vit-base-patch16-224-finetuned-cifar10

phuong-tk-nguyen/vit-base-patch16-224-finetuned-cifar10

vit-base-patch16-224-finetuned-cifar10 is a image classification model from phuong-tk-nguyen. 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

769

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: Nov 22, 2023
Updated: Nov 22, 2023
SHA: 74b0a4c0

Base models

google/vit-base-patch16-224

Datasets

imagefolder

Model card

From the Hugging Face model README

vit-base-patch16-224-finetuned-cifar10

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

Loss: 0.0564
Accuracy: 0.9844

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: 1

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy
2.4597	0.03	10	2.2902	0.1662
2.1429	0.06	20	1.7855	0.5086
1.6466	0.09	30	1.0829	0.8484
0.9962	0.11	40	0.4978	0.9288
0.6127	0.14	50	0.2717	0.9508
0.4544	0.17	60	0.1942	0.9588
0.4352	0.2	70	0.1504	0.9672
0.374	0.23	80	0.1221	0.9718
0.3261	0.26	90	0.1057	0.9772
0.34	0.28	100	0.0943	0.979
0.284	0.31	110	0.0958	0.9754
0.3151	0.34	120	0.0866	0.9776
0.3004	0.37	130	0.0838	0.9788
0.3334	0.4	140	0.0798	0.9806
0.3018	0.43	150	0.0800	0.9778
0.2957	0.45	160	0.0749	0.9808
0.2952	0.48	170	0.0704	0.9814
0.3084	0.51	180	0.0720	0.9812
0.3015	0.54	190	0.0708	0.983
0.2763	0.57	200	0.0672	0.9832
0.3376	0.6	210	0.0700	0.982
0.285	0.63	220	0.0657	0.9828
0.2857	0.65	230	0.0629	0.9836
0.2644	0.68	240	0.0612	0.9842
0.2461	0.71	250	0.0601	0.9836
0.2802	0.74	260	0.0589	0.9842
0.2481	0.77	270	0.0604	0.9838
0.2641	0.8	280	0.0591	0.9846
0.2737	0.82	290	0.0581	0.9842
0.2391	0.85	300	0.0565	0.9852
0.2283	0.88	310	0.0558	0.986
0.2626	0.91	320	0.0559	0.9852
0.2325	0.94	330	0.0563	0.9846
0.2459	0.97	340	0.0565	0.9846
0.2474	1.0	350	0.0564	0.9844

Framework versions

Transformers 4.35.0
Pytorch 2.1.1
Datasets 2.14.6
Tokenizers 0.14.1

Task: Image Classification
Library: transformers
Type: vit
License: apache-2.0
Created: Nov 22, 2023
Updated: Nov 22, 2023