|
--- |
|
license: apache-2.0 |
|
base_model: google/vit-base-patch16-224-in21k |
|
tags: |
|
- image-classification |
|
- generated_from_trainer |
|
datasets: |
|
- renovation |
|
metrics: |
|
- accuracy |
|
model-index: |
|
- name: vit-base-renovation2 |
|
results: |
|
- task: |
|
name: Image Classification |
|
type: image-classification |
|
dataset: |
|
name: renovations |
|
type: renovation |
|
config: default |
|
split: validation |
|
args: default |
|
metrics: |
|
- name: Accuracy |
|
type: accuracy |
|
value: 0.6027397260273972 |
|
pipeline_tag: image-classification |
|
--- |
|
|
|
<!-- 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-renovation2 |
|
|
|
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 renovations dataset. |
|
It achieves the following results on the evaluation set: |
|
- Loss: 1.2384 |
|
- Accuracy: 0.6027 |
|
|
|
## 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 | |
|
|:-------------:|:-----:|:----:|:---------------:|:--------:| |
|
| 0.273 | 0.2 | 25 | 1