videomae-large-finetuned-kinetics-finetuned-engine-subset-R2-K400-20230418_3

steveice/videomae-large-finetuned-kinetics-finetuned-engine-subset-R2-K400-20230418_3

videomae-large-finetuned-kinetics-finetuned-engine-subset-R2-K400-20230418_3 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

3% of all-time downloads

All-time downloads

337

Public

Repo size

17.3 GB

Likes

Public

Hugging Face

Repo makeup

Click a slice to open those files.

.bin345 MB · 100%

At a glance

Task: Video Classification
Library: transformers
License: cc-by-nc-4.0
Model type: videomae
Access: Public
Created: Apr 18, 2023
Updated: Apr 19, 2023
SHA: 03180ed8

Model card

From the Hugging Face model README

videomae-large-finetuned-kinetics-finetuned-engine-subset-R2-K400-20230418_3

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: 3.1972
Accuracy: 0.2647

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: 6
eval_batch_size: 6
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: 2700

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy
2.5562	0.02	55	2.5746	0.0221
2.4543	1.02	110	2.5524	0.0956
2.1443	2.02	165	2.5214	0.1103
1.6604	3.02	220	2.6415	0.1397
1.5847	4.02	275	2.9843	0.0735
1.4657	5.02	330	2.7476	0.1471
1.0823	6.02	385	3.0872	0.1471
1.0672	7.02	440	2.9539	0.2206
0.7241	8.02	495	3.5364	0.1103
0.6532	9.02	550	3.1972	0.2647
0.6476	10.02	605	4.1289	0.0735
0.3725	11.02	660	4.4710	0.0588
0.7363	12.02	715	4.9241	0.0662
0.3136	13.02	770	4.8217	0.1176
0.3154	14.02	825	4.2717	0.1838
0.309	15.02	880	4.9466	0.0588
0.3094	16.02	935	5.5394	0.0147
0.3333	17.02	990	5.0940	0.0956
0.2299	18.02	1045	6.3148	0.0074
0.2257	19.02	1100	5.3869	0.0588
0.255	20.02	1155	6.4134	0.0147
0.2335	21.02	1210	6.1413	0.0441
0.3507	22.02	1265	6.2911	0.0074
0.1463	23.02	1320	6.5273	0.0074
0.193	24.02	1375	6.6533	0.0074
0.1167	25.02	1430	6.8094	0.0
0.1168	26.02	1485	6.7632	0.0
0.0511	27.02	1540	7.0046	0.0074
0.1336	28.02	1595	7.2877	0.0
0.1518	29.02	1650	7.3102	0.0
0.1972	30.02	1705	7.1632	0.0
0.0605	31.02	1760	7.2970	0.0
0.1633	32.02	1815	7.3427	0.0
0.1902	33.02	1870	7.4095	0.0
0.132	34.02	1925	7.3169	0.0
0.1226	35.02	1980	7.4196	0.0074
0.115	36.02	2035	7.3248	0.0074
0.1348	37.02	2090	7.1318	0.0
0.1684	38.02	2145	7.6482	0.0
0.0722	39.02	2200	7.5944	0.0074
0.1155	40.02	2255	7.5615	0.0
0.1425	41.02	2310	7.6454	0.0074
0.1552	42.02	2365	7.4774	0.0074
0.1078	43.02	2420	7.3991	0.0074
0.1169	44.02	2475	7.3240	0.0
0.1438	45.02	2530	7.4133	0.0
0.1227	46.02	2585	7.4592	0.0
0.0716	47.02	2640	7.5590	0.0
0.2077	48.02	2695	7.5708	0.0
0.0731	49.0	2700	7.5710	0.0

Framework versions

Transformers 4.26.1
Pytorch 1.12.1+cu113
Datasets 2.10.1
Tokenizers 0.13.2

Task: Video Classification
Library: transformers
Type: videomae
License: cc-by-nc-4.0
Created: Apr 18, 2023
Updated: Apr 19, 2023