metadata
license: apache-2.0
base_model: microsoft/swinv2-base-patch4-window12-192-22k
tags:
- generated_from_trainer
metrics:
- accuracy
model-index:
- name: Psoriasis-Project-Aug-M2-swinv2-base-patch4-window12-192-22k
results: []
pipeline_tag: image-classification
Psoriasis-Project-Aug-M2-swinv2-base-patch4-window12-192-22k
This model is a fine-tuned version of microsoft/swinv2-base-patch4-window12-192-22k on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.0088
- Accuracy: 1.0
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: 7
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|---|---|---|---|---|
| 0.7078 | 0.99 | 36 | 0.1447 | 0.9375 |
| 0.1858 | 1.99 | 72 | 0.0584 | 0.9792 |
| 0.0891 | 2.98 | 108 | 0.0082 | 1.0 |
| 0.0619 | 4.0 | 145 | 0.0215 | 1.0 |
| 0.0252 | 4.99 | 181 | 0.0120 | 1.0 |
| 0.018 | 5.99 | 217 | 0.0139 | 1.0 |
| 0.0112 | 6.95 | 252 | 0.0088 | 1.0 |
Test results
| precision | recall | f1-score | support | |
|---|---|---|---|---|
| Erythromelal | 1.00 | 1.00 | 1.00 | 5 |
| Guttate | 1.00 | 1.00 | 1.00 | 7 |
| Inverse | 1.00 | 1.00 | 1.00 | 4 |
| Nail | 1.00 | 1.00 | 1.00 | 10 |
| Normal | 1.00 | 1.00 | 1.00 | 11 |
| Plaque | 1.00 | 1.00 | 1.00 | 10 |
| Psoriatic Arthritis | 1.00 | 1.00 | 1.00 | 6 |
| Pustular | 1.00 | 1.00 | 1.00 | 6 |
| :-------------------: | :---------: | :------: | :--------: | :------: |
| accuracy | 1.00 | 59 | ||
| macro avg | 1.00 | 1.00 | 1.00 | 59 |
| weighted avg | 1.00 | 1.00 | 1.00 | 59 |
Framework versions
- Transformers 4.39.3
- Pytorch 2.1.2
- Datasets 2.18.0
- Tokenizers 0.15.2