swin-finetuned

kijeong22/swin-finetuned

swin-finetuned is a image classification model from kijeong22. 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

3% of all-time downloads

All-time downloads

298

Public

Parameters

86.8M

12.5 GB on disk

Likes

Public

Hugging Face

Repo makeup

Click a slice to open those files.

.safetensors347 MB · 100%

Parameter types

How the weights are stored.

F3286.7M · 100%

Base models

microsoft/swin-tiny-patch4-window7-224

Model card

From the Hugging Face model README

swin-finetuned

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

Loss: 0.6900
Accuracy: 0.5407

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: 4
eval_batch_size: 1
seed: 42
gradient_accumulation_steps: 4
total_train_batch_size: 16
optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
lr_scheduler_type: linear
lr_scheduler_warmup_ratio: 0.1
num_epochs: 4
mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy
0.693	1.0	605	0.6910	0.5407
0.6853	2.0	1211	0.6900	0.5407
0.6875	3.0	1817	0.6903	0.5407
0.6988	4.0	2420	0.6900	0.5407

Framework versions

Transformers 4.36.2
Pytorch 1.13.1+cu116
Datasets 2.16.1
Tokenizers 0.15.0

Task: Image Classification
Library: transformers
Type: swin
License: apache-2.0
Created: Jan 4, 2024
Updated: Jan 17, 2024