vit-base_rvl_cdip-N1K_aAURC_128

bdpc/vit-base_rvl_cdip-N1K_aAURC_128

vit-base_rvl_cdip-N1K_aAURC_128 is a image classification model from bdpc. 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

553

Public

Repo size

687 MB

Likes

Public

Hugging Face

Repo makeup

Click a slice to open those files.

.bin343 MB · 100%

At a glance

Task: Image Classification
Library: transformers
License: apache-2.0
Model type: vit
Access: Public
Created: Oct 28, 2023
Updated: Oct 28, 2023
SHA: 40014d08

Base models

jordyvl/vit-base_rvl-cdip

Model card

From the Hugging Face model README

vit-base_rvl_cdip-N1K_aAURC_128

This model is a fine-tuned version of jordyvl/vit-base_rvl-cdip on the None dataset. It achieves the following results on the evaluation set:

Loss: 0.4634
Accuracy: 0.8915
Brier Loss: 0.1791
Nll: 0.9824
F1 Micro: 0.8915
F1 Macro: 0.8918
Ece: 0.0767
Aurc: 0.0184

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: 2e-05
train_batch_size: 128
eval_batch_size: 128
seed: 42
optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
lr_scheduler_type: linear
lr_scheduler_warmup_ratio: 0.1
num_epochs: 10

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy	Brier Loss	Nll	F1 Micro	F1 Macro	Ece	Aurc
No log	1.0	125	0.3790	0.8935	0.1649	1.1886	0.8935	0.8937	0.0488	0.0175
No log	2.0	250	0.3783	0.8958	0.1605	1.1495	0.8958	0.8959	0.0497	0.0178
No log	3.0	375	0.4065	0.8915	0.1700	1.0956	0.8915	0.8918	0.0617	0.0183
0.0928	4.0	500	0.4158	0.8932	0.1705	1.0843	0.8932	0.8936	0.0635	0.0183
0.0928	5.0	625	0.4328	0.8932	0.1721	1.0369	0.8932	0.8935	0.0673	0.0186
0.0928	6.0	750	0.4442	0.891	0.1764	1.0214	0.891	0.8913	0.0737	0.0183
0.0928	7.0	875	0.4542	0.8935	0.1770	1.0053	0.8935	0.8938	0.0722	0.0187
0.0125	8.0	1000	0.4587	0.891	0.1790	0.9941	0.891	0.8913	0.0767	0.0183
0.0125	9.0	1125	0.4616	0.891	0.1786	0.9847	0.891	0.8912	0.0767	0.0185
0.0125	10.0	1250	0.4634	0.8915	0.1791	0.9824	0.8915	0.8918	0.0767	0.0184

Framework versions

Transformers 4.33.3
Pytorch 2.2.0.dev20231002
Datasets 2.7.1
Tokenizers 0.13.3

Task: Image Classification
Library: transformers
Type: vit
License: apache-2.0
Created: Oct 28, 2023
Updated: Oct 28, 2023