![[The AI Show Episode 144]: ChatGPT’s New Memory, Shopify CEO’s Leaked “AI First” Memo, Google Cloud Next Releases, o3 and o4-mini Coming Soon & Llama 4’s Rocky Launch](https://www.marketingaiinstitute.com/hubfs/ep%20144%20cover.png)
![[DEALS] The All-in-One Microsoft Office Pro 2019 for Windows: Lifetime License + Windows 11 Pro Bundle (89% off) & Other Deals Up To 98% Off](https://www.javacodegeeks.com/wp-content/uploads/2012/12/jcg-logo.jpg){kind=logo}
_Andreas_Prott_Alamy.jpg?width=1280&auto=webp&quality=80&disable=upscale#)
![What features do you get with Gemini Advanced? [April 2025]](https://i0.wp.com/9to5google.com/wp-content/uploads/sites/4/2024/02/gemini-advanced-cover.jpg?resize=1200%2C628&quality=82&strip=all&ssl=1)
![Apple Shares Official Trailer for 'Long Way Home' Starring Ewan McGregor and Charley Boorman [Video]](https://www.iclarified.com/images/news/97069/97069/97069-640.jpg)
![Apple Watch Series 10 Back On Sale for $299! [Lowest Price Ever]](https://www.iclarified.com/images/news/96657/96657/96657-640.jpg)
![EU Postpones Apple App Store Fines Amid Tariff Negotiations [Report]](https://www.iclarified.com/images/news/97068/97068/97068-640.jpg)
ToImage in PyTorch
Buy Me a Coffee☕ *My post explains OxfordIIITPet(). ToImage() can convert a PIL(Pillow library) Image, tensor or ndarray to an Image as shown below: *Memos: The 1st argument is img(Required-Type:PIL Image or tensor/ndarray(int/float/complex/bool)): *Memos: A tensor must be 2D or more D. A ndarray must be 0D to 3D. Don't use img=. v2 is recommended to use according to V1 or V2? Which one should I use?. from torchvision.datasets import OxfordIIITPet from torchvision.transforms.v2 import ToImage ToImage() # ToImage() origin_data = OxfordIIITPet( # It's PIL Image. root="data", transform=None ) Image_data = OxfordIIITPet( root="data", transform=ToImage() ) Image_data # Dataset OxfordIIITPet # Number of datapoints: 3680 # Root location: data # StandardTransform # Transform: ToImage() Image_data[0] # (Image([[[37, 35, 36, ..., 247, 249, 249], # [35, 35, 37, ..., 246, 248, 249], # ..., # [28, 28, 27, ..., 59, 65, 76]], # [[20, 18, 19, ..., 248, 248, 248], # [18, 18, 20, ..., 247, 247, 248], # ..., # [27, 27, 27, ..., 94, 106, 117]], # [[12, 10, 11, ..., 253, 253, 253], # [10, 10, 12, ..., 251, 252, 253], # ..., # [35, 35, 35, ..., 214, 232, 223]]], dtype=torch.uint8,), 0) Image_data[0][0].size() # torch.Size([3, 500, 394]) Image_data[0][0] # Image([[[37, 35, 36, ..., 247, 249, 249], # [35, 35, 37, ..., 246, 248, 249], # ..., # [28, 28, 27, ..., 59, 65, 76]], # [[20, 18, 19, ..., 248, 248, 248], # [18, 18, 20, ..., 247, 247, 248], # ..., # [27, 27, 27, ..., 94, 106, 117]], # [[12, 10, 11, ..., 253, 253, 253], # [10, 10, 12, ..., 251, 252, 253], # ..., # [35, 35, 35, ..., 214, 232, 223]]], dtype=torch.uint8,) Image_data[0][1] # 0 import matplotlib.pyplot as plt plt.imshow(X=Image_data[0][0]) # TypeError: Invalid shape (3, 500, 394) for image data ti = ToImage() ti(origin_data[0][0]) # Image([[[37, 35, 36, ..., 247, 249, 249], # [35, 35, 37, ..., 246, 248, 249], # ..., # [28, 28, 27, ..., 59, 65, 76]], # [[20, 18, 19, ..., 248, 248, 248], # [18, 18, 20, ..., 247, 247, 248], # ..., # [27, 27, 27, ..., 94, 106, 117]], # [[12, 10, 11, ..., 253, 253, 253], # [10, 10, 12, ..., 251, 252, 253], # ..., # [35, 35, 35, ..., 214, 232, 223]]], dtype=torch.uint8,) plt.imshow(ti(origin_data[0][0])) # TypeError: Invalid shape (3, 500, 394) for image data ti(torch.tensor([[0, 1, 2]])) # Image([[[0, 1, 2]]],) ti(np.array([[0, 1, 2]])) # Image([[[0, 1, 2]]], dtype=torch.int32,)
*My post explains OxfordIIITPet().
