# Load model directly
from transformers import AutoImageProcessor, AutoModelForImageClassification
processor = AutoImageProcessor.from_pretrained("Starmaster7/bird_genus_image_classification_model")
model = AutoModelForImageClassification.from_pretrained("Starmaster7/bird_genus_image_classification_model", device_map="auto")Quick Links
results_final
This model is a fine-tuned version of google/efficientnet-b3 on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 5.4534
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: 0.07
- train_batch_size: 16
- eval_batch_size: 16
- seed: 42
- optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
- lr_scheduler_type: linear
- lr_scheduler_warmup_steps: 0.02
- num_epochs: 30
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 3.7801 | 1.0 | 240 | 3.5997 |
| 3.6030 | 2.0 | 480 | 3.4122 |
| 3.5533 | 3.0 | 720 | 3.4880 |
| 3.4716 | 4.0 | 960 | 3.5813 |
| 3.3849 | 5.0 | 1200 | 3.8072 |
| 3.3499 | 6.0 | 1440 | 3.1296 |
| 3.2501 | 7.0 | 1680 | 3.3787 |
| 3.2307 | 8.0 | 1920 | 3.2702 |
| 3.1690 | 9.0 | 2160 | 3.4604 |
| 3.1316 | 10.0 | 2400 | 3.0390 |
| 3.1056 | 11.0 | 2640 | 3.6019 |
| 3.0999 | 12.0 | 2880 | 3.3648 |
| 3.0658 | 13.0 | 3120 | 3.2586 |
| 3.0190 | 14.0 | 3360 | 3.3761 |
| 2.9633 | 15.0 | 3600 | 3.4629 |
| 2.9125 | 16.0 | 3840 | 2.9820 |
| 2.8926 | 17.0 | 4080 | 2.9411 |
| 2.8830 | 18.0 | 4320 | 2.8852 |
| 2.8468 | 19.0 | 4560 | 2.8470 |
| 2.8401 | 20.0 | 4800 | 3.1739 |
| 2.8407 | 21.0 | 5040 | 2.8360 |
| 2.8088 | 22.0 | 5280 | 2.8013 |
| 2.7835 | 23.0 | 5520 | 2.7773 |
| 2.7627 | 24.0 | 5760 | 2.7736 |
| 2.7417 | 25.0 | 6000 | 2.8376 |
| 2.7228 | 26.0 | 6240 | 2.7436 |
| 2.7087 | 27.0 | 6480 | 2.7369 |
| 2.6784 | 28.0 | 6720 | 2.7986 |
| 2.6436 | 29.0 | 6960 | 2.7207 |
| 2.6153 | 30.0 | 7200 | 5.4534 |
Framework versions
- Transformers 5.13.1
- Pytorch 2.11.0+cu128
- Datasets 4.0.0
- Tokenizers 0.22.2
- Downloads last month
- -
Model tree for Starmaster7/bird_genus_image_classification_model
Base model
google/efficientnet-b3
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("image-classification", model="Starmaster7/bird_genus_image_classification_model") pipe("https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/hub/parrots.png")