metadata

license: apache-2.0
tags:
  - generated_from_trainer
datasets:
  - imagefolder
metrics:
  - accuracy
model-index:
  - name: vit-artworkclassifier
    results:
      - task:
          name: Image Classification
          type: image-classification
        dataset:
          name: imagefolder
          type: imagefolder
          config: artbench10-vit
          split: test
          args: artbench10-vit
        metrics:
          - name: Accuracy
            type: accuracy
            value: 0.4887640449438202

vit-artworkclassifier

This model is a fine-tuned version of google/vit-base-patch16-224-in21k on the imagefolder dataset, a subset of the artbench-10 dataset. Train set size 1800, test set size 180, split equally over the 9 classes. It achieves the following results on the evaluation set:

Loss: 1.3363
Accuracy: 0.4888

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: 0.0001
train_batch_size: 32
eval_batch_size: 8
seed: 42
optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
lr_scheduler_type: linear
num_epochs: 8
mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy
1.4136	1.79	100	1.5093	0.5112
0.7189	3.57	200	1.3363	0.4888
0.2717	5.36	300	1.4907	0.5281
0.1227	7.14	400	1.4826	0.5562

Framework versions

Transformers 4.26.1
Pytorch 1.13.1+cu117
Datasets 2.9.0
Tokenizers 0.13.2

Code to Run

def vit_classify(image): from transformers import ViTFeatureExtractor from transformers import ViTForImageClassification import torch

vit = ViTForImageClassification.from_pretrained("oschamp/vit-artworkclassifier")
vit.eval()
device = torch.device('cuda' if torch.cuda.is_available() else 'cpu')
vit.to(device)

model_name_or_path = 'google/vit-base-patch16-224-in21k'
feature_extractor = ViTFeatureExtractor.from_pretrained(model_name_or_path)

#LOAD IMAGE

encoding = feature_extractor(images=image, return_tensors="pt")
encoding.keys()

pixel_values = encoding['pixel_values'].to(device)

outputs = vit(pixel_values)
logits = outputs.logits

prediction = logits.argmax(-1)
return prediction.item() #vit.config.id2label[prediction.item()]