videomae-base-action_detection

athmurikarthik/videomae-base-action_detection

videomae-base-action_detection is a video classification model from athmurikarthik. 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

26% of all-time downloads

All-time downloads

Public

Parameters

86.2M

20.7 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: Feb 6, 2024
Updated: Feb 7, 2024
SHA: 6c9781fe

Base models

MCG-NJU/videomae-base

Model card

From the Hugging Face model README

videomae-base-action_detection

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

Loss: 1.2662
Accuracy: 0.7243

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: 2
eval_batch_size: 2
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: 15200

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy
1.0956	0.02	305	1.3464	0.4774
0.683	1.02	610	2.3774	0.3704
0.5519	2.02	915	2.1501	0.3128
1.5863	3.02	1220	2.7112	0.2387
0.8028	4.02	1525	1.5204	0.7037
1.1797	5.02	1830	2.6479	0.2963
1.185	6.02	2135	0.8982	0.7860
0.9516	7.02	2440	1.2030	0.6008
0.5755	8.02	2745	0.8003	0.8189
0.6815	9.02	3050	2.3653	0.4198
1.1649	10.02	3355	3.0645	0.4403
1.1024	11.02	3660	2.4187	0.4321
1.1158	12.02	3965	2.2631	0.5597
0.2375	13.02	4270	2.2977	0.5432
0.7445	14.02	4575	1.0086	0.7860
0.6555	15.02	4880	0.7161	0.8560
0.8807	16.02	5185	1.2404	0.6584
1.0477	17.02	5490	1.6849	0.6173
0.498	18.02	5795	2.0557	0.5844
0.5536	19.02	6100	2.0703	0.5967
0.2232	20.02	6405	2.7690	0.4856
0.5589	21.02	6710	0.9549	0.7243
0.3377	22.02	7015	0.6488	0.8189
0.7096	23.02	7320	1.6638	0.5556
0.1201	24.02	7625	1.6283	0.5761
0.136	25.02	7930	1.4397	0.5926
0.2558	26.02	8235	1.7421	0.5350
0.3245	27.02	8540	1.2982	0.6132
0.0029	28.02	8845	1.0594	0.7202
0.3272	29.02	9150	1.0833	0.8272
0.0841	30.02	9455	1.3230	0.5926
0.5595	31.02	9760	2.5545	0.5844
0.0837	32.02	10065	1.5960	0.6296
0.0127	33.02	10370	1.8149	0.5720
0.3622	34.02	10675	2.4455	0.4938
0.0006	35.02	10980	1.6700	0.6461
0.0027	36.02	11285	2.2488	0.5720
0.0544	37.02	11590	2.6388	0.5514
0.2504	38.02	11895	1.5352	0.6379
0.0149	39.02	12200	2.2851	0.5391
0.4035	40.02	12505	1.8876	0.5556
0.0008	41.02	12810	2.4479	0.5473
0.3176	42.02	13115	2.0729	0.6049
0.0007	43.02	13420	1.5171	0.6255
0.3948	44.02	13725	1.4067	0.6132
0.0016	45.02	14030	1.0621	0.7325
0.2173	46.02	14335	1.5515	0.6132
0.0007	47.02	14640	1.2523	0.7284
0.2819	48.02	14945	1.5618	0.6461
0.0004	49.02	15200	1.2662	0.7243

Framework versions

Transformers 4.37.2
Pytorch 2.1.2+cu121
Datasets 2.16.1
Tokenizers 0.15.1

Task: Video Classification
Library: transformers
Type: videomae
License: cc-by-nc-4.0
Created: Feb 6, 2024
Updated: Feb 7, 2024