swin-tiny-patch4-window7-224-finetuned-plantdisease
This model is a fine-tuned version of microsoft/swin-tiny-patch4-window7-224 on the imagefolder dataset. It achieves the following results on the evaluation set:
- Loss: 0.1032
- Accuracy: 0.9690
Model description
This model was created by importing the dataset of the photos of diseased plants into Google Colab from kaggle here: https://www.kaggle.com/datasets/emmarex/plantdisease. I then used the image classification tutorial here: https://colab.research.google.com/github/huggingface/notebooks/blob/main/examples/image_classification.ipynb
obtaining the following notebook:
https://colab.research.google.com/drive/14ItHnpARBBGaYQCiJwJsnWiiNQnlrIyP?usp=sharing
The possible classified diseases are: Tomato Tomato YellowLeaf Curl Virus , Tomato Late blight , Pepper bell Bacterial spot, Tomato Early blight, Potato healthy, Tomato healthy , Tomato Target_Spot , Potato Early blight , Tomato Tomato mosaic virus, Pepper bell healthy, Potato Late blight, Tomato Septoria leaf spot , Tomato Leaf Mold , Tomato Spider mites Two spotted spider mite , Tomato Bacterial spot .
Leaf example:
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: 1
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|---|---|---|---|---|
| 0.1903 | 1.0 | 145 | 0.1032 | 0.9690 |
Framework versions
- Transformers 4.20.1
- Pytorch 1.11.0+cu113
- Datasets 2.3.2
- Tokenizers 0.12.1