swin-original-5

genofog/swin-original-5

swin-original-5 is a machine learning model from genofog. Use it for the machine learning task on the model card, and read the license before you ship it in a product. The card lists the license as apache-2.0.

should probably proofread and complete it, then remove this comment. --

Downloads · 30 days

17% of all-time downloads

All-time downloads

Public

Parameters

27.9M

1.1 GB on disk

Likes

Public

Hugging Face

Repo makeup

Click a slice to open those files.

.safetensors112 MB · 100%

Parameter types

How the weights are stored.

F3227.9M · 100%

Base models

microsoft/swin-tiny-patch4-window7-224

Datasets

imagefolder

Model card

From the Hugging Face model README

swin-original-5

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: 0.1231
Accuracy: 0.9853

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: 5

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy
4.9811	1.0	247	2.3893	0.5847
1.6282	2.0	494	0.4871	0.9393
0.6306	3.0	741	0.2507	0.9709
0.478	4.0	988	0.1513	0.9830
0.3531	5.0	1235	0.1231	0.9853

Framework versions

Transformers 4.39.3
Pytorch 2.2.2+cu121
Datasets 3.0.0
Tokenizers 0.15.2

Type: swin
License: apache-2.0
Created: Sep 12, 2024
Updated: Sep 12, 2024