VIT-VGGFace

skutaada/VIT-VGGFace

VIT-VGGFace is a image classification model from skutaada. 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

6% of all-time downloads

All-time downloads

743

Public

Parameters

92.8M

4.8 GB on disk

Likes

Public

Hugging Face

Repo makeup

Click a slice to open those files.

.safetensors371 MB · 100%

At a glance

Task: Image Classification
Library: transformers
License: apache-2.0
Model type: vit
Access: Public
Created: Jul 19, 2024
Updated: Jul 22, 2024
SHA: e85f0c9c

Base models

google/vit-base-patch16-224-in21k

Model card

From the Hugging Face model README

ViT-VGGFace

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

Loss: 0.8361
Accuracy: 0.8306

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: 24
eval_batch_size: 24
seed: 42
gradient_accumulation_steps: 4
total_train_batch_size: 96
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
1.6402	0.9982	416	1.7366	0.7127
1.1955	1.9988	833	1.2342	0.7782
0.9051	2.9994	1250	1.0314	0.8023
0.7446	4.0	1667	0.9074	0.8172
0.8081	4.9910	2080	0.8361	0.8306

Framework versions

Transformers 4.42.4
Pytorch 2.3.1+rocm6.0
Datasets 2.20.0
Tokenizers 0.19.1

Task: Image Classification
Library: transformers
Type: vit
License: apache-2.0
Created: Jul 19, 2024
Updated: Jul 22, 2024