|
--- |
|
license: apache-2.0 |
|
base_model: google/vit-base-patch16-224-in21k |
|
tags: |
|
- generated_from_trainer |
|
metrics: |
|
- accuracy |
|
model-index: |
|
- name: alzheimer_mri_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. --> |
|
|
|
# alzheimer_mri_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 an unknown dataset. |
|
It achieves the following results on the evaluation set: |
|
- Loss: 0.3404 |
|
- Accuracy: 0.8770 |
|
|
|
## 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: 32 |
|
- eval_batch_size: 32 |
|
- seed: 42 |
|
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 |
|
- lr_scheduler_type: linear |
|
- num_epochs: 15 |
|
|
|
### Training results |
|
|
|
| Training Loss | Epoch | Step | Validation Loss | Accuracy | |
|
|:-------------:|:-----:|:----:|:---------------:|:--------:| |
|
| No log | 1.0 | 128 | 0.8345 | 0.5996 | |
|
| No log | 2.0 | 256 | 0.8245 | 0.6309 | |
|
| No log | 3.0 | 384 | 0.7492 | 0.6543 | |
|
| 0.8188 | 4.0 | 512 | 0.7173 | 0.6777 | |
|
| 0.8188 | 5.0 | 640 | 0.6625 | 0.7168 | |
|
| 0.8188 | 6.0 | 768 | 0.6182 | 0.7373 | |
|
| 0.8188 | 7.0 | 896 | 0.5058 | 0.8027 | |
|
| 0.5344 | 8.0 | 1024 | 0.5567 | 0.7764 | |
|
| 0.5344 | 9.0 | 1152 | 0.4702 | 0.8193 | |
|
| 0.5344 | 10.0 | 1280 | 0.4502 | 0.8242 | |
|
| 0.5344 | 11.0 | 1408 | 0.4024 | 0.8408 | |
|
| 0.3356 | 12.0 | 1536 | 0.4263 | 0.8516 | |
|
| 0.3356 | 13.0 | 1664 | 0.3782 | 0.8535 | |
|
| 0.3356 | 14.0 | 1792 | 0.3378 | 0.8604 | |
|
| 0.3356 | 15.0 | 1920 | 0.3570 | 0.8701 | |
|
|
|
|
|
### Framework versions |
|
|
|
- Transformers 4.38.2 |
|
- Pytorch 2.2.1+cu121 |
|
- Datasets 2.18.0 |
|
- Tokenizers 0.15.2 |
|
|