swinv2-tiny-patch4-window8-256-dmae-humeda-DAV68

RobertoSonic/swinv2-tiny-patch4-window8-256-dmae-humeda-DAV68

swinv2-tiny-patch4-window8-256-dmae-humeda-DAV68 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

4% of all-time downloads

All-time downloads

108

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: Mar 21, 2025
Updated: Mar 21, 2025
SHA: fcc25d7c

Base models

microsoft/swinv2-tiny-patch4-window8-256

Model card

From the Hugging Face model README

swinv2-tiny-patch4-window8-256-dmae-humeda-DAV68

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: 0.2868
Accuracy: 0.9314

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: 3e-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: 45
mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy
1.0651	1.0	18	1.0769	0.4686
0.9503	2.0	36	0.8111	0.7257
0.5745	3.0	54	0.4972	0.7314
0.4746	4.0	72	0.4788	0.7486
0.4363	5.0	90	0.5427	0.7314
0.4362	6.0	108	0.3581	0.8686
0.3476	7.0	126	0.3572	0.8686
0.3113	8.0	144	0.4335	0.7886
0.3943	9.0	162	0.2782	0.8686
0.2574	10.0	180	0.3320	0.8686
0.2345	11.0	198	0.4383	0.8343
0.3002	12.0	216	0.3053	0.8686
0.2038	13.0	234	0.3189	0.8743
0.2244	14.0	252	0.2766	0.8743
0.2277	15.0	270	0.2637	0.8857
0.2318	16.0	288	0.4612	0.8114
0.1908	17.0	306	0.3167	0.8857
0.1932	18.0	324	0.2949	0.9029
0.1676	19.0	342	0.2627	0.9086
0.1442	20.0	360	0.2584	0.9143
0.1606	21.0	378	0.2626	0.9143
0.1624	22.0	396	0.2351	0.9257
0.1735	23.0	414	0.2746	0.9257
0.1604	24.0	432	0.3237	0.8914
0.122	25.0	450	0.2852	0.8914
0.1447	26.0	468	0.2594	0.92
0.1265	27.0	486	0.2857	0.9029
0.1265	28.0	504	0.3238	0.8743
0.122	29.0	522	0.3029	0.8857
0.0929	30.0	540	0.2936	0.9029
0.1276	31.0	558	0.2777	0.9143
0.1118	32.0	576	0.2812	0.9143
0.1058	33.0	594	0.2925	0.92
0.0824	34.0	612	0.3519	0.8914
0.1084	35.0	630	0.2847	0.92
0.1074	36.0	648	0.2735	0.9143
0.1415	37.0	666	0.2724	0.9257
0.0702	38.0	684	0.2873	0.92
0.0987	39.0	702	0.2924	0.92
0.0637	40.0	720	0.2868	0.9314
0.1183	41.0	738	0.2892	0.92
0.096	42.0	756	0.2910	0.9143
0.0719	42.5217	765	0.2897	0.9143

Framework versions

Transformers 4.49.0
Pytorch 2.6.0+cu124
Datasets 3.4.1
Tokenizers 0.21.1

Task: Image Classification
Library: transformers
Type: swinv2
License: apache-2.0
Created: Mar 21, 2025
Updated: Mar 21, 2025