swin-tiny-patch4-window7-224-finetuned-crop-classification
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: 0.6957
- Accuracy: 0.7234
Model description
This model was created by importing images of crop damage. 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/1qEskI6O-Jjv7UCanfQmUmzz8qUyg7FS3?usp=sharing
The possible classified data are:
Damage types
| Damage | Definition |
|---|---|
| DR | Drought |
| G | Good (growth) |
| ND | Nutrient Deficient |
| WD | Weed |
| other | Disease, Pest, Wind |
Crop 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: 2
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|---|---|---|---|---|
| 0.7819 | 1.0 | 183 | 0.7262 | 0.7016 |
| 0.7104 | 1.99 | 366 | 0.6957 | 0.7234 |
Framework versions
- Transformers 4.35.2
- Pytorch 2.1.0+cu121
- Datasets 2.16.1
- Tokenizers 0.15.0