beit-sketch-classifier-pt-metaset

kmewhort/beit-sketch-classifier-pt-metaset

beit-sketch-classifier-pt-metaset is a image classification model from kmewhort. 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

628

Public

Repo size

2.1 GB

Likes

Public

Hugging Face

Repo makeup

Click a slice to open those files.

.bin348 MB · 100%

At a glance

Task: Image Classification
Library: transformers
License: apache-2.0
Model type: beit
Access: Public
Created: Jan 10, 2023
Updated: Jan 16, 2023
SHA: 10b1d582

Model card

From the Hugging Face model README

beit-sketch-classifier-pt-metaset

This model is a fine-tuned version of microsoft/beit-base-patch16-224-pt22k-ft22k on the None dataset. It achieves the following results on the evaluation set:

Loss: 0.6732
Accuracy: 0.8277

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: 5

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy
0.8069	1.0	76608	0.7673	0.7988
0.6922	2.0	153216	0.6982	0.8159
0.6289	3.0	229824	0.6709	0.8236
0.5332	4.0	306432	0.6635	0.8271
0.4283	5.0	383040	0.6732	0.8277

Framework versions

Transformers 4.25.1
Pytorch 1.13.1+cu117
Datasets 2.7.1
Tokenizers 0.13.2

Task: Image Classification
Library: transformers
Type: beit
License: apache-2.0
Created: Jan 10, 2023
Updated: Jan 16, 2023