resnet-50-finetuned-oxfordflowers
This model is a fine-tuned version of microsoft/resnet-50 on the oxford102_flower_dataset dataset. It achieves the following results on the evaluation set:
- Loss: 0.6561
- Accuracy: 0.8330
- Precision: 0.8531
- Recall: 0.8330
- F1: 0.8319
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: 0.001
- train_batch_size: 32
- eval_batch_size: 32
- seed: 42
- optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
- lr_scheduler_type: linear
- num_epochs: 20
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy | Precision | Recall | F1 |
|---|---|---|---|---|---|---|---|
| 4.4813 | 1.0 | 32 | 4.1934 | 0.3176 | 0.3522 | 0.3176 | 0.2599 |
| 2.6507 | 2.0 | 64 | 1.8716 | 0.5382 | 0.5792 | 0.5382 | 0.4930 |
| 1.257 | 3.0 | 96 | 1.0998 | 0.7216 | 0.7663 | 0.7216 | 0.7085 |
| 0.5333 | 4.0 | 128 | 0.9724 | 0.7422 | 0.7875 | 0.7422 | 0.7296 |
| 0.2506 | 5.0 | 160 | 0.8243 | 0.7627 | 0.7975 | 0.7627 | 0.7566 |
| 0.0689 | 6.0 | 192 | 0.7067 | 0.8147 | 0.8482 | 0.8147 | 0.8111 |
| 0.0325 | 7.0 | 224 | 0.6370 | 0.8206 | 0.8428 | 0.8206 | 0.8175 |
| 0.0132 | 8.0 | 256 | 0.5774 | 0.8412 | 0.8617 | 0.8412 | 0.8389 |
| 0.0117 | 9.0 | 288 | 0.5469 | 0.8559 | 0.8726 | 0.8559 | 0.8542 |
| 0.0066 | 10.0 | 320 | 0.5384 | 0.8608 | 0.8722 | 0.8608 | 0.8575 |
| 0.0072 | 11.0 | 352 | 0.5246 | 0.8686 | 0.8783 | 0.8686 | 0.8650 |
| 0.0068 | 12.0 | 384 | 0.5130 | 0.8716 | 0.8790 | 0.8716 | 0.8679 |
| 0.0045 | 13.0 | 416 | 0.5038 | 0.8716 | 0.8814 | 0.8716 | 0.8691 |
| 0.0025 | 14.0 | 448 | 0.5486 | 0.85 | 0.8627 | 0.85 | 0.8448 |
| 0.0029 | 15.0 | 480 | 0.4992 | 0.8637 | 0.8736 | 0.8637 | 0.8619 |
Framework versions
- Transformers 4.47.1
- Pytorch 2.5.1+cu121
- Datasets 3.2.0
- Tokenizers 0.21.0