Today I have started to learn Pytorch and I stuck here. The code piece in the comment raises this error:
TypeError: Cannot interpret 'torch.uint8' as a data type
For changing the data type of the tensor I used: quzu_torch = quzu_torch.type(torch.float) But this time I got this error:
TypeError: Cannot interpret 'torch.float32' as a data type
import numpy as np
import torch
from matplotlib import pyplot as plt
quzu = np.array(Image.open('wool.jpg').resize((224,224)))
quzu_torch = torch.from_numpy(quzu)
plt.imsave('quzucuq.jpg', quzu)
# quzu_torch = quzu_torch.type(torch.bool)
plt.imsave('quzucuq_tensor.jpg', quzu_torch)```
Just use the numpy array for the image don't convert it into a torch tensor.
If you love us? You can donate to us via Paypal or buy me a coffee so we can maintain and grow! Thank you!
Donate Us With