|
--- |
|
license: apache-2.0 |
|
base_model: microsoft/swin-large-patch4-window7-224 |
|
tags: |
|
- generated_from_trainer |
|
datasets: |
|
- imagefolder |
|
metrics: |
|
- accuracy |
|
model-index: |
|
- name: Psoriasis-500-100aug-224-swin-large |
|
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: 0.845414847161572 |
|
--- |
|
|
|
<!-- 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. --> |
|
|
|
# Psoriasis-500-100aug-224-swin-large |
|
|
|
This model is a fine-tuned version of [microsoft/swin-large-patch4-window7-224](https://huggingface.co./microsoft/swin-large-patch4-window7-224) on the imagefolder dataset. |
|
It achieves the following results on the evaluation set: |
|
- Loss: 0.7503 |
|
- Accuracy: 0.8454 |
|
|
|
## 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: 16 |
|
- eval_batch_size: 16 |
|
- seed: 42 |
|
- gradient_accumulation_steps: 4 |
|
- total_train_batch_size: 64 |
|
- 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 | |
|
|:-------------:|:------:|:----:|:---------------:|:--------:| |
|
| 0.4942 | 0.9973 | 92 | 0.6791 | 0.7825 | |
|
| 0.2458 | 1.9946 | 184 | 0.6565 | 0.8087 | |
|
| 0.0935 | 2.9919 | 276 | 0.6838 | 0.8140 | |
|
| 0.056 | 4.0 | 369 | 0.8758 | 0.7913 | |
|
| 0.0267 | 4.9973 | 461 | 0.7926 | 0.8245 | |
|
| 0.0074 | 5.9946 | 553 | 0.7328 | 0.8437 | |
|
| 0.0056 | 6.9919 | 645 | 0.7332 | 0.8480 | |
|
| 0.0019 | 8.0 | 738 | 0.7667 | 0.8524 | |
|
| 0.0013 | 8.9973 | 830 | 0.7548 | 0.8437 | |
|
| 0.0006 | 9.9729 | 920 | 0.7503 | 0.8454 | |
|
|
|
# Classification Report |
|
|
|
| Class | Precision (%) | Recall (%) | F1-Score (%) | Support | |
|
|---------------------|---------------|------------|--------------|---------| |
|
| Abnormal | 68 | 81 | 74 | 108 | |
|
| Erythrodermic | 94 | 76 | 84 | 100 | |
|
| Guttate | 92 | 87 | 89 | 114 | |
|
| Inverse | 92 | 93 | 92 | 108 | |
|
| Nail | 86 | 84 | 85 | 99 | |
|
| Normal | 85 | 87 | 86 | 82 | |
|
| Not Define | 99 | 99 | 99 | 92 | |
|
| Palm Soles | 79 | 80 | 80 | 102 | |
|
| Plaque | 88 | 75 | 81 | 84 | |
|
| Psoriatic Arthritis | 83 | 82 | 83 | 104 | |
|
| Pustular | 77 | 84 | 80 | 112 | |
|
| Scalp | 88 | 94 | 91 | 80 | |
|
| **Accuracy** | | | **85** | 1185 | |
|
| **Macro Avg** | **86** | **85** | **85** | 1185 | |
|
| **Weighted Avg** | **86** | **85** | **85** | 1185 | |
|
|
|
### Framework versions |
|
|
|
- Transformers 4.41.2 |
|
- Pytorch 2.1.2 |
|
- Datasets 2.19.2 |
|
- Tokenizers 0.19.1 |
|
|
