|
--- |
|
license: apache-2.0 |
|
base_model: google/vit-base-patch16-224-in21k |
|
tags: |
|
- image-classification |
|
- generated_from_trainer |
|
metrics: |
|
- accuracy |
|
model-index: |
|
- name: Melanoma-Classification |
|
results: [] |
|
--- |
|
|
|
<!-- 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. --> |
|
|
|
# Melanoma-Classification |
|
|
|
This model is a fine-tuned version of [google/vit-base-patch16-224-in21k](https://huggingface.co/google/vit-base-patch16-224-in21k) on the [SeyedAli/Skin-Lesion-Dataset](https://huggingface.co/SeyedAli/Skin-Lesion-Dataset) dataset. |
|
It achieves the following results on the evaluation set: |
|
- Loss: 0.5750 |
|
- Accuracy: 0.8167 |
|
|
|
## 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: 0.0002 |
|
- train_batch_size: 16 |
|
- eval_batch_size: 8 |
|
- seed: 42 |
|
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 |
|
- lr_scheduler_type: linear |
|
- num_epochs: 4 |
|
|
|
### Training results |
|
|
|
| Training Loss | Epoch | Step | Validation Loss | Accuracy | |
|
|:-------------:|:-----:|:----:|:---------------:|:--------:| |
|
| 0.9779 | 0.08 | 100 | 1.1158 | 0.6041 | |
|
| 0.9934 | 0.16 | 200 | 1.0227 | 0.6501 | |
|
| 0.9562 | 0.24 | 300 | 0.9276 | 0.6748 | |
|
| 1.0995 | 0.32 | 400 | 0.9088 | 0.6836 | |
|
| 0.8198 | 0.39 | 500 | 0.8581 | 0.6949 | |
|
| 0.8034 | 0.47 | 600 | 0.8444 | 0.6967 | |
|
| 0.8319 | 0.55 | 700 | 0.8196 | 0.7148 | |
|
| 0.787 | 0.63 | 800 | 0.8360 | 0.6975 | |
|
| 0.8642 | 0.71 | 900 | 0.8250 | 0.7008 | |
|
| 0.8329 | 0.79 | 1000 | 0.7939 | 0.7172 | |
|
| 0.9678 | 0.87 | 1100 | 0.7661 | 0.7332 | |
|
| 0.8226 | 0.95 | 1200 | 0.7284 | 0.7373 | |
|
| 0.7967 | 1.03 | 1300 | 0.7355 | 0.7411 | |
|
| 0.6531 | 1.1 | 1400 | 0.7561 | 0.7247 | |
|
| 0.5719 | 1.18 | 1500 | 0.6839 | 0.7638 | |
|
| 0.6123 | 1.26 | 1600 | 0.6857 | 0.7584 | |
|
| 0.6504 | 1.34 | 1700 | 0.6970 | 0.7531 | |
|
| 0.6214 | 1.42 | 1800 | 0.6841 | 0.7576 | |
|
| 0.4925 | 1.5 | 1900 | 0.6624 | 0.7642 | |
|
| 0.5797 | 1.58 | 2000 | 0.6287 | 0.7709 | |
|
| 0.6018 | 1.66 | 2100 | 0.6537 | 0.7622 | |
|
| 0.6334 | 1.74 | 2200 | 0.6413 | 0.7713 | |
|
| 0.4111 | 1.82 | 2300 | 0.6242 | 0.7786 | |
|
| 0.4779 | 1.89 | 2400 | 0.6260 | 0.7790 | |
|
| 0.5488 | 1.97 | 2500 | 0.6146 | 0.7807 | |
|
| 0.3212 | 2.05 | 2600 | 0.6975 | 0.7707 | |
|
| 0.4282 | 2.13 | 2700 | 0.6344 | 0.7790 | |
|
| 0.2822 | 2.21 | 2800 | 0.6985 | 0.7845 | |
|
| 0.3003 | 2.29 | 2900 | 0.5954 | 0.7993 | |
|
| 0.2982 | 2.37 | 3000 | 0.6156 | 0.7940 | |
|
| 0.2628 | 2.45 | 3100 | 0.6318 | 0.7963 | |
|
| 0.2987 | 2.53 | 3200 | 0.6495 | 0.8030 | |
|
| 0.2714 | 2.6 | 3300 | 0.6018 | 0.8052 | |
|
| 0.3059 | 2.68 | 3400 | 0.5944 | 0.8078 | |
|
| 0.2762 | 2.76 | 3500 | 0.6296 | 0.7936 | |
|
| 0.3685 | 2.84 | 3600 | 0.6277 | 0.8017 | |
|
| 0.2299 | 2.92 | 3700 | 0.5834 | 0.8125 | |
|
| 0.3414 | 3.0 | 3800 | 0.5750 | 0.8167 | |
|
| 0.1082 | 3.08 | 3900 | 0.6201 | 0.8196 | |
|
| 0.049 | 3.16 | 4000 | 0.6475 | 0.8161 | |
|
| 0.102 | 3.24 | 4100 | 0.6791 | 0.8097 | |
|
| 0.0483 | 3.31 | 4200 | 0.6582 | 0.8216 | |
|
| 0.1204 | 3.39 | 4300 | 0.6603 | 0.8222 | |
|
| 0.0611 | 3.47 | 4400 | 0.7174 | 0.8190 | |
|
| 0.0555 | 3.55 | 4500 | 0.6841 | 0.8236 | |
|
| 0.0188 | 3.63 | 4600 | 0.7009 | 0.8240 | |
|
| 0.1292 | 3.71 | 4700 | 0.7040 | 0.8204 | |
|
| 0.0661 | 3.79 | 4800 | 0.7074 | 0.8238 | |
|
| 0.1061 | 3.87 | 4900 | 0.6984 | 0.8210 | |
|
| 0.0861 | 3.95 | 5000 | 0.6913 | 0.8230 | |
|
|
|
|
|
### Framework versions |
|
|
|
- Transformers 4.38.1 |
|
- Pytorch 2.1.0+cu121 |
|
- Datasets 2.18.0 |
|
- Tokenizers 0.15.2 |
|
|
