<!-- This model card has been generated automatically according to the information the Trainer had access to. You should probably proofread and complete it, then remove this comment. -->
vit_model
This model is a fine-tuned version of google/vit-base-patch16-224-in21k on the beans dataset. It achieves the following results on the evaluation set:
- Loss: 0.0821
- Accuracy: 0.9774
Model description
This model distinguishes between healthy and diseased bean leaves. It can also categorize between two diseases: bean rust and angular leaf spot. Just upload a photo and the model will tell you the probability of these three categories.
Healty
Bean Rust
Angular Leaf Spot
Intended uses & limitations
Just classifies bean leaves
Training and evaluation data
The model was trained with the dataset beans: https://huggingface.co/datasets/beans
Training procedure
Training hyperparameters
The following hyperparameters were used during training:
- learning_rate: 0.0002
- train_batch_size: 8
- eval_batch_size: 8
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 4
Training results
Training Loss | Epoch | Step | Validation Loss | Accuracy |
---|---|---|---|---|
0.1435 | 3.85 | 500 | 0.0821 | 0.9774 |
Framework versions
- Transformers 4.30.2
- Pytorch 2.0.1+cu118
- Datasets 2.14.2
- Tokenizers 0.13.3