_dir = PROJECT_PATH+"/categorized_products"
transform = transforms.Compose([transforms.Grayscale(), CustomToTensor()])
dataset = ImageFolder(data_dir, transform=transform)
indices = list(range(len(dataset)))
train_indices = indices[:int(len(indices)*0.8)]
test_indices = indices[int(len(indices)*0.8):]
train_sampler = SubsetRandomSampler(train_indices)
test_sampler = SubsetRandomSampler(test_indices)
train_loader = torch.utils.data.DataLoader(dataset, batch_size=batch_size, sampler=train_sampler, num_workers=16)
test_loader = torch.utils.data.DataLoader(dataset, batch_size=batch_size, sampler=test_sampler, num_workers=16)
我想分别打印出训练和测试数据中每个班级的图像数量,如下所示:
火车数据中:
在测试数据中:
我尝试过:
from collections import Counter
print(dict(Counter(sample_tup[1] for sample_tup in dataset.imgs)))
但我收到此错误:
AttributeError: 'MyDataset' object has no attribute 'img'
答案 0 :(得分:5)
您需要使用.targets
来访问数据标签,即
print(dict(Counter(dataset.targets)))
它将打印这样的内容(例如在MNIST数据集中):
{5: 5421, 0: 5923, 4: 5842, 1: 6742, 9: 5949, 2: 5958, 3: 6131, 6: 5918, 7: 6265, 8: 5851}
此外,您可以使用.classes
或.class_to_idx
来获取标签ID到类的映射:
print(dataset.class_to_idx)
{'0 - zero': 0,
'1 - one': 1,
'2 - two': 2,
'3 - three': 3,
'4 - four': 4,
'5 - five': 5,
'6 - six': 6,
'7 - seven': 7,
'8 - eight': 8,
'9 - nine': 9}
编辑:方法1
根据评论,为了分别获得培训和测试集的课程分布,您可以按如下所示简单地遍历子集:
train_size = int(0.8 * len(dataset))
test_size = len(dataset) - train_size
train_dataset, test_dataset = torch.utils.data.random_split(dataset, [train_size, test_size])
# labels in training set
train_classes = [label for _, label in train_dataset]
Counter(train_classes)
Counter({0: 4757,
1: 5363,
2: 4782,
3: 4874,
4: 4678,
5: 4321,
6: 4747,
7: 5024,
8: 4684,
9: 4770})
编辑(2):方法2
由于您的数据集很大,并且正如您所说的,要花大量的时间来遍历所有训练集,所以有另一种方法:
您可以使用子集的.indices
,它引用为子集选择的原始数据集中的索引。
即
train_classes = [dataset.targets[i] for i in train_dataset.indices]
Counter(train_classes) # if doesn' work: Counter(i.item() for i in train_classes)