videomae-base-finetuned-ucf101-subset-finetuned

ali5341/videomae-base-finetuned-ucf101-subset-finetuned

videomae-base-finetuned-ucf101-subset-finetuned is a video classification model from ali5341. 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.

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

Downloads · 30 days

2% of all-time downloads

All-time downloads

280

Public

Repo size

1.7 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
Model type: videomae
Access: Public
Created: Oct 11, 2023
Updated: Oct 16, 2023
SHA: 966958c3

Model card

From the Hugging Face model README

videomae-base-finetuned-ucf101-subset-finetuned

This model was trained from scratch on an unknown dataset. It achieves the following results on the evaluation set:

Loss: 0.9147
Accuracy: 0.7701

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: 29760

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy
1.537	0.2	5952	1.8361	0.4807
0.8794	1.2	11904	1.6076	0.5795
0.3028	2.2	17856	1.5198	0.6318
0.2322	3.2	23808	0.9564	0.7515
0.4151	4.2	29760	0.9741	0.7595

Framework versions

Transformers 4.33.2
Pytorch 2.0.1+cu117
Datasets 2.14.5
Tokenizers 0.13.3

Task: Video Classification
Library: transformers
Type: videomae
Created: Oct 11, 2023
Updated: Oct 16, 2023