Skip to content

torchvision.transforms.functional_tensor in video classification example #602

Open
@LeninGF

Description

@LeninGF

When executing the following cell where some video transforms are required

`import pytorchvideo.data

from pytorchvideo.transforms import (
ApplyTransformToKey,
Normalize,
RandomShortSideScale,
RemoveKey,
ShortSideScale,
UniformTemporalSubsample,
)

from torchvision.transforms import (
Compose,
Lambda,
RandomCrop,
RandomHorizontalFlip,
Resize,
)`
The following error shows


ModuleNotFoundError Traceback (most recent call last)
/tmp/ipython-input-16-3436037420.py in <cell line: 0>()
1 import pytorchvideo.data
2
----> 3 from pytorchvideo.transforms import (
4 ApplyTransformToKey,
5 Normalize,

2 frames
/usr/local/lib/python3.11/dist-packages/pytorchvideo/transforms/augmentations.py in
7 import torch
8 import torchvision
----> 9 import torchvision.transforms.functional_tensor as F_t
10 from torchvision.transforms.functional import InterpolationMode
11

ModuleNotFoundError: No module named 'torchvision.transforms.functional_tensor'


NOTE: If your import is failing due to a missing package, you can
manually install dependencies using either !pip or !apt.

To view examples of installing some common dependencies, click the
"Open Examples" button below.

Metadata

Metadata

Assignees

No one assigned

    Labels

    No labels
    No labels

    Type

    No type

    Projects

    No projects

    Milestone

    No milestone

    Relationships

    None yet

    Development

    No branches or pull requests

    Issue actions