swin-tiny-patch4-window7-224-finetuned-eurosat-newtrain

KaiQ/swin-tiny-patch4-window7-224-finetuned-eurosat-newtrain

swin-tiny-patch4-window7-224-finetuned-eurosat-newtrain is a machine learning model from KaiQ. Use it for the machine learning task on the model card, and read the license before you ship it in a product.

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

3.1 GB on disk

Likes

Public

Hugging Face

Repo makeup

Click a slice to open those files.

.safetensors110 MB · 100%

Parameter types

How the weights are stored.

F3227.5M · 100%

Datasets

imagefolder

Model card

From the Hugging Face model README

swin-tiny-patch4-window7-224-finetuned-eurosat-newtrain

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

Loss: 0.0003
Accuracy: 0.9998

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: 32
eval_batch_size: 32
seed: 42
gradient_accumulation_steps: 4
total_train_batch_size: 128
optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
lr_scheduler_type: linear
lr_scheduler_warmup_ratio: 0.01
num_epochs: 30

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy
0.1073	0.9985	343	0.0380	0.9891
0.0667	2.0	687	0.0187	0.9948
0.0486	2.9985	1030	0.0135	0.9944
0.0598	4.0	1374	0.0118	0.9952
0.0376	4.9985	1717	0.0083	0.9962
0.0191	6.0	2061	0.0058	0.9972
0.0265	6.9985	2404	0.0072	0.9980
0.0306	8.0	2748	0.0076	0.9982
0.0222	8.9985	3091	0.0053	0.9972
0.0196	10.0	3435	0.0063	0.9978
0.0086	10.9985	3778	0.0053	0.9984
0.0047	12.0	4122	0.0039	0.9988
0.0187	12.9985	4465	0.0076	0.9976
0.0169	14.0	4809	0.0018	0.9994
0.0068	14.9985	5152	0.0015	0.9996
0.0182	16.0	5496	0.0022	0.9992
0.0174	16.9985	5839	0.0031	0.9988
0.0174	18.0	6183	0.0017	0.9994
0.017	18.9985	6526	0.0007	0.9998
0.0097	20.0	6870	0.0018	0.9998
0.0074	20.9985	7213	0.0005	0.9998
0.0074	22.0	7557	0.0003	0.9998
0.0037	22.9985	7900	0.0008	0.9998
0.011	24.0	8244	0.0009	0.9996
0.0094	24.9985	8587	0.0009	0.9996
0.01	26.0	8931	0.0011	0.9996
0.007	26.9985	9274	0.0005	0.9998
0.0098	28.0	9618	0.0004	0.9998
0.0053	28.9985	9961	0.0005	0.9998
0.0031	29.9563	10290	0.0003	0.9998

Framework versions

Transformers 4.41.0.dev0
Pytorch 2.3.0
Datasets 2.17.1
Tokenizers 0.19.1

Type: swin
Created: Aug 13, 2024
Updated: Aug 13, 2024