videomae-base-ipm_all_videos

rickysk/videomae-base-ipm_all_videos

videomae-base-ipm_all_videos is a video classification model from rickysk. 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

2% of all-time downloads

All-time downloads

554

Public

Repo size

21 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: Jun 2, 2023
Updated: Jul 12, 2023
SHA: 0a2a0c60

Spaces

Model card

From the Hugging Face model README

videomae-base-ipm_all_videos

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: 0.4713
Accuracy: 0.8559

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: 4
eval_batch_size: 4
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: 3600

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy
1.7831	0.02	60	1.8965	0.1186
1.7706	1.02	120	1.9115	0.1186
1.7497	2.02	180	1.8985	0.1356
1.5214	3.02	240	1.4807	0.3475
1.1458	4.02	300	1.7024	0.3559
1.1587	5.02	360	1.6771	0.2966
0.9256	6.02	420	1.6428	0.3814
1.265	7.02	480	1.5169	0.5
0.8271	8.02	540	1.0310	0.5847
0.6011	9.02	600	1.1739	0.5508
0.9542	10.02	660	1.3323	0.5424
1.1231	11.02	720	1.4279	0.4915
0.728	12.02	780	2.1913	0.4661
0.5991	13.02	840	1.1088	0.6271
1.0613	14.02	900	1.3781	0.5
0.9121	15.02	960	1.4224	0.5424
0.6083	16.02	1020	0.8779	0.6695
0.408	17.02	1080	0.8512	0.7119
0.3741	18.02	1140	0.8884	0.7034
0.8906	19.02	1200	1.1396	0.6017
0.568	20.02	1260	0.7380	0.6949
0.4135	21.02	1320	0.7966	0.6525
0.5492	22.02	1380	0.9815	0.6780
0.902	23.02	1440	0.9267	0.6441
0.6889	24.02	1500	1.4313	0.5763
0.788	25.02	1560	1.2156	0.5678
0.7324	26.02	1620	0.8015	0.6780
0.6733	27.02	1680	0.8682	0.6949
0.498	28.02	1740	0.8767	0.6949
0.5558	29.02	1800	0.9248	0.6780
0.5583	30.02	1860	1.1784	0.6356
0.3905	31.02	1920	1.0646	0.6864
0.3728	32.02	1980	0.8338	0.7797
0.5988	33.02	2040	0.8339	0.7542
0.3636	34.02	2100	0.7577	0.7627
0.505	35.02	2160	1.0310	0.6864
0.5344	36.02	2220	0.6345	0.7458
0.2814	37.02	2280	0.9954	0.7119
0.2187	38.02	2340	0.7515	0.7797
0.4876	39.02	2400	0.8392	0.7627
0.1148	40.02	2460	0.6182	0.8729
0.3139	41.02	2520	1.1651	0.6949
0.2638	42.02	2580	0.8299	0.7797
0.1989	43.02	2640	0.5943	0.8220
0.5473	44.02	2700	0.6514	0.8644
0.3921	45.02	2760	0.6708	0.8220
0.1756	46.02	2820	0.5431	0.8305
0.1089	47.02	2880	0.6040	0.8136
0.3616	48.02	2940	0.5281	0.8475
0.2752	49.02	3000	0.6430	0.8305
0.3847	50.02	3060	0.5640	0.8644
0.0909	51.02	3120	0.5178	0.8559
0.3426	52.02	3180	0.3770	0.8983
0.0516	53.02	3240	0.5365	0.8390
0.2133	54.02	3300	0.5919	0.8475
0.1382	55.02	3360	0.5112	0.8390
0.1803	56.02	3420	0.5173	0.8475
0.1352	57.02	3480	0.5207	0.8390
0.4445	58.02	3540	0.4763	0.8559
0.3249	59.02	3600	0.4713	0.8559

Framework versions

Transformers 4.29.1
Pytorch 2.0.1+cu117
Datasets 2.12.0
Tokenizers 0.13.3

Task: Video Classification
Library: transformers
Type: videomae
License: cc-by-nc-4.0
Created: Jun 2, 2023
Updated: Jul 12, 2023