vit-base-patch16-224-in21k-Mango_leaf_Disease
This model is a fine-tuned version of google/vit-base-patch16-224-in21k. It achieves the following results on the evaluation set:
- Loss: 0.0189
- Accuracy: 1.0
- Weighted f1: 1.0
- Micro f1: 1.0
- Macro f1: 1.0
- Weighted recall: 1.0
- Micro recall: 1.0
- Macro recall: 1.0
- Weighted precision: 1.0
- Micro precision: 1.0
- Macro precision: 1.0
Model description
This is a multiclass image classification model of mango leaf diseases.
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/Mango%20Leaf%20Disease%20Dataset/Mango_Leaf_Disease_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/aryashah2k/mango-leaf-disease-dataset
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: 2
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 |
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| 0.0554 | 1.0 | 200 | 0.0359 | 0.9988 | 0.9988 | 0.9988 | 0.9987 | 0.9988 | 0.9988 | 0.9987 | 0.9988 | 0.9988 | 0.9987 |
| 0.0192 | 2.0 | 400 | 0.0189 | 1.0 | 1.0 | 1.0 | 1.0 | 1.0 | 1.0 | 1.0 | 1.0 | 1.0 | 1.0 |
Framework versions
- Transformers 4.27.4
- Pytorch 2.0.0
- Datasets 2.11.0
- Tokenizers 0.13.3
License Notice
This model is a fine-tuned derivative of a pretrained model. Users must comply with the original model license.
Dataset Notice
This model was fine-tuned on third-party datasets which may have separate licenses or usage restrictions.