ToImage() can convert a PIL(Pillow library) Image, tensor or ndarray to an Image as shown below:
*Memos:
- The 1st argument is
img(Required-Type:PIL Imageortensor/ndarray(int/float/complex/bool)): *Memos:- A tensor must be 2D or more D.
- A ndarray must be 0D to 3D.
- Don't use
img=.
-
v2is recommended to use according to V1 or V2? Which one should I use?.
from torchvision.datasets import OxfordIIITPet
from torchvision.transforms.v2 import ToImage
ToImage()
# ToImage()
origin_data = OxfordIIITPet( # It's PIL Image.
root="data",
transform=None
)
Image_data = OxfordIIITPet(
root="data",
transform=ToImage()
)
Image_data
# Dataset OxfordIIITPet
# Number of datapoints: 3680
# Root location: data
# StandardTransform
# Transform: ToImage()
Image_data[0]
# (Image([[[37, 35, 36, ..., 247, 249, 249],
# [35, 35, 37, ..., 246, 248, 249],
# ...,
# [28, 28, 27, ..., 59, 65, 76]],
# [[20, 18, 19, ..., 248, 248, 248],
# [18, 18, 20, ..., 247, 247, 248],
# ...,
# [27, 27, 27, ..., 94, 106, 117]],
# [[12, 10, 11, ..., 253, 253, 253],
# [10, 10, 12, ..., 251, 252, 253],
# ...,
# [35, 35, 35, ..., 214, 232, 223]]], dtype=torch.uint8,), 0)
Image_data[0][0].size()
# torch.Size([3, 500, 394])
Image_data[0][0]
# Image([[[37, 35, 36, ..., 247, 249, 249],
# [35, 35, 37, ..., 246, 248, 249],
# ...,
# [28, 28, 27, ..., 59, 65, 76]],
# [[20, 18, 19, ..., 248, 248, 248],
# [18, 18, 20, ..., 247, 247, 248],
# ...,
# [27, 27, 27, ..., 94, 106, 117]],
# [[12, 10, 11, ..., 253, 253, 253],
# [10, 10, 12, ..., 251, 252, 253],
# ...,
# [35, 35, 35, ..., 214, 232, 223]]], dtype=torch.uint8,)
Image_data[0][1]
# 0
import matplotlib.pyplot as plt
plt.imshow(X=Image_data[0][0])
# TypeError: Invalid shape (3, 500, 394) for image data
ti = ToImage()
ti(origin_data[0][0])
# Image([[[37, 35, 36, ..., 247, 249, 249],
# [35, 35, 37, ..., 246, 248, 249],
# ...,
# [28, 28, 27, ..., 59, 65, 76]],
# [[20, 18, 19, ..., 248, 248, 248],
# [18, 18, 20, ..., 247, 247, 248],
# ...,
# [27, 27, 27, ..., 94, 106, 117]],
# [[12, 10, 11, ..., 253, 253, 253],
# [10, 10, 12, ..., 251, 252, 253],
# ...,
# [35, 35, 35, ..., 214, 232, 223]]], dtype=torch.uint8,)
plt.imshow(ti(origin_data[0][0]))
# TypeError: Invalid shape (3, 500, 394) for image data
ti(torch.tensor([[0, 1, 2]]))
# Image([[[0, 1, 2]]],)
ti(np.array([[0, 1, 2]]))
# Image([[[0, 1, 2]]], dtype=torch.int32,)
