|
--- |
|
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: 0.8933333333333333 |
|
- name: Precision |
|
type: precision |
|
value: 0.8772576832151301 |
|
- name: Recall |
|
type: recall |
|
value: 0.8933333333333333 |
|
--- |
|
|
|
<!-- 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: 0.2912 |
|
- Accuracy: 0.8933 |
|
- Precision: 0.8773 |
|
- Recall: 0.8933 |
|
- F1 Score: 0.8762 |
|
|
|
## 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 | 0.4588 | 0.8708 | 0.7584 | 0.8708 | 0.8107 | |
|
| No log | 2.0 | 8 | 0.3854 | 0.8708 | 0.7584 | 0.8708 | 0.8107 | |
|
| No log | 3.0 | 12 | 0.4070 | 0.8708 | 0.7584 | 0.8708 | 0.8107 | |
|
| 0.4953 | 4.0 | 16 | 0.3890 | 0.8708 | 0.7584 | 0.8708 | 0.8107 | |
|
| 0.4953 | 5.0 | 20 | 0.3688 | 0.8708 | 0.7584 | 0.8708 | 0.8107 | |
|
| 0.4953 | 6.0 | 24 | 0.3549 | 0.8708 | 0.7584 | 0.8708 | 0.8107 | |
|
| 0.4953 | 7.0 | 28 | 0.3138 | 0.8708 | 0.7584 | 0.8708 | 0.8107 | |
|
| 0.4217 | 8.0 | 32 | 0.3330 | 0.8708 | 0.8312 | 0.8708 | 0.8308 | |
|
| 0.4217 | 9.0 | 36 | 0.2946 | 0.9 | 0.8881 | 0.9 | 0.8845 | |
|
| 0.4217 | 10.0 | 40 | 0.2753 | 0.9042 | 0.8938 | 0.9042 | 0.8905 | |
|
| 0.4217 | 11.0 | 44 | 0.2996 | 0.9 | 0.8909 | 0.9 | 0.8935 | |
|
| 0.3747 | 12.0 | 48 | 0.2684 | 0.9 | 0.8883 | 0.9 | 0.8894 | |
|
| 0.3747 | 13.0 | 52 | 0.2670 | 0.9 | 0.8883 | 0.9 | 0.8894 | |
|
| 0.3747 | 14.0 | 56 | 0.2722 | 0.9042 | 0.8940 | 0.9042 | 0.8951 | |
|
| 0.3579 | 15.0 | 60 | 0.2718 | 0.9042 | 0.8940 | 0.9042 | 0.8951 | |
|
|
|
|
|
### Framework versions |
|
|
|
- Transformers 4.33.2 |
|
- Pytorch 2.0.1+cu118 |
|
- Datasets 2.14.5 |
|
- Tokenizers 0.13.3 |
|
|
