Generating image from MNIST Data

Question:

I am quite new to python and pytorch. Please review my code below. I have tried everything I know but I am not able to create a MNIST data set image out of the matrix below. I expect the image should be 1.
It would be great if someone can help me in it.

import torch
import torch.nn.functional as F
import torch.optim as optim

import torchquantum as tq
import torchquantum.functional as tqf

from torchquantum.datasets import MNIST
from torch.optim.lr_scheduler import CosineAnnealingLR

import random
import numpy as np
import matplotlib.pyplot as plt
%matplotlib inline
dataset = MNIST(root='../Data_Manu',
                 train_valid_split_ratio=[0.9, 0.1],
            digits_of_interest=[3, 6],
            n_test_samples=75)


data_value =dataset['train'][0]
## Output is below

{‘image’: tensor([[[-0.4242, -0.4242, -0.4242, -0.4242, -0.4242, -0.4242, -0.4242,
-0.4242, -0.4242, -0.4242, -0.4242, -0.4242, -0.4242, -0.4242,
-0.4242, -0.4242, -0.4242, -0.4242, -0.4242, -0.4242, -0.4242,
-0.4242, -0.4242, -0.4242, -0.4242, -0.4242, -0.4242, -0.4242],
[-0.4242, -0.4242, -0.4242, -0.4242, -0.4242, -0.4242, -0.4242,
-0.4242, -0.4242, -0.4242, -0.4242, -0.4242, -0.4242, -0.4242,
-0.4242, -0.4242, -0.4242, -0.4242, -0.4242, -0.4242, -0.4242,
-0.4242, -0.4242, -0.4242, -0.4242, -0.4242, -0.4242, -0.4242],
[-0.4242, -0.4242, -0.4242, -0.4242, -0.4242, -0.4242, -0.4242,
-0.4242, -0.4242, -0.4242, -0.4242, -0.4242, -0.4242, -0.4242,
-0.4242, -0.4242, -0.4242, -0.4242, -0.4242, -0.4242, -0.4242,
-0.4242, -0.4242, -0.4242, -0.4242, -0.4242, -0.4242, -0.4242],
[-0.4242, -0.4242, -0.4242, -0.4242, -0.4242, -0.4242, -0.4242,
-0.4242, -0.4242, -0.4242, -0.4242, -0.4242, -0.4242, -0.4242,
-0.4242, -0.4242, -0.4242, -0.4242, 0.1740, 2.5415, 2.7960,
2.7960, 1.4214, -0.4242, -0.4242, -0.4242, -0.4242, -0.4242],
[-0.4242, -0.4242, -0.4242, -0.4242, -0.4242, -0.4242, -0.4242,
-0.4242, -0.4242, -0.4242, -0.4242, -0.4242, -0.4242, -0.4242,
-0.4242, -0.4242, -0.4242, 1.1668, 2.5415, 2.7833, 2.7833,
2.7833, 2.2105, -0.1696, -0.4242, -0.4242, -0.4242, -0.4242],
[-0.4242, -0.4242, -0.4242, -0.4242, -0.4242, -0.4242, -0.4242,
-0.4242, -0.4242, -0.4242, -0.4242, -0.4242, -0.4242, -0.4242,
-0.4242, -0.2842, 0.3140, 2.3887, 2.7960, 2.7833, 2.7069,
2.3124, 1.1668, -0.4242, -0.4242, -0.4242, -0.4242, -0.4242],
[-0.4242, -0.4242, -0.4242, -0.4242, -0.4242, -0.4242, -0.4242,
-0.4242, -0.4242, -0.4242, -0.4242, -0.4242, -0.4242, -0.4242,
-0.4115, 1.5487, 2.7833, 2.7833, 2.7960, 2.2487, 0.7468,
-0.4242, -0.4242, -0.4242, -0.4242, -0.4242, -0.4242, -0.4242],
[-0.4242, -0.4242, -0.4242, -0.4242, -0.4242, -0.4242, -0.4242,
-0.4242, -0.4242, -0.4242, -0.4242, -0.4242, -0.4242, -0.4242,
1.7523, 2.7833, 2.7833, 2.7833, 2.1978, -0.1696, -0.4242,
-0.4242, -0.4242, -0.4242, -0.4242, -0.4242, -0.4242, -0.4242],
[-0.4242, -0.4242, -0.4242, -0.4242, -0.4242, -0.4242, -0.4242,
