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-wsdmhar
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: 0.9297520661157025
swin-tiny-patch4-window7-224-finetuned-wsdmhar
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: 0.1990
- Accuracy: 0.9298
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 |
|---|---|---|---|---|
| 0.7388 | 1.0 | 53 | 0.6308 | 0.7118 |
| 0.5099 | 2.0 | 106 | 0.3669 | 0.8485 |
| 0.4319 | 3.0 | 159 | 0.3324 | 0.8685 |
| 0.4002 | 4.0 | 212 | 0.2758 | 0.9029 |
| 0.3589 | 5.0 | 265 | 0.2503 | 0.9132 |
| 0.3096 | 6.0 | 318 | 0.2419 | 0.9136 |
| 0.2708 | 7.0 | 371 | 0.2277 | 0.9232 |
| 0.261 | 8.0 | 424 | 0.2168 | 0.9253 |
| 0.2526 | 9.0 | 477 | 0.2099 | 0.9246 |
| 0.2767 | 10.0 | 530 | 0.1990 | 0.9298 |
Framework versions
- Transformers 4.43.2
- Pytorch 2.3.1+cu118
- Datasets 2.20.0
- Tokenizers 0.19.1