vivit-b-16x2-kinetics400-ft-9811

Temo27Anas/vivit-b-16x2-kinetics400-ft-9811

vivit-b-16x2-kinetics400-ft-9811 is a video classification model from Temo27Anas. Use it for the video classification task on the model card, and read the license before you ship it in a product. It is set up for transformers. The card lists the license as mit.

should probably proofread and complete it, then remove this comment. --

Downloads · 30 days

5% of all-time downloads

All-time downloads

316

Public

Parameters

34M

544 MB on disk

Likes

Public

Hugging Face

Repo makeup

Click a slice to open those files.

.safetensors136 MB · 100%

At a glance

Task: Video Classification
Library: transformers
License: mit
Model type: vivit
Access: Public
Created: Jul 8, 2024
Updated: Jul 8, 2024
SHA: 49196423

Base models

google/vivit-b-16x2-kinetics400

Model card

From the Hugging Face model README

vivit-b-16x2-kinetics400-ft-9811

This model is a fine-tuned version of google/vivit-b-16x2-kinetics400 on an unknown dataset. It achieves the following results on the evaluation set:

Loss: 0.9429
Accuracy: 0.5767

Model description

More information needed

Intended uses & limitations

More information needed

Training and evaluation data

More information needed

Training procedure

Training hyperparameters

The following hyperparameters were used during training:

learning_rate: 5e-05
train_batch_size: 8
eval_batch_size: 8
seed: 42
optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
lr_scheduler_type: linear
lr_scheduler_warmup_ratio: 0.1
training_steps: 440

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy
1.0942	0.2523	111	1.1040	0.4392
1.0041	1.2523	222	0.9264	0.5608
0.9804	2.2523	333	0.8831	0.5979
0.79	3.2432	440	0.8656	0.6085

Framework versions

Transformers 4.41.2
Pytorch 1.13.0+cu117
Datasets 2.20.0
Tokenizers 0.19.1

Task: Video Classification
Library: transformers
Type: vivit
License: mit
Created: Jul 8, 2024
Updated: Jul 8, 2024