# Load model directly
from transformers import AutoImageProcessor, AutoModelForImageClassification
processor = AutoImageProcessor.from_pretrained("crangana/trained-race")
model = AutoModelForImageClassification.from_pretrained("crangana/trained-race")Quick Links
trained-race
This model is a fine-tuned version of microsoft/resnet-50 on the fair_face dataset. It achieves the following results on the evaluation set:
- Loss: 0.9830
- Accuracy: 0.6258
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: 0.0002
- train_batch_size: 16
- 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 |
|---|---|---|---|---|
| 1.3923 | 0.18 | 1000 | 1.3550 | 0.4712 |
| 1.1517 | 0.37 | 2000 | 1.1854 | 0.5429 |
| 1.2405 | 0.55 | 3000 | 1.1001 | 0.5754 |
| 1.0752 | 0.74 | 4000 | 1.0330 | 0.6018 |
| 1.0986 | 0.92 | 5000 | 0.9973 | 0.6173 |
| 1.0007 | 1.11 | 6000 | 0.9735 | 0.6279 |
| 0.9851 | 1.29 | 7000 | 0.9830 | 0.6258 |
Framework versions
- Transformers 4.34.0
- Pytorch 2.0.1+cu118
- Datasets 2.14.5
- Tokenizers 0.14.0
- Downloads last month
- 67
Model tree for crangana/trained-race
Base model
microsoft/resnet-50Evaluation results
- Accuracy on fair_facevalidation set self-reported0.626
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("image-classification", model="crangana/trained-race") pipe("https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/hub/parrots.png")