Torchvision

Latest version: v0.20.1

Safety actively analyzes 688087 Python packages for vulnerabilities to keep your Python projects secure.

Scan your dependencies

Page 3 of 23

97.48

96.878

96.864

</td>
<td>
<ul>

96.816

</td>
<td>
<ul>

96.722

</td>
<td>
<p style="text-align: right">
-</p>

</td>
</tr>
</table>


We would like to thank [Ren Pang](https://github.com/ain-soph) and [Teodor Poncu](https://github.com/TeodorPoncu) for contributing the 2 models to torchvision.


[[BETA](https://pytorch.org/blog/pytorch-feature-classification-changes/#beta)] Video Classification Model

We added two new video classification models, MViT and S3D. MViT is a state of the art video classification transformer model which has 80.757% accuracy on Kinetics400 dataset, while S3D is a relatively small model with good accuracy for its size. These models can be used as follows:


python
import torch
from torchvision.models.video import *

video = torch.rand(3, 32, 800, 600)
model = mvit_v2_s(weights="DEFAULT")
model = s3d(weights="DEFAULT")
model.eval()
prediction = model(images)



Here is the table showing the accuracy of the new video classification models tested in the Kinetics400 dataset.


<table>
<tr>
<td><strong>Model</strong>
</td>
<td><strong>Acc1</strong>
</td>
<td><strong>Acc5</strong>
</td>
</tr>
<tr>
<td>mvit_v1_b
</td>
<td><p style="text-align: right">

96.454

Page 3 of 23

© 2024 Safety CLI Cybersecurity Inc. All Rights Reserved.