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-proposed-5
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: 0.9868387749936725
swin-proposed-5
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: 0.1236
- Accuracy: 0.9868
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: 5
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|---|---|---|---|---|
| 4.8849 | 1.0 | 247 | 2.2694 | 0.6262 |
| 1.6628 | 2.0 | 494 | 0.4817 | 0.9517 |
| 0.639 | 3.0 | 741 | 0.2165 | 0.9762 |
| 0.4807 | 4.0 | 988 | 0.1525 | 0.9830 |
| 0.3724 | 5.0 | 1235 | 0.1236 | 0.9868 |
Framework versions
- Transformers 4.39.3
- Pytorch 2.2.2+cu121
- Datasets 3.0.0
- Tokenizers 0.15.2