mobilenet_v2_1.0_224-finetuned-plantdisease
This model is a fine-tuned version of google/mobilenet_v2_1.0_224 on the imagefolder dataset. It achieves the following results on the evaluation set:
- Loss: 0.0702
- Accuracy: 0.9777
Model description
More information needed
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: 10
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|---|---|---|---|---|
| 0.3974 | 0.9996 | 1145 | 0.3599 | 0.8979 |
| 0.2155 | 2.0 | 2291 | 0.1525 | 0.9603 |
| 0.2058 | 2.9996 | 3436 | 0.1492 | 0.9559 |
| 0.1524 | 4.0 | 4582 | 0.1025 | 0.9694 |
| 0.1274 | 4.9996 | 5727 | 0.0928 | 0.9706 |
| 0.1141 | 6.0 | 6873 | 0.0874 | 0.9723 |
| 0.1275 | 6.9996 | 8018 | 0.1226 | 0.9620 |
| 0.1323 | 8.0 | 9164 | 0.0702 | 0.9777 |
| 0.1212 | 8.9996 | 10309 | 0.1257 | 0.9607 |
| 0.0981 | 9.9956 | 11450 | 0.0750 | 0.9751 |
Framework versions
- Transformers 4.44.2
- Pytorch 2.5.0+cu121
- Datasets 3.1.0
- Tokenizers 0.19.1