Image Classification
Transformers
TensorBoard
Safetensors
swinv2
Generated from Trainer
Eval Results (legacy)
# Load model directly
from transformers import AutoImageProcessor, AutoModelForImageClassification
processor = AutoImageProcessor.from_pretrained("Angy309/swinv2-tiny-patch4-window16-256-prueba3")
model = AutoModelForImageClassification.from_pretrained("Angy309/swinv2-tiny-patch4-window16-256-prueba3")Quick Links
swinv2-tiny-patch4-window16-256-prueba3
This model is a fine-tuned version of microsoft/swinv2-tiny-patch4-window16-256 on the imagefolder dataset. It achieves the following results on the evaluation set:
- Loss: 0.5599
- Accuracy: 0.7179
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: 3
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|---|---|---|---|---|
| No log | 0.9091 | 5 | 0.6165 | 0.6667 |
| 0.6601 | 2.0 | 11 | 0.5599 | 0.7179 |
| 0.6601 | 2.7273 | 15 | 0.5462 | 0.7179 |
Framework versions
- Transformers 4.40.2
- Pytorch 2.2.1+cu121
- Datasets 2.19.1
- Tokenizers 0.19.1
- Downloads last month
- 4
Model tree for Angy309/swinv2-tiny-patch4-window16-256-prueba3
Base model
microsoft/swinv2-tiny-patch4-window16-256Evaluation results
- Accuracy on imagefolderself-reported0.718
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("image-classification", model="Angy309/swinv2-tiny-patch4-window16-256-prueba3") pipe("https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/hub/parrots.png")