videomae-large-finetuned-kinetics-finetuned-videomae-large-kitchen

steveice/videomae-large-finetuned-kinetics-finetuned-videomae-large-kitchen

videomae-large-finetuned-kinetics-finetuned-videomae-large-kitchen is a video classification model from steveice. 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

1% of all-time downloads

All-time downloads

338

Public

Repo size

62 GB

Likes

Public

Hugging Face

Repo makeup

Click a slice to open those files.

.bin1.2 GB · 100%

At a glance

Task: Video Classification
Library: transformers
License: cc-by-nc-4.0
Model type: videomae
Access: Public
Created: Sep 20, 2023
Updated: Sep 21, 2023
SHA: adf14b88

Base models

MCG-NJU/videomae-large-finetuned-kinetics

Model card

From the Hugging Face model README

videomae-large-finetuned-kinetics-finetuned-videomae-large-kitchen

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

Loss: 0.6309
Accuracy: 0.8900

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: 11100

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy
3.5158	0.02	222	3.6067	0.0588
2.8571	1.02	444	3.1445	0.3014
1.8854	2.02	666	2.3644	0.4607
1.5533	3.02	888	1.7967	0.5621
1.3935	4.02	1110	1.3755	0.6502
1.1722	5.02	1332	1.2232	0.7109
0.2896	6.02	1554	1.2859	0.6256
0.3166	7.02	1776	1.2910	0.6720
0.6902	8.02	1998	1.2702	0.6995
0.4193	9.02	2220	1.2087	0.7137
0.1889	10.02	2442	1.0500	0.7611
0.4502	11.02	2664	1.1647	0.7118
0.7703	12.02	2886	1.1037	0.7242
0.0957	13.02	3108	1.0967	0.7706
0.3202	14.02	3330	1.0479	0.7545
0.3634	15.02	3552	1.0714	0.8057
0.3883	16.02	3774	1.2323	0.7498
0.0322	17.02	3996	1.0504	0.7848
0.5108	18.02	4218	1.1356	0.7915
0.309	19.02	4440	1.1409	0.7592
0.56	20.02	4662	1.0828	0.7915
0.3675	21.02	4884	0.9154	0.8123
0.0076	22.02	5106	1.0974	0.8133
0.0451	23.02	5328	1.0361	0.8152
0.2558	24.02	5550	0.7830	0.8237
0.0125	25.02	5772	0.8728	0.8171
0.4184	26.02	5994	0.8413	0.8265
0.2566	27.02	6216	1.0644	0.8009
0.1257	28.02	6438	0.8641	0.8265
0.1326	29.02	6660	0.8444	0.8417
0.0436	30.02	6882	0.8615	0.8322
0.0408	31.02	7104	0.8075	0.8332
0.0316	32.02	7326	0.8699	0.8341
0.2235	33.02	7548	0.8151	0.8455
0.0079	34.02	7770	0.8099	0.8550
0.001	35.02	7992	0.8640	0.8370
0.0007	36.02	8214	0.7146	0.8483
0.464	37.02	8436	0.7917	0.8464
0.0005	38.02	8658	0.7239	0.8531
0.0004	39.02	8880	0.7702	0.8701
0.1705	40.02	9102	0.7543	0.8521
0.0039	41.02	9324	0.7456	0.8673
0.0168	42.02	9546	0.7255	0.8730
0.2615	43.02	9768	0.7453	0.8758
0.0004	44.02	9990	0.6824	0.8806
0.236	45.02	10212	0.6624	0.8825
0.0007	46.02	10434	0.6727	0.8815
0.0004	47.02	10656	0.6478	0.8863
0.268	48.02	10878	0.6309	0.8900
0.0025	49.02	11100	0.6284	0.8900

Framework versions

Transformers 4.33.2
Pytorch 1.12.1+cu113
Datasets 2.14.5
Tokenizers 0.13.3

Task: Video Classification
Library: transformers
Type: videomae
License: cc-by-nc-4.0
Created: Sep 20, 2023
Updated: Sep 21, 2023