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

phuong-tk-nguyen/swin-tiny-patch4-window7-224-finetuned-eurosat

swin-tiny-patch4-window7-224-finetuned-eurosat is a image classification model from phuong-tk-nguyen. 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

Public

Parameters

27.6M

221 MB 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%

Base models

microsoft/swin-tiny-patch4-window7-224

Datasets

imagefolder

Model card

From the Hugging Face model README

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

This model is a fine-tuned version of microsoft/swin-tiny-patch4-window7-224 on the imagefolder dataset. It achieves the following results on the evaluation set:

Loss: 0.1436
Accuracy: 0.9526

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: 0.1
num_epochs: 1

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy
2.3316	0.03	10	2.2478	0.1604
2.1681	0.06	20	1.9824	0.4184
1.8612	0.09	30	1.5035	0.604
1.3889	0.11	40	0.9938	0.7216
1.2006	0.14	50	0.7234	0.8074
0.9586	0.17	60	0.5678	0.8392
0.8623	0.2	70	0.4286	0.8826
0.7509	0.23	80	0.3739	0.8848
0.6981	0.26	90	0.3286	0.904
0.7039	0.28	100	0.3099	0.9048
0.634	0.31	110	0.2724	0.9162
0.6496	0.34	120	0.2538	0.9196
0.5795	0.37	130	0.2426	0.9214
0.6245	0.4	140	0.2195	0.9294
0.5503	0.43	150	0.2034	0.9374
0.5557	0.45	160	0.1889	0.94
0.5474	0.48	170	0.1849	0.9408
0.5562	0.51	180	0.1912	0.9346
0.5442	0.54	190	0.1761	0.9422
0.5367	0.57	200	0.1866	0.9374
0.5252	0.6	210	0.1636	0.9482
0.5394	0.63	220	0.1656	0.9458
0.5582	0.65	230	0.1670	0.944
0.5642	0.68	240	0.1633	0.9486
0.5	0.71	250	0.1602	0.9468
0.504	0.74	260	0.1624	0.9448
0.4887	0.77	270	0.1556	0.9482
0.4755	0.8	280	0.1493	0.9522
0.4605	0.82	290	0.1444	0.9516
0.5271	0.85	300	0.1471	0.9526
0.514	0.88	310	0.1453	0.9506
0.5155	0.91	320	0.1448	0.9516
0.4785	0.94	330	0.1434	0.9522
0.4647	0.97	340	0.1436	0.9528
0.4657	1.0	350	0.1436	0.9526

Framework versions

Transformers 4.35.0
Pytorch 2.1.1
Datasets 2.14.6
Tokenizers 0.14.1

Task: Image Classification
Library: transformers
Type: swin
License: apache-2.0
Created: Nov 20, 2023
Updated: Nov 20, 2023