vivit-b-16x2-kinetics400-ft-76388

Temo27Anas/vivit-b-16x2-kinetics400-ft-76388

vivit-b-16x2-kinetics400-ft-76388 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

322

Public

Parameters

37.9M

7.6 GB on disk

Likes

Public

Hugging Face

Repo makeup

Click a slice to open those files.

.safetensors152 MB · 100%

At a glance

Task: Video Classification
Library: transformers
License: mit
Model type: vivit
Access: Public
Created: Jul 11, 2024
Updated: Jul 12, 2024
SHA: faf91a6e

Base models

google/vivit-b-16x2-kinetics400

Model card

From the Hugging Face model README

vivit-b-16x2-kinetics400-ft-76388

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: 0.9924
Accuracy: 0.5595

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
1.1083	0.0202	111	1.1112	0.3347
1.0789	1.0202	222	1.0576	0.4259
1.0767	2.0202	333	1.0863	0.4246
1.1114	3.0202	444	1.1061	0.3704
1.0832	4.0202	555	1.0536	0.4193
1.0622	5.0202	666	1.0720	0.4577
1.0874	6.0202	777	1.0304	0.4709
0.9742	7.0202	888	1.0340	0.4511
0.9848	8.0202	999	1.0367	0.4669
1.12	9.0202	1110	1.0269	0.4193
1.0484	10.0202	1221	1.0105	0.4511
0.9445	11.0202	1332	1.0052	0.4881
1.032	12.0202	1443	1.0365	0.4524
0.987	13.0202	1554	1.0019	0.5106
1.0797	14.0202	1665	1.0128	0.4656
0.9196	15.0202	1776	1.0431	0.5013
1.0727	16.0202	1887	1.0016	0.5344
0.9481	17.0202	1998	0.9983	0.5265
0.9034	18.0202	2109	1.0221	0.5013
0.8569	19.0202	2220	0.9825	0.5265
0.9256	20.0202	2331	0.9678	0.5397
1.0311	21.0202	2442	0.9574	0.5106
0.8651	22.0202	2553	1.0048	0.4987
0.9384	23.0202	2664	0.9717	0.5225
0.9545	24.0202	2775	0.9763	0.5172
0.9187	25.0202	2886	0.9628	0.5212
0.7953	26.0202	2997	0.9523	0.5265
0.8793	27.0202	3108	0.9977	0.5370
0.7897	28.0202	3219	0.9965	0.5317
0.8034	29.0202	3330	0.9272	0.5463
0.8469	30.0202	3441	0.9231	0.5384
0.79	31.0202	3552	0.9281	0.5728
0.8516	32.0202	3663	0.9310	0.5569
0.8138	33.0202	3774	0.9582	0.5675
0.8322	34.0202	3885	0.9741	0.5622
0.8064	35.0202	3996	0.9573	0.5754
0.8767	36.0202	4107	0.9290	0.5714
0.7978	37.0202	4218	0.9449	0.5728
0.8113	38.0202	4329	0.9493	0.5780
0.8065	39.0202	4440	0.9015	0.5926
0.7989	40.0202	4551	0.9139	0.5886
0.6323	41.0202	4662	0.9004	0.5992
0.6847	42.0202	4773	0.9083	0.6124
0.7711	43.0202	4884	0.9023	0.5979
0.5815	44.0202	4995	0.9247	0.6058
0.8821	45.0202	5106	0.9071	0.6058
0.7436	46.0202	5217	0.8924	0.6085
0.6863	47.0202	5328	0.8965	0.6111
0.7035	48.0202	5439	0.8941	0.6045
0.6348	49.0111	5500	0.8950	0.6124

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 11, 2024
Updated: Jul 12, 2024