videomae-base-finetuned-kinetics-finetuned-freeway-subset

peter881122/videomae-base-finetuned-kinetics-finetuned-freeway-subset

videomae-base-finetuned-kinetics-finetuned-freeway-subset is a video classification model from peter881122. 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 cc-by-nc-4.0.

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

Downloads · 30 days

5% of all-time downloads

All-time downloads

262

Public

Parameters

86.2M

17.2 GB on disk

Likes

Public

Hugging Face

Repo makeup

Click a slice to open those files.

.safetensors345 MB · 100%

At a glance

Task: Video Classification
Library: transformers
License: cc-by-nc-4.0
Model type: videomae
Access: Public
Created: Jun 9, 2024
Updated: Jun 9, 2024
SHA: 329c9528

Base models

MCG-NJU/videomae-base-finetuned-kinetics

Model card

From the Hugging Face model README

videomae-base-finetuned-kinetics-finetuned-freeway-subset

This model is a fine-tuned version of MCG-NJU/videomae-base-finetuned-kinetics on an unknown dataset. It achieves the following results on the evaluation set:

Loss: 0.0016
Accuracy: 1.0

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: 5
eval_batch_size: 5
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: 1800

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy
0.6551	0.02	36	0.7171	0.5
0.6085	1.02	72	0.7057	0.5
0.5876	2.02	108	0.5834	0.75
0.5757	3.02	144	0.5360	0.7143
0.7017	4.02	180	0.4589	0.7143
0.5681	5.02	216	0.3667	0.8214
0.3418	6.02	252	0.2312	0.9286
0.6408	7.02	288	0.2724	0.8929
0.3846	8.02	324	0.1288	0.9643
0.1551	9.02	360	0.6198	0.8214
0.4879	10.02	396	0.3241	0.8571
0.0982	11.02	432	0.1815	0.9286
0.112	12.02	468	0.2504	0.9643
0.3627	13.02	504	0.2357	0.9643
0.2329	14.02	540	0.6101	0.8571
0.141	15.02	576	0.0218	1.0
0.1755	16.02	612	0.0791	0.9643
0.079	17.02	648	0.1167	0.9643
0.0859	18.02	684	0.0118	1.0
0.0131	19.02	720	0.0020	1.0
0.0014	20.02	756	0.0054	1.0
0.0008	21.02	792	0.0841	0.9286
0.0024	22.02	828	0.0852	0.9643
0.1803	23.02	864	0.0005	1.0
0.0001	24.02	900	0.0379	0.9643
0.0012	25.02	936	0.0705	0.9643
0.0018	26.02	972	0.0010	1.0
0.0007	27.02	1008	0.0210	1.0
0.0028	28.02	1044	0.0030	1.0
0.0465	29.02	1080	0.0005	1.0
0.0004	30.02	1116	0.0011	1.0
0.0016	31.02	1152	0.0005	1.0
0.0	32.02	1188	0.0012	1.0
0.0002	33.02	1224	0.0001	1.0
0.0315	34.02	1260	0.0027	1.0
0.0253	35.02	1296	0.0003	1.0
0.0011	36.02	1332	0.0022	1.0
0.0001	37.02	1368	0.0006	1.0
0.0007	38.02	1404	0.0120	1.0
0.0001	39.02	1440	0.1001	0.9643
0.0005	40.02	1476	0.0331	0.9643
0.0009	41.02	1512	0.0418	0.9643
0.0035	42.02	1548	0.0761	0.9643
0.0001	43.02	1584	0.0020	1.0
0.0001	44.02	1620	0.0020	1.0
0.0	45.02	1656	0.0010	1.0
0.0001	46.02	1692	0.0009	1.0
0.0005	47.02	1728	0.0012	1.0
0.0001	48.02	1764	0.0015	1.0
0.0002	49.02	1800	0.0016	1.0

Framework versions

Transformers 4.42.0.dev0
Pytorch 2.1.1
Datasets 2.19.2
Tokenizers 0.19.1

Task: Video Classification
Library: transformers
Type: videomae
License: cc-by-nc-4.0
Created: Jun 9, 2024
Updated: Jun 9, 2024