metadata

license: apache-2.0
tags:
  - generated_from_trainer
datasets:
  - imagefolder
metrics:
  - accuracy
  - f1
  - recall
  - precision
model-index:
  - name: vit-base-patch16-224-in21k-Landscape_Recognition
    results:
      - task:
          name: Image Classification
          type: image-classification
        dataset:
          name: imagefolder
          type: imagefolder
          config: default
          split: train
          args: default
        metrics:
          - name: Accuracy
            type: accuracy
            value: 0.8686666666666667
language:
  - en
pipeline_tag: image-classification

vit-base-patch16-224-in21k-Landscape_Recognition

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

Loss: 0.4648
Accuracy: 0.8687
Weighted f1: 0.8694
Micro f1: 0.8687
Macro f1: 0.8694
Weighted recall: 0.8687
Micro recall: 0.8687
Macro recall: 0.8687
Weighted precision: 0.8714
Micro precision: 0.8687
Macro precision: 0.8714

Model description

This is a multiclass image classification model of different types of landscaping.

For more information on how it was created, check out the following link: https://github.com/DunnBC22/Vision_Audio_and_Multimodal_Projects/blob/main/Computer%20Vision/Image%20Classification/Multiclass%20Classification/Landscape%20Recognition/Landscape_Recognition_ViT.ipynb

Intended uses & limitations

This model is intended to demonstrate my ability to solve a complex problem using technology.

Training and evaluation data

Dataset Source: https://www.kaggle.com/datasets/utkarshsaxenadn/landscape-recognition-image-dataset-12k-images

Sample Images From Dataset:

Training procedure

Training hyperparameters

The following hyperparameters were used during training:

learning_rate: 0.0002
train_batch_size: 16
eval_batch_size: 8
seed: 42
optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
lr_scheduler_type: linear
num_epochs: 3

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy	Weighted f1	Micro f1	Macro f1	Weighted recall	Micro recall	Macro recall	Weighted precision	Micro precision	Macro precision
0.2866	1.0	625	0.4308	0.8487	0.8538	0.8487	0.8538	0.8487	0.8487	0.8487	0.8700	0.8487	0.8700
0.1522	2.0	1250	0.4648	0.8687	0.8694	0.8687	0.8694	0.8687	0.8687	0.8687	0.8714	0.8687	0.8714
0.0609	3.0	1875	0.5122	0.866	0.8678	0.866	0.8678	0.866	0.866	0.866	0.8710	0.866	0.8710

Framework versions

Transformers 4.27.4
Pytorch 2.0.0
Datasets 2.11.0
Tokenizers 0.13.3