|
--- |
|
license: apache-2.0 |
|
tags: |
|
- generated_from_trainer |
|
datasets: |
|
- chest-xray-classification |
|
metrics: |
|
- accuracy |
|
model-index: |
|
- name: vit-pneumonia |
|
results: |
|
- task: |
|
name: Image Classification |
|
type: image-classification |
|
dataset: |
|
name: chest-xray-classification |
|
type: chest-xray-classification |
|
config: full |
|
split: validation |
|
args: full |
|
metrics: |
|
- name: Accuracy |
|
type: accuracy |
|
value: 0.976824034334764 |
|
--- |
|
|
|
<!-- 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. --> |
|
|
|
# vit-pneumonia |
|
|
|
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 chest-xray-classification dataset. |
|
It achieves the following results on the evaluation set: |
|
- Loss: 0.1086 |
|
- Accuracy: 0.9768 |
|
|
|
## 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: 64 |
|
- eval_batch_size: 64 |
|
- seed: 42 |
|
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 |
|
- lr_scheduler_type: cosine |
|
- lr_scheduler_warmup_ratio: 0.25 |
|
- num_epochs: 10 |
|
|
|
### Training results |
|
|
|
| Training Loss | Epoch | Step | Validation Loss | Accuracy | |
|
|:-------------:|:-----:|:----:|:---------------:|:--------:| |
|
| 0.0357 | 1.0 | 192 | 0.0955 | 0.9691 | |
|
| 0.0404 | 2.0 | 384 | 0.0720 | 0.9751 | |
|
| 0.0546 | 3.0 | 576 | 0.2275 | 0.9468 | |
|
| 0.0113 | 4.0 | 768 | 0.1386 | 0.9648 | |
|
| 0.0101 | 5.0 | 960 | 0.1212 | 0.9708 | |
|
| 0.0003 | 6.0 | 1152 | 0.0929 | 0.9777 | |
|
| 0.0002 | 7.0 | 1344 | 0.1051 | 0.9777 | |
|
| 0.0002 | 8.0 | 1536 | 0.1075 | 0.9777 | |
|
| 0.0002 | 9.0 | 1728 | 0.1084 | 0.9768 | |
|
| 0.0002 | 10.0 | 1920 | 0.1086 | 0.9768 | |
|
|
|
|
|
### Framework versions |
|
|
|
- Transformers 4.26.1 |
|
- Pytorch 1.13.1+cu116 |
|
- Datasets 2.10.1 |
|
- Tokenizers 0.13.2 |
|
|
