metadata
license: apache-2.0
tags:
- generated_from_trainer
datasets:
- imagefolder
metrics:
- accuracy
model-index:
- name: swin-tiny-patch4-window7-224-bottom_cleaned_data
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: 0.9726247987117552
swin-tiny-patch4-window7-224-bottom_cleaned_data
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: 0.0839
- Accuracy: 0.9726
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: 8
- eval_batch_size: 8
- seed: 42
- gradient_accumulation_steps: 4
- total_train_batch_size: 32
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_ratio: 0.01
- num_epochs: 10
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|---|---|---|---|---|
| 0.4444 | 1.0 | 174 | 0.2271 | 0.9163 |
| 0.3518 | 2.0 | 349 | 0.2449 | 0.9034 |
| 0.225 | 3.0 | 523 | 0.1325 | 0.9501 |
| 0.2195 | 4.0 | 698 | 0.1024 | 0.9549 |
| 0.2627 | 5.0 | 872 | 0.1046 | 0.9630 |
| 0.142 | 6.0 | 1047 | 0.0839 | 0.9726 |
| 0.1516 | 7.0 | 1221 | 0.0918 | 0.9630 |
| 0.1498 | 8.0 | 1396 | 0.0780 | 0.9726 |
| 0.1189 | 9.0 | 1570 | 0.0721 | 0.9662 |
| 0.1594 | 9.97 | 1740 | 0.0668 | 0.9726 |
Framework versions
- Transformers 4.28.1
- Pytorch 2.0.0+cu118
- Datasets 2.11.0
- Tokenizers 0.13.3