Набор данных MNIST не удалось преобразовать как тензорный объект

Question

Как правильно преобразовать набор данных MNIST в тензорный тип? Я пробовал ниже, но не работал. Сообщение об ошибке AttributeError: 'int' object has no attribute 'type' указывает, что это не тензорный тип.

Приведенные ниже коды можно протестировать в Google Colab.

Похоже, что PyTorch Version 1.3.1 может запускать это, но не для 1.5.1.

>>> import torch
>>> import torch.nn as nn
>>> import torchvision.transforms as transforms
>>> import torchvision.datasets as dsets
>>> import numpy as np
>>> torch.__version__
1.5.1+cu101

>>> train_dataset = dsets.MNIST(root='./data', train=True, download=True, transform=transforms.ToTensor())
Downloading http://yann.lecun.com/exdb/mnist/train-images-idx3-ubyte.gz to ./data/MNIST/raw/train-images-idx3-ubyte.gz
100.1%Extracting ./data/MNIST/raw/train-images-idx3-ubyte.gz to ./data/MNIST/raw
Downloading http://yann.lecun.com/exdb/mnist/train-labels-idx1-ubyte.gz to ./data/MNIST/raw/train-labels-idx1-ubyte.gz
113.5%Extracting ./data/MNIST/raw/train-labels-idx1-ubyte.gz to ./data/MNIST/raw
Downloading http://yann.lecun.com/exdb/mnist/t10k-images-idx3-ubyte.gz to ./data/MNIST/raw/t10k-images-idx3-ubyte.gz
100.4%Extracting ./data/MNIST/raw/t10k-images-idx3-ubyte.gz to ./data/MNIST/raw
Downloading http://yann.lecun.com/exdb/mnist/t10k-labels-idx1-ubyte.gz to ./data/MNIST/raw/t10k-labels-idx1-ubyte.gz
180.4%Extracting ./data/MNIST/raw/t10k-labels-idx1-ubyte.gz to ./data/MNIST/raw
Processing...
/pytorch/torch/csrc/utils/tensor_numpy.cpp:141: UserWarning: The given NumPy array is not writeable, and PyTorch does not support non-writeable tensors. This means you can write to the underlying (supposedly non-writeable) NumPy array using the tensor. You may want to copy the array to protect its data or make it writeable before converting it to a tensor. This type of warning will be suppressed for the rest of this program.
Done!

>>> print("Print the training dataset:\n ", train_dataset)
Print the training dataset:
  Dataset MNIST
    Number of datapoints: 60000
    Root location: ./data
    Split: Train
    StandardTransform
Transform: ToTensor()

>>> print("Type of data element: ", train_dataset[0][1].type())
Traceback (most recent call last):
  File "<stdin>", line 1, in <module>
AttributeError: 'int' object has no attribute 'type'

Answer 1

Вам нужен Ist элемент (соответствующий тензорам изображения), а не второй (метки), т.е.

>>> print("Type of data element: ", train_dataset[0][0].type())
Type of data element:  torch.FloatTensor

>>> print(train_dataset[0][0].shape, train_dataset[0][1])
(torch.Size([1, 28, 28]), 5)