metadata
license: apache-2.0
base_model: microsoft/swin-tiny-patch4-window7-224
tags:
- generated_from_trainer
datasets:
- imagefolder
metrics:
- accuracy
model-index:
- name: swin-tiny-patch4-window7-224-finetuned-soccer-binary2
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: 0.9719298245614035
swin-tiny-patch4-window7-224-finetuned-soccer-binary2
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: 0.1078
- Accuracy: 0.9719
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: 10
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|---|---|---|---|---|
| 0.4085 | 0.99 | 20 | 0.1740 | 0.9544 |
| 0.1281 | 1.98 | 40 | 0.1078 | 0.9719 |
| 0.108 | 2.96 | 60 | 0.0978 | 0.9684 |
| 0.1077 | 4.0 | 81 | 0.1006 | 0.9684 |
| 0.0916 | 4.99 | 101 | 0.0954 | 0.9649 |
| 0.0824 | 5.98 | 121 | 0.0935 | 0.9684 |
| 0.0859 | 6.96 | 141 | 0.0975 | 0.9684 |
| 0.0927 | 8.0 | 162 | 0.0949 | 0.9684 |
| 0.0836 | 8.99 | 182 | 0.0928 | 0.9684 |
| 0.0958 | 9.88 | 200 | 0.0940 | 0.9684 |
Framework versions
- Transformers 4.35.2
- Pytorch 2.1.0+cu118
- Datasets 2.15.0
- Tokenizers 0.15.0