vit-base-cifar10

Alan1402/vit-base-cifar10

vit-base-cifar10 is a image classification model from Alan1402. 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

2% of all-time downloads

All-time downloads

590

Public

Parameters

85.8M

343 MB on disk

Likes

Public

Hugging Face

Repo makeup

Click a slice to open those files.

.safetensors343 MB · 100%

At a glance

Task: Image Classification
Library: transformers
License: apache-2.0
Model type: vit
Access: Public
Created: Jul 11, 2024
Updated: Jul 11, 2024
SHA: f537f1de

Base models

google/vit-base-patch16-224-in21k

Model card

From the Hugging Face model README

vit-base-cifar10

This model is a fine-tuned version of google/vit-base-patch16-224-in21k on the cifar dataset. It achieves the following results on the evaluation set:

Loss: 0.0803
Accuracy: 0.9773

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: 0.0002
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: 2
mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy
0.1043	0.0457	100	0.2855	0.919
0.2671	0.0914	200	0.3650	0.9015
0.2935	0.1371	300	0.3167	0.9067
0.27	0.1828	400	0.3518	0.8922
0.3634	0.2285	500	0.3660	0.8953
0.2559	0.2742	600	0.3964	0.8901
0.197	0.3199	700	0.2481	0.9253
0.2594	0.3656	800	0.2486	0.923
0.4545	0.4113	900	0.3271	0.9
0.1243	0.4570	1000	0.2448	0.9269
0.3593	0.5027	1100	0.2118	0.9354
0.1375	0.5484	1200	0.2205	0.9349
0.1521	0.5941	1300	0.2009	0.9376
0.1237	0.6399	1400	0.1803	0.9445
0.2214	0.6856	1500	0.2026	0.9395
0.1324	0.7313	1600	0.1635	0.9493
0.1864	0.7770	1700	0.1672	0.9493
0.128	0.8227	1800	0.2015	0.9409
0.121	0.8684	1900	0.1753	0.9451
0.1918	0.9141	2000	0.1370	0.9588
0.1658	0.9598	2100	0.1543	0.9535
0.1088	1.0055	2200	0.1361	0.9577
0.0916	1.0512	2300	0.1393	0.9597
0.005	1.0969	2400	0.1295	0.9621
0.0294	1.1426	2500	0.1327	0.9639
0.0939	1.1883	2600	0.1409	0.9621
0.0756	1.2340	2700	0.1202	0.9682
0.0466	1.2797	2800	0.1274	0.964
0.0565	1.3254	2900	0.1250	0.9663
0.0609	1.3711	3000	0.1299	0.9657
0.0201	1.4168	3100	0.1203	0.9685
0.0258	1.4625	3200	0.1166	0.9693
0.0913	1.5082	3300	0.1009	0.9736
0.0235	1.5539	3400	0.0964	0.9732
0.0089	1.5996	3500	0.0966	0.9747
0.0455	1.6453	3600	0.0963	0.9748
0.0271	1.6910	3700	0.0874	0.9763
0.0407	1.7367	3800	0.0898	0.9761
0.1095	1.7824	3900	0.0849	0.976
0.0327	1.8282	4000	0.0926	0.9745
0.0427	1.8739	4100	0.0811	0.9769
0.003	1.9196	4200	0.0821	0.9761
0.0182	1.9653	4300	0.0803	0.9773

Framework versions

Transformers 4.41.2
Pytorch 2.3.0+cu121
Datasets 2.20.0
Tokenizers 0.19.1

Task: Image Classification
Library: transformers
Type: vit
License: apache-2.0
Created: Jul 11, 2024
Updated: Jul 11, 2024