DunnBC22's picture
Update README.md
b56f768
---
license: apache-2.0
tags:
- generated_from_trainer
datasets:
- imagefolder
metrics:
- accuracy
- f1
- recall
- precision
model-index:
- name: vit-base-patch16-224-in21k_lung_and_colon_cancer
results:
- task:
name: Image Classification
type: image-classification
dataset:
name: imagefolder
type: imagefolder
config: default
split: train
args: default
metrics:
- name: Accuracy
type: accuracy
value: 0.9994
language:
- en
pipeline_tag: image-classification
---
# vit-base-patch16-224-in21k_lung_and_colon_cancer
This model is a fine-tuned version of [google/vit-base-patch16-224-in21k](https://huggingface.co/google/vit-base-patch16-224-in21k).
It achieves the following results on the evaluation set:
- Loss: 0.0016
- Accuracy: 0.9994
- F1
- Weighted: 0.9994
- Micro: 0.9994
- Macro: 0.9994
- Recall
- Weighted: 0.9994
- Micro: 0.9994
- Macro: 0.9994
- Precision
- Weighted: 0.9994
- Micro: 0.9994
- Macro: 0.9994
## Model description
This is a multiclass image classification model of lung and colon cancers.
For more information on how it was created, check out the following link: https://github.com/DunnBC22/Vision_Audio_and_Multimodal_Projects/blob/main/Computer%20Vision/Image%20Classification/Multiclass%20Classification/Lung%20%26%20Colon%20Cancer/Lung_and_colon_cancer_ViT.ipynb
## Intended uses & limitations
This model is intended to demonstrate my ability to solve a complex problem using technology.
## Training and evaluation data
Dataset Source: https://www.kaggle.com/datasets/andrewmvd/lung-and-colon-cancer-histopathological-images
_Sample Images From Dataset:_
![Sample Images](https://github.com/DunnBC22/Vision_Audio_and_Multimodal_Projects/raw/main/Computer%20Vision/Image%20Classification/Multiclass%20Classification/Lung%20%26%20Colon%20Cancer/Images/Sample%20Images.png)
## 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: 3
### Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy | Weighted F1 | Micro F1 | Macro F1 | Weighted Recall | Micro Recall | Macro Recall | Weighted Precision | Micro Precision | Macro Precision |
|:-------------:|:-----:|:----:|:---------------:|:--------:|:-----------:|:--------:|:--------:|:---------------:|:------------:|:------------:|:------------------:|:---------------:|:---------------:|
| 0.0574 | 1.0 | 1250 | 0.0410 | 0.9864 | 0.9864 | 0.9864 | 0.9865 | 0.9864 | 0.9864 | 0.9864 | 0.9872 | 0.9864 | 0.9875 |
| 0.0031 | 2.0 | 2500 | 0.0105 | 0.9972 | 0.9972 | 0.9972 | 0.9972 | 0.9972 | 0.9972 | 0.9973 | 0.9972 | 0.9972 | 0.9972 |
| 0.0007 | 3.0 | 3750 | 0.0016 | 0.9994 | 0.9994 | 0.9994 | 0.9994 | 0.9994 | 0.9994 | 0.9994 | 0.9994 | 0.9994 | 0.9994 |
### Framework versions
- Transformers 4.22.2
- Pytorch 1.12.1
- Datasets 2.5.2
- Tokenizers 0.12.1