swin-tiny-patch4-window7-224-finetuned-phones

kisa-misa/swin-tiny-patch4-window7-224-finetuned-phones

swin-tiny-patch4-window7-224-finetuned-phones is a image classification model from kisa-misa. 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

1% of all-time downloads

All-time downloads

380

Public

Parameters

27.5M

12.6 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%

Base models

microsoft/swin-tiny-patch4-window7-224

Datasets

imagefolder

Model card

From the Hugging Face model README

swin-tiny-patch4-window7-224-finetuned-phones

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: 0.3938
Accuracy: 0.8654

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: 30

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy
No log	0.9333	7	0.6743	0.5673
0.6763	2.0	15	0.6166	0.6923
0.635	2.9333	22	0.5646	0.7404
0.5724	4.0	30	0.5074	0.7308
0.5724	4.9333	37	0.4809	0.7692
0.527	6.0	45	0.4597	0.7692
0.5304	6.9333	52	0.4758	0.7596
0.4597	8.0	60	0.4343	0.7885
0.4597	8.9333	67	0.4249	0.7981
0.4606	10.0	75	0.4236	0.7981
0.4286	10.9333	82	0.4055	0.8462
0.3857	12.0	90	0.4144	0.8269
0.3857	12.9333	97	0.4294	0.7981
0.3801	14.0	105	0.4081	0.8462
0.3538	14.9333	112	0.4195	0.8462
0.3585	16.0	120	0.4069	0.8558
0.3585	16.9333	127	0.3971	0.8558
0.3258	18.0	135	0.3938	0.8654
0.3288	18.9333	142	0.3964	0.8462
0.3276	20.0	150	0.4423	0.8558
0.3276	20.9333	157	0.4067	0.8365
0.317	22.0	165	0.4179	0.8654
0.288	22.9333	172	0.3882	0.8558
0.2735	24.0	180	0.4215	0.8558
0.2735	24.9333	187	0.3972	0.8462
0.2805	26.0	195	0.3943	0.8558
0.2961	26.9333	202	0.3999	0.8558
0.2832	28.0	210	0.4043	0.8558

Framework versions

Transformers 4.41.2
Pytorch 2.3.0+cu121
Datasets 2.19.2
Tokenizers 0.19.1

Task: Image Classification
Library: transformers
Type: swin
License: apache-2.0
Created: May 16, 2024
Updated: Jun 10, 2024