swinv2-tiny-patch4-window8-256-dmae-humeda-DAV71

RobertoSonic/swinv2-tiny-patch4-window8-256-dmae-humeda-DAV71

swinv2-tiny-patch4-window8-256-dmae-humeda-DAV71 is a image classification model from RobertoSonic. Use it when you need a label for an image. It is set up for transformers. The card lists the license as apache-2.0.

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

Downloads · 30 days

18% of all-time downloads

All-time downloads

Public

Parameters

27.6M

6.2 GB on disk

Likes

Public

Hugging Face

Repo makeup

Click a slice to open those files.

.safetensors110 MB · 100%

At a glance

Task: Image Classification
Library: transformers
License: apache-2.0
Model type: swinv2
Access: Public
Created: May 23, 2025
Updated: May 23, 2025
SHA: e3fa80ad

Base models

microsoft/swinv2-tiny-patch4-window8-256

Model card

From the Hugging Face model README

swinv2-tiny-patch4-window8-256-dmae-humeda-DAV71

This model is a fine-tuned version of microsoft/swinv2-tiny-patch4-window8-256 on an unknown dataset. It achieves the following results on the evaluation set:

Loss: 0.5977
Accuracy: 0.9029

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: 6e-05
train_batch_size: 16
eval_batch_size: 16
seed: 42
gradient_accumulation_steps: 4
total_train_batch_size: 64
optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
lr_scheduler_type: linear
lr_scheduler_warmup_ratio: 0.1
num_epochs: 60
mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy
1.1246	1.0	15	1.0559	0.4171
0.8728	2.0	30	0.7460	0.6971
0.6663	3.0	45	0.4563	0.8057
0.4632	4.0	60	0.4076	0.8286
0.4278	5.0	75	0.3670	0.84
0.361	6.0	90	0.3624	0.8457
0.3742	7.0	105	0.3504	0.8629
0.3313	8.0	120	0.2962	0.8629
0.2977	9.0	135	0.3321	0.8686
0.2589	10.0	150	0.3425	0.8629
0.2477	11.0	165	0.3982	0.8457
0.2187	12.0	180	0.5954	0.8514
0.2342	13.0	195	0.3745	0.8514
0.2444	14.0	210	0.5220	0.8629
0.2067	15.0	225	0.4433	0.8457
0.1882	16.0	240	0.3937	0.8629
0.199	17.0	255	0.5103	0.8629
0.1565	18.0	270	0.3608	0.8857
0.2068	19.0	285	0.3679	0.88
0.194	20.0	300	0.5581	0.8457
0.1654	21.0	315	0.5074	0.8686
0.1986	22.0	330	0.4395	0.88
0.1257	23.0	345	0.4293	0.8686
0.1976	24.0	360	0.4932	0.8571
0.1563	25.0	375	0.4254	0.8857
0.0985	26.0	390	0.5097	0.8686
0.1238	27.0	405	0.7264	0.8514
0.1577	28.0	420	0.4827	0.8571
0.1271	29.0	435	0.5305	0.8686
0.1002	30.0	450	0.5888	0.8629
0.1268	31.0	465	0.6433	0.8571
0.1153	32.0	480	0.8394	0.8343
0.1191	33.0	495	0.7475	0.84
0.1184	34.0	510	0.4884	0.8743
0.1332	35.0	525	0.5834	0.8857
0.1071	36.0	540	0.6279	0.8571
0.0886	37.0	555	0.6999	0.8629
0.0744	38.0	570	0.7295	0.8686
0.1274	39.0	585	0.6137	0.8914
0.0795	40.0	600	0.5706	0.8743
0.0962	41.0	615	0.6100	0.8857
0.094	42.0	630	0.6149	0.8743
0.0945	43.0	645	0.5689	0.88
0.0584	44.0	660	0.7019	0.8743
0.0676	45.0	675	0.6934	0.88
0.0763	46.0	690	0.6047	0.8914
0.0762	47.0	705	0.6064	0.88
0.0696	48.0	720	0.7336	0.8686
0.0555	49.0	735	0.6599	0.8743
0.0572	50.0	750	0.5977	0.9029
0.0648	51.0	765	0.6257	0.88
0.0705	52.0	780	0.6654	0.8857
0.0646	53.0	795	0.6813	0.8686
0.0795	54.0	810	0.6209	0.8743
0.0828	55.0	825	0.6457	0.8743
0.0674	56.0	840	0.6521	0.88

Framework versions

Transformers 4.51.3
Pytorch 2.6.0+cu124
Datasets 2.19.0
Tokenizers 0.21.1

Task: Image Classification
Library: transformers
Type: swinv2
License: apache-2.0
Created: May 23, 2025
Updated: May 23, 2025