vit-base-patch16-224-in21k

ri-xx/vit-base-patch16-224-in21k

vit-base-patch16-224-in21k is a image classification model from ri-xx. Use it when you need a label for an image. It is set up for transformers.

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

Downloads · 30 days

1% of all-time downloads

All-time downloads

371

Public

Repo size

20.6 GB

Likes

Public

Hugging Face

Repo makeup

Click a slice to open those files.

.bin343 MB · 100%

At a glance

Task: Image Classification
Library: transformers
Model type: vit
Access: Public
Created: Sep 18, 2023
Updated: Sep 18, 2023
SHA: dfab75db

Datasets

imagefolder

Model card

From the Hugging Face model README

vit-base-patch16-224-in21k

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

Loss: 1.6306
Accuracy: 0.5375

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: 16
eval_batch_size: 16
seed: 42
optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
lr_scheduler_type: linear
num_epochs: 50

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy
No log	1.0	40	1.2472	0.5312
No log	2.0	80	1.2878	0.5188
No log	3.0	120	1.3116	0.525
No log	4.0	160	1.2578	0.55
No log	5.0	200	1.2186	0.5563
No log	6.0	240	1.2680	0.5563
No log	7.0	280	1.3674	0.5
No log	8.0	320	1.3814	0.525
No log	9.0	360	1.4394	0.5
No log	10.0	400	1.3710	0.5437
No log	11.0	440	1.3721	0.5437
No log	12.0	480	1.4309	0.5563
0.4861	13.0	520	1.3424	0.575
0.4861	14.0	560	1.4617	0.525
0.4861	15.0	600	1.3964	0.5813
0.4861	16.0	640	1.4751	0.5687
0.4861	17.0	680	1.5296	0.55
0.4861	18.0	720	1.5887	0.5188
0.4861	19.0	760	1.5784	0.5312
0.4861	20.0	800	1.7036	0.5375
0.4861	21.0	840	1.6988	0.5188
0.4861	22.0	880	1.6070	0.5687
0.4861	23.0	920	1.7111	0.55
0.4861	24.0	960	1.6730	0.55
0.2042	25.0	1000	1.6559	0.55
0.2042	26.0	1040	1.7221	0.5563
0.2042	27.0	1080	1.6637	0.5813
0.2042	28.0	1120	1.6806	0.5625
0.2042	29.0	1160	1.5743	0.5938
0.2042	30.0	1200	1.7899	0.4938
0.2042	31.0	1240	1.7422	0.5312
0.2042	32.0	1280	1.7712	0.55
0.2042	33.0	1320	1.7480	0.5188
0.2042	34.0	1360	1.7964	0.5375
0.2042	35.0	1400	1.9687	0.5188
0.2042	36.0	1440	1.7412	0.5813
0.2042	37.0	1480	1.9312	0.4875
0.1342	38.0	1520	1.7944	0.525
0.1342	39.0	1560	1.8180	0.55
0.1342	40.0	1600	1.7720	0.5563
0.1342	41.0	1640	1.9014	0.5312
0.1342	42.0	1680	1.7519	0.55
0.1342	43.0	1720	1.9793	0.5
0.1342	44.0	1760	1.8642	0.55
0.1342	45.0	1800	1.7573	0.5875
0.1342	46.0	1840	1.8508	0.5125
0.1342	47.0	1880	1.9741	0.5625
0.1342	48.0	1920	1.9012	0.525
0.1342	49.0	1960	1.8771	0.5625
0.0926	50.0	2000	1.8728	0.5125

Framework versions

Transformers 4.33.2
Pytorch 2.0.1+cu118
Datasets 2.14.5
Tokenizers 0.13.3

Task: Image Classification
Library: transformers
Type: vit
Created: Sep 18, 2023
Updated: Sep 18, 2023