-0.4242, -0.4242, -0.4242, -0.4242, -0.4242, -0.2842, 0.5049,
2.7960, 2.7833, 2.7833, 2.2487, -0.1696, -0.4242, -0.4242,
-0.4242, -0.4242, -0.4242, -0.4242, -0.4242, -0.4242, -0.4242],
[-0.4242, -0.4242, -0.4242, -0.4242, -0.4242, -0.4242, -0.4242,
-0.4242, -0.4242, -0.4242, -0.4242, -0.4242, 1.3577, 2.7833,
2.7960, 2.7833, 2.1851, -0.0296, -0.4242, -0.4242, -0.4242,
-0.4242, -0.4242, -0.4242, -0.4242, -0.4242, -0.4242, -0.4242],
[-0.4242, -0.4242, -0.4242, -0.4242, -0.4242, -0.4242, -0.4242,
-0.4242, -0.4242, -0.4242, -0.4242, 1.1668, 2.3887, 2.7833,
2.7960, 2.2487, -0.0296, -0.4242, -0.4242, -0.4242, -0.4242,
-0.4242, -0.4242, -0.4242, -0.4242, -0.4242, -0.4242, -0.4242],
[-0.4242, -0.4242, -0.4242, -0.4242, -0.4242, -0.4242, -0.4242,
-0.4242, -0.4242, -0.4242, 0.9759, 2.7960, 2.7960, 2.7960,
2.8215, 1.0904, -0.4242, -0.4242, -0.4242, -0.4242, -0.4242,
-0.4242, -0.4242, -0.4242, -0.4242, -0.4242, -0.4242, -0.4242],
[-0.4242, -0.4242, -0.4242, -0.4242, -0.4242, -0.4242, -0.4242,
-0.4242, -0.4242, -0.4115, 1.4723, 2.7833, 2.7833, 2.7833,
0.0213, -0.3606, -0.4242, 0.1104, -0.0169, -0.2969, -0.4242,
-0.4242, -0.4242, -0.4242, -0.4242, -0.4242, -0.4242, -0.4242],
[-0.4242, -0.4242, -0.4242, -0.4242, -0.4242, -0.4242, -0.4242,
-0.4242, -0.4242, -0.1569, 2.7833, 2.7833, 2.7833, 1.4596,
-0.4242, -0.0169, 1.3577, 2.3887, 2.2742, 1.4723, -0.0169,
-0.4242, -0.4242, -0.4242, -0.4242, -0.4242, -0.4242, -0.4242],
[-0.4242, -0.4242, -0.4242, -0.4242, -0.4242, -0.4242, -0.4242,
-0.4242, -0.1569, 2.1978, 2.7833, 2.7833, 2.7833, 0.9504,
1.4214, 2.5924, 2.7833, 2.7833, 2.7960, 2.7833, 2.3124,
-0.4242, -0.4242, -0.4242, -0.4242, -0.4242, -0.4242, -0.4242],
[-0.4242, -0.4242, -0.4242, -0.4242, -0.4242, -0.4242, -0.4242,
-0.4242, 0.0467, 2.7960, 2.7960, 2.7960, 2.7960, 2.7960,
2.8215, 2.7960, 2.7960, 2.7960, 2.8215, 2.7960, 2.5287,
0.1740, -0.4242, -0.4242, -0.4242, -0.4242, -0.4242, -0.4242],
[-0.4242, -0.4242, -0.4242, -0.4242, -0.4242, -0.4242, -0.4242,
-0.4242, 0.0467, 2.7833, 2.7833, 2.7833, 2.7833, 2.7833,
2.7960, 2.7833, 2.7833, 2.7833, 2.7960, 2.7833, 2.6433,
0.5559, -0.4242, -0.4242, -0.4242, -0.4242, -0.4242, -0.4242],
[-0.4242, -0.4242, -0.4242, -0.4242, -0.4242, -0.4242, -0.4242,
-0.4242, 1.3577, 2.7833, 2.7833, 2.7833, 2.7833, 2.7833,
2.7960, 2.7833, 2.7833, 2.7833, 2.7960, 2.7833, 2.3124,
-0.4242, -0.4242, -0.4242, -0.4242, -0.4242, -0.4242, -0.4242],
[-0.4242, -0.4242, -0.4242, -0.4242, -0.4242, -0.4242, -0.4242,
-0.4242, 1.8796, 2.7833, 2.7833, 2.7833, 2.7833, 2.7833,
2.7960, 2.7833, 2.7833, 2.7833, 2.7960, 2.2487, 0.7468,
-0.4242, -0.4242, -0.4242, -0.4242, -0.4242, -0.4242, -0.4242],
[-0.4242, -0.4242, -0.4242, -0.4242, -0.4242, -0.4242, -0.4242,
-0.4242, 1.8923, 2.7960, 2.7960, 2.7960, 2.7960, 2.7960,
2.8215, 2.7960, 2.7960, 2.7960, 1.4214, -0.1696, -0.4242,
-0.4242, -0.4242, -0.4242, -0.4242, -0.4242, -0.4242, -0.4242],
