swinv2-tiny-patch4-window8-256-dmae-humeda-DAV56

RobertoSonic/swinv2-tiny-patch4-window8-256-dmae-humeda-DAV56

swinv2-tiny-patch4-window8-256-dmae-humeda-DAV56 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

13% of all-time downloads

All-time downloads

168

Public

Parameters

27.6M

4.6 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: Feb 10, 2025
Updated: Feb 10, 2025
SHA: d343064e

Base models

microsoft/swinv2-tiny-patch4-window8-256

Model card

From the Hugging Face model README

swinv2-tiny-patch4-window8-256-dmae-humeda-DAV56

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: 0.8748
Accuracy: 0.7308

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: 2e-05
train_batch_size: 32
eval_batch_size: 32
seed: 42
gradient_accumulation_steps: 4
total_train_batch_size: 128
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: cosine_with_restarts
lr_scheduler_warmup_ratio: 0.1
num_epochs: 45
mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy
No log	0.8421	4	1.5618	0.3269
No log	1.8421	8	1.5396	0.4423
1.7209	2.8421	12	1.5124	0.3077
1.7209	3.8421	16	1.4679	0.3269
1.7209	4.8421	20	1.4130	0.3462
1.5864	5.8421	24	1.3107	0.5385
1.5864	6.8421	28	1.2112	0.5385
1.5864	7.8421	32	1.1194	0.5962
1.2629	8.8421	36	1.0422	0.5962
1.2629	9.8421	40	0.9706	0.6538
1.2629	10.8421	44	0.9638	0.6538
0.951	11.8421	48	0.9906	0.6154
0.951	12.8421	52	0.9890	0.5962
0.951	13.8421	56	0.9110	0.6538
0.7947	14.8421	60	0.9282	0.6731
0.7947	15.8421	64	0.9315	0.6538
0.7947	16.8421	68	0.9230	0.6154
0.7143	17.8421	72	0.9068	0.6538
0.7143	18.8421	76	0.8997	0.6154
0.7143	19.8421	80	0.8648	0.6923
0.6329	20.8421	84	0.8624	0.6538
0.6329	21.8421	88	0.8737	0.6154
0.6329	22.8421	92	0.8636	0.6731
0.5508	23.8421	96	0.8545	0.6538
0.5508	24.8421	100	0.8617	0.6731
0.5508	25.8421	104	0.8635	0.6346
0.5009	26.8421	108	0.8650	0.6346
0.5009	27.8421	112	0.8638	0.6538
0.5009	28.8421	116	0.8730	0.6538
0.5286	29.8421	120	0.8886	0.6346
0.5286	30.8421	124	0.8827	0.6538
0.5286	31.8421	128	0.8748	0.7308
0.4559	32.8421	132	0.8671	0.7115
0.4559	33.8421	136	0.8727	0.6731
0.4559	34.8421	140	0.8755	0.7115
0.4704	35.8421	144	0.8760	0.7308
0.4704	36.8421	148	0.8786	0.7308
0.4704	37.8421	152	0.8781	0.7308
0.4582	38.8421	156	0.8771	0.7308
0.4582	39.8421	160	0.8754	0.7308
0.4582	40.8421	164	0.8741	0.7308
0.4538	41.8421	168	0.8742	0.7308
0.4538	42.8421	172	0.8740	0.7308
0.4538	43.8421	176	0.8740	0.7308
0.4476	44.8421	180	0.8741	0.7308

Framework versions

Transformers 4.48.2
Pytorch 2.5.1+cu124
Datasets 3.2.0
Tokenizers 0.21.0

Task: Image Classification
Library: transformers
Type: swinv2
License: apache-2.0
Created: Feb 10, 2025
Updated: Feb 10, 2025