metadata
license: apache-2.0
tags:
- generated_from_trainer
datasets:
- imagefolder
metrics:
- accuracy
model-index:
- name: >-
swinv2-large-patch4-window12to16-192to256-22kto1k-ft-finetuned-Lesion-Classification-HAM10000-AH
results:
- task:
name: Image Classification
type: image-classification
dataset:
name: imagefolder
type: imagefolder
config: Augmented-Final
split: train
args: Augmented-Final
metrics:
- name: Accuracy
type: accuracy
value: 0.9681397738951696
swinv2-large-patch4-window12to16-192to256-22kto1k-ft-finetuned-Lesion-Classification-HAM10000-AH
This model is a fine-tuned version of microsoft/swinv2-large-patch4-window12to16-192to256-22kto1k-ft on the imagefolder dataset. It achieves the following results on the evaluation set:
- Loss: 0.1143
- Accuracy: 0.9681
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-06
- train_batch_size: 16
- eval_batch_size: 16
- seed: 42
- gradient_accumulation_steps: 2
- total_train_batch_size: 32
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_ratio: 0.9
- num_epochs: 12
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|---|---|---|---|---|
| 1.9527 | 1.0 | 122 | 1.9746 | 0.1716 |
| 1.818 | 2.0 | 244 | 1.7423 | 0.3628 |
| 1.5044 | 3.0 | 366 | 1.3707 | 0.5046 |
| 1.1173 | 4.0 | 488 | 0.9796 | 0.6300 |
| 0.8714 | 5.0 | 610 | 0.7475 | 0.7379 |
| 0.8631 | 6.0 | 732 | 0.5978 | 0.7729 |
| 0.628 | 7.0 | 854 | 0.4791 | 0.8212 |
| 0.5588 | 8.0 | 976 | 0.3517 | 0.8705 |
| 0.5632 | 9.0 | 1098 | 0.2564 | 0.9168 |
| 0.3693 | 10.0 | 1220 | 0.1875 | 0.9455 |
| 0.321 | 11.0 | 1342 | 0.1525 | 0.9424 |
| 0.2761 | 12.0 | 1464 | 0.1143 | 0.9681 |
Framework versions
- Transformers 4.30.2
- Pytorch 2.0.1+cu118
- Datasets 2.13.1
- Tokenizers 0.13.3