datasets:
- pierreguillou/DocLayNet-base
metrics:
- accuracy
base_model:
- google/vit-base-patch16-224-in21k
library_name: transformers
tags:
- vision
- document-layout-analysis
- document-classification
- vit
- doclaynet
ViT Model for Document Layout Classification
This model is a fine-tuned Vision Transformer (ViT) for document layout classification based on the DocLayNet dataset.
Model description
This model is built upon the google/vit-base-patch16-224-in21k Vision Transformer architecture and fine-tuned specifically for document layout classification. The base ViT model uses a patch size of 16x16 pixels and was pre-trained on ImageNet-21k. The model has been optimized to recognize and classify different types of document layouts from the DocLayNet dataset.
Training data
The model was trained on DocLayNet-base dataset, which is available on the Hugging Face Hub: pierreguillou/DocLayNet-base
DocLayNet is a comprehensive dataset for document layout analysis, containing various document types and their corresponding layout annotations.
Training procedure
The training was made with following hyperparameters:
{
'batch_size': 64,
'num_epochs': 20,
'learning_rate': 1e-4,
'weight_decay': 0.05,
'warmup_ratio': 0.2,
'gradient_clip': 0.1,
'dropout_rate': 0.1,
'label_smoothing': 0.1,
'optimizer': 'AdamW'
}
## Evaluation results
The model achieved the following performance metrics on the test set:
Test Loss: 0.8622
Test Accuracy: 81.36%