|
--- |
|
license: apache-2.0 |
|
base_model: microsoft/swin-tiny-patch4-window7-224 |
|
tags: |
|
- generated_from_trainer |
|
datasets: |
|
- imagefolder |
|
metrics: |
|
- accuracy |
|
- precision |
|
- recall |
|
model-index: |
|
- name: swin-tiny-patch4-window7-224 |
|
results: |
|
- task: |
|
name: Image Classification |
|
type: image-classification |
|
dataset: |
|
name: imagefolder |
|
type: imagefolder |
|
config: default |
|
split: validation |
|
args: default |
|
metrics: |
|
- name: Accuracy |
|
type: accuracy |
|
value: 0.7133333333333334 |
|
- name: Precision |
|
type: precision |
|
value: 0.6732516172965611 |
|
- name: Recall |
|
type: recall |
|
value: 0.7133333333333334 |
|
--- |
|
|
|
<!-- This model card has been generated automatically according to the information the Trainer had access to. You |
|
should probably proofread and complete it, then remove this comment. --> |
|
|
|
# swin-tiny-patch4-window7-224 |
|
|
|
This model is a fine-tuned version of [microsoft/swin-tiny-patch4-window7-224](https://huggingface.co./microsoft/swin-tiny-patch4-window7-224) on the imagefolder dataset. |
|
It achieves the following results on the evaluation set: |
|
- Loss: 0.5797 |
|
- Accuracy: 0.7133 |
|
- Precision: 0.6733 |
|
- Recall: 0.7133 |
|
- F1 Score: 0.6650 |
|
|
|
## 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: 64 |
|
- eval_batch_size: 64 |
|
- seed: 42 |
|
- gradient_accumulation_steps: 4 |
|
- total_train_batch_size: 256 |
|
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 |
|
- lr_scheduler_type: linear |
|
- lr_scheduler_warmup_ratio: 0.1 |
|
- num_epochs: 15 |
|
|
|
### Training results |
|
|
|
| Training Loss | Epoch | Step | Validation Loss | Accuracy | Precision | Recall | F1 Score | |
|
|:-------------:|:-----:|:----:|:---------------:|:--------:|:---------:|:------:|:--------:| |
|
| No log | 1.0 | 4 | 0.5965 | 0.725 | 0.5256 | 0.725 | 0.6094 | |
|
| No log | 2.0 | 8 | 0.6045 | 0.7125 | 0.5795 | 0.7125 | 0.6104 | |
|
| No log | 3.0 | 12 | 0.5910 | 0.725 | 0.6645 | 0.725 | 0.6169 | |
|
| 0.6165 | 4.0 | 16 | 0.5865 | 0.7333 | 0.7162 | 0.7333 | 0.6418 | |
|
| 0.6165 | 5.0 | 20 | 0.5789 | 0.7292 | 0.6846 | 0.7292 | 0.6562 | |
|
| 0.6165 | 6.0 | 24 | 0.5649 | 0.725 | 0.6702 | 0.725 | 0.6427 | |
|
| 0.6165 | 7.0 | 28 | 0.5660 | 0.7375 | 0.7090 | 0.7375 | 0.6668 | |
|
| 0.5966 | 8.0 | 32 | 0.5972 | 0.7375 | 0.7108 | 0.7375 | 0.7132 | |
|
| 0.5966 | 9.0 | 36 | 0.5666 | 0.7417 | 0.7134 | 0.7417 | 0.6835 | |
|
| 0.5966 | 10.0 | 40 | 0.5781 | 0.7417 | 0.7124 | 0.7417 | 0.7084 | |
|
| 0.5966 | 11.0 | 44 | 0.6009 | 0.7083 | 0.6900 | 0.7083 | 0.6967 | |
|
| 0.5921 | 12.0 | 48 | 0.5678 | 0.75 | 0.7244 | 0.75 | 0.7118 | |
|
| 0.5921 | 13.0 | 52 | 0.5581 | 0.7583 | 0.7429 | 0.7583 | 0.7115 | |
|
| 0.5921 | 14.0 | 56 | 0.5587 | 0.7542 | 0.7340 | 0.7542 | 0.7083 | |
|
| 0.5847 | 15.0 | 60 | 0.5589 | 0.7542 | 0.7340 | 0.7542 | 0.7083 | |
|
|
|
|
|
### Framework versions |
|
|
|
- Transformers 4.33.2 |
|
- Pytorch 2.0.1+cu118 |
|
- Datasets 2.14.5 |
|
- Tokenizers 0.13.3 |
|
|