[-0.4242, -0.4242, -0.4242, -0.4242, -0.4242, -0.4242, -0.4242,
-0.4242, 1.3450, 2.7833, 2.7833, 2.7833, 2.7833, 2.7833,
2.7960, 2.7833, 2.1214, 0.8104, -0.4242, -0.4242, -0.4242,
-0.4242, -0.4242, -0.4242, -0.4242, -0.4242, -0.4242, -0.4242],
[-0.4242, -0.4242, -0.4242, -0.4242, -0.4242, -0.4242, -0.4242,
-0.4242, 0.0467, 2.7833, 2.7833, 2.7833, 2.4524, 2.3124,
0.4922, 0.4795, -0.1696, -0.4242, -0.4242, -0.4242, -0.4242,
-0.4242, -0.4242, -0.4242, -0.4242, -0.4242, -0.4242, -0.4242],
[-0.4242, -0.4242, -0.4242, -0.4242, -0.4242, -0.4242, -0.4242,
-0.4242, -0.2206, 1.9942, 2.7833, 2.2487, -0.0296, -0.4242,
-0.4242, -0.4242, -0.4242, -0.4242, -0.4242, -0.4242, -0.4242,
-0.4242, -0.4242, -0.4242, -0.4242, -0.4242, -0.4242, -0.4242],
[-0.4242, -0.4242, -0.4242, -0.4242, -0.4242, -0.4242, -0.4242,
-0.4242, -0.4242, -0.4242, -0.4242, -0.4242, -0.4242, -0.4242,
-0.4242, -0.4242, -0.4242, -0.4242, -0.4242, -0.4242, -0.4242,
-0.4242, -0.4242, -0.4242, -0.4242, -0.4242, -0.4242, -0.4242],
[-0.4242, -0.4242, -0.4242, -0.4242, -0.4242, -0.4242, -0.4242,
-0.4242, -0.4242, -0.4242, -0.4242, -0.4242, -0.4242, -0.4242,
-0.4242, -0.4242, -0.4242, -0.4242, -0.4242, -0.4242, -0.4242,
-0.4242, -0.4242, -0.4242, -0.4242, -0.4242, -0.4242, -0.4242],
[-0.4242, -0.4242, -0.4242, -0.4242, -0.4242, -0.4242, -0.4242,
-0.4242, -0.4242, -0.4242, -0.4242, -0.4242, -0.4242, -0.4242,
-0.4242, -0.4242, -0.4242, -0.4242, -0.4242, -0.4242, -0.4242,
-0.4242, -0.4242, -0.4242, -0.4242, -0.4242, -0.4242, -0.4242],
[-0.4242, -0.4242, -0.4242, -0.4242, -0.4242, -0.4242, -0.4242,
-0.4242, -0.4242, -0.4242, -0.4242, -0.4242, -0.4242, -0.4242,
-0.4242, -0.4242, -0.4242, -0.4242, -0.4242, -0.4242, -0.4242,
-0.4242, -0.4242, -0.4242, -0.4242, -0.4242, -0.4242, -0.4242],
[-0.4242, -0.4242, -0.4242, -0.4242, -0.4242, -0.4242, -0.4242,
-0.4242, -0.4242, -0.4242, -0.4242, -0.4242, -0.4242, -0.4242,
-0.4242, -0.4242, -0.4242, -0.4242, -0.4242, -0.4242, -0.4242,
-0.4242, -0.4242, -0.4242, -0.4242, -0.4242, -0.4242, -0.4242]]]),
‘digit’: 1}

plt.imshow(data_value.numpy()[0], cmap='gray')

AttributeError                            Traceback (most recent call last)
<ipython-input-7-498b4257facf> in <module>
----> 1 plt.imshow(data_value.numpy()[0], cmap='gray')

AttributeError: 'dict' object has no attribute 'numpy'

Thank you for the great help.

Asked By: Manu

||
Source

Answers:

Try change this plt.imshow(data_value.numpy()[0], cmap='gray') to plt.imshow(data_value['image'].numpy()[0], cmap='gray').

Your output is not a torch.Tensor is dict than contains two labels "image" (Tensor) and "digit" (int).

Is for that reason you have this error AttributeError: 'dict' object has no attribute 'numpy'

Answered By: StandardIO
Categories: questions Tags: , ,
Answers are sorted by their score. The answer accepted by the question owner as the best is marked with
at the top-right corner.