|
--- |
|
license: apache-2.0 |
|
base_model: google/vit-base-patch16-224-in21k |
|
tags: |
|
- generated_from_trainer |
|
datasets: |
|
- renovation |
|
metrics: |
|
- accuracy |
|
model-index: |
|
- name: vit-base-renovation |
|
results: |
|
- task: |
|
name: Image Classification |
|
type: image-classification |
|
dataset: |
|
name: renovation |
|
type: renovation |
|
config: default |
|
split: validation |
|
args: default |
|
metrics: |
|
- name: Accuracy |
|
type: accuracy |
|
value: 0.6863636363636364 |
|
--- |
|
|
|
<!-- 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-base-renovation |
|
|
|
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 renovation dataset. |
|
It achieves the following results on the evaluation set: |
|
- Loss: 0.9761 |
|
- Accuracy: 0.6864 |
|
|
|
## 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 |
|
- mixed_precision_training: Native AMP |
|
|
|
### Training results |
|
|
|
| Training Loss | Epoch | Step | Validation Loss | Accuracy | |
|
|:-------------:|:-----:|:----:|:---------------:|:--------:| |
|
| 0.9737 | 0.2 | 25 | 1.0076 | 0.5045 | |
|
| 0.862 | 0.4 | 50 | 1.0220 | 0.5045 | |
|
| 0.9064 | 0.6 | 75 | 0.9076 | 0.5591 | |
|
| 0.8528 | 0.81 | 100 | 0.8157 | 0.65 | |
|
| 0.8848 | 1.01 | 125 | 0.8089 | 0.6273 | |
|
| 0.6608 | 1.21 | 150 | 0.8615 | 0.6409 | |
|
| 0.6748 | 1.41 | 175 | 0.8426 | 0.6318 | |
|
| 0.6559 | 1.61 | 200 | 0.8427 | 0.6091 | |
|
| 0.5654 | 1.81 | 225 | 0.8267 | 0.6682 | |
|
| 0.5254 | 2.02 | 250 | 0.7622 | 0.6545 | |
|
| 0.2778 | 2.22 | 275 | 0.9481 | 0.6636 | |
|
| 0.309 | 2.42 | 300 | 0.8998 | 0.6409 | |
|
| 0.2396 | 2.62 | 325 | 0.9171 | 0.6409 | |
|
| 0.2773 | 2.82 | 350 | 1.0582 | 0.6091 | |
|
| 0.2516 | 3.02 | 375 | 0.9362 | 0.6455 | |
|
| 0.1578 | 3.23 | 400 | 0.9264 | 0.6773 | |
|
| 0.0979 | 3.43 | 425 | 0.9470 | 0.6773 | |
|
| 0.0836 | 3.63 | 450 | 0.9941 | 0.6682 | |
|
| 0.126 | 3.83 | 475 | 0.9761 | 0.6864 | |
|
|
|
|
|
### Framework versions |
|
|
|
- Transformers 4.38.2 |
|
- Pytorch 2.2.1+cu121 |
|
- Datasets 2.18.0 |
|
- Tokenizers 0.15.2 |
|
|
