vivit-b-16x2-kinetics400-ft-92397

Temo27Anas/vivit-b-16x2-kinetics400-ft-92397

vivit-b-16x2-kinetics400-ft-92397 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

25% of all-time downloads

All-time downloads

Public

Parameters

35.5M

7.1 GB on disk

Likes

Public

Hugging Face

Repo makeup

Click a slice to open those files.

.safetensors142 MB · 100%

At a glance

Task: Video Classification
Library: transformers
License: mit
Model type: vivit
Access: Public
Created: Jul 10, 2024
Updated: Jul 11, 2024
SHA: eadf107f

Base models

google/vivit-b-16x2-kinetics400

Model card

From the Hugging Face model README

vivit-b-16x2-kinetics400-ft-92397

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: 1.1332
Accuracy: 0.3386

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: 5500

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy
1.1076	0.0202	111	1.1240	0.3333
1.1466	1.0202	222	1.1166	0.3333
1.1022	2.0202	333	1.1221	0.3333
1.109	3.0202	444	1.1170	0.3333
1.1007	4.0202	555	1.1375	0.3333
1.1146	5.0202	666	1.1004	0.3386
1.1575	6.0202	777	1.1249	0.3333
1.0851	7.0202	888	1.1254	0.3439
1.1069	8.0202	999	1.1136	0.3333
1.0998	9.0202	1110	1.0945	0.3545
1.1289	10.0202	1221	1.0992	0.3439
1.0674	11.0202	1332	1.0957	0.3545
1.1144	12.0202	1443	1.1139	0.3228
1.0971	13.0202	1554	1.1089	0.3228
1.0704	14.0202	1665	1.1031	0.3333
1.1064	15.0202	1776	1.1003	0.3492
1.0782	16.0202	1887	1.1026	0.3386
1.1086	17.0202	1998	1.1091	0.3175
1.0911	18.0202	2109	1.0965	0.3386
1.0961	19.0202	2220	1.1108	0.3333
1.0967	20.0202	2331	1.1029	0.3175
1.0746	21.0202	2442	1.1127	0.3333
1.1076	22.0202	2553	1.0996	0.3492
1.0786	23.0202	2664	1.1138	0.3333
1.0819	24.0202	2775	1.0970	0.3651
1.1031	25.0202	2886	1.1135	0.3333
1.092	26.0202	2997	1.1050	0.3439
1.103	27.0202	3108	1.1039	0.3598
1.0903	28.0202	3219	1.1149	0.3333
1.1232	29.0202	3330	1.1062	0.3333
1.106	30.0202	3441	1.1124	0.3175
1.0607	31.0202	3552	1.1095	0.3333
1.0839	32.0202	3663	1.1083	0.3386
1.0867	33.0202	3774	1.1007	0.3545
1.0913	34.0202	3885	1.0996	0.3598
1.0567	35.0202	3996	1.0946	0.3386
1.0877	36.0202	4107	1.1004	0.3280
1.0828	37.0202	4218	1.1074	0.3228
1.131	38.0202	4329	1.0992	0.3122
1.0299	39.0202	4440	1.1035	0.3280
1.0864	40.0202	4551	1.0947	0.3386
1.0643	41.0202	4662	1.1006	0.3545
1.0687	42.0202	4773	1.1056	0.3280
1.0978	43.0202	4884	1.0907	0.3598
1.0273	44.0202	4995	1.0969	0.3439
1.0459	45.0202	5106	1.1021	0.3492
1.0561	46.0202	5217	1.1003	0.3386
1.0482	47.0202	5328	1.1028	0.3386
1.0916	48.0202	5439	1.1053	0.3545
1.0729	49.0111	5500	1.1055	0.3545

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 10, 2024
Updated: Jul 11, 2024