metadata
license: apache-2.0
base_model: microsoft/swinv2-large-patch4-window12-192-22k
tags:
- generated_from_trainer
datasets:
- imagefolder
metrics:
- accuracy
model-index:
- name: Psoriasis-500-100aug-224-swinv2-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: 0.8305676855895197
Psoriasis-500-100aug-224-swinv2-large
This model is a fine-tuned version of microsoft/swinv2-large-patch4-window12-192-22k on the imagefolder dataset. It achieves the following results on the evaluation set:
- Loss: 0.9383
- Accuracy: 0.8306
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 |
|---|---|---|---|---|
| 0.8251 | 0.9840 | 46 | 0.8572 | 0.7118 |
| 0.3662 | 1.9893 | 93 | 0.8063 | 0.7389 |
| 0.1443 | 2.9947 | 140 | 0.8198 | 0.7755 |
| 0.0974 | 4.0 | 187 | 0.8232 | 0.8105 |
| 0.0464 | 4.9840 | 233 | 0.9549 | 0.7904 |
| 0.0234 | 5.9893 | 280 | 0.9775 | 0.7956 |
| 0.0125 | 6.9947 | 327 | 0.9146 | 0.8192 |
| 0.0066 | 8.0 | 374 | 0.9364 | 0.8279 |
| 0.0025 | 8.9840 | 420 | 0.9412 | 0.8288 |
| 0.0006 | 9.8396 | 460 | 0.9383 | 0.8306 |
Framework versions
- Transformers 4.41.2
- Pytorch 2.1.2
- Datasets 2.19.2
- Tokenizers 0.19.1