metadata
license: apache-2.0
base_model: microsoft/swin-tiny-patch4-window7-224
tags:
- generated_from_trainer
datasets:
- imagefolder
metrics:
- accuracy
model-index:
- name: attraction-classifier-swin
results:
- task:
name: Image Classification
type: image-classification
dataset:
name: imagefolder
type: imagefolder
config: default
split: train
args: default
metrics:
- name: Accuracy
type: accuracy
value: 0.739010989010989
attraction-classifier-swin
This model is a fine-tuned version of microsoft/swin-tiny-patch4-window7-224 on the imagefolder dataset. It achieves the following results on the evaluation set:
- Loss: 0.5367
- Accuracy: 0.7390
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: 16
- eval_batch_size: 16
- seed: 69
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: cosine
- lr_scheduler_warmup_ratio: 0.05
- num_epochs: 10
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|---|---|---|---|---|
| 0.6207 | 0.49 | 100 | 0.5599 | 0.7115 |
| 0.6256 | 0.98 | 200 | 0.5238 | 0.7225 |
| 0.597 | 1.46 | 300 | 0.5003 | 0.7418 |
| 0.6121 | 1.95 | 400 | 0.5409 | 0.7610 |
| 0.5457 | 2.44 | 500 | 0.5123 | 0.7555 |
| 0.5258 | 2.93 | 600 | 0.4792 | 0.7637 |
| 0.504 | 3.41 | 700 | 0.5169 | 0.7390 |
| 0.541 | 3.9 | 800 | 0.4858 | 0.7582 |
| 0.5704 | 4.39 | 900 | 0.5367 | 0.7390 |
Framework versions
- Transformers 4.35.2
- Pytorch 2.0.1+cu117
- Datasets 2.15.0
- Tokenizers 0.15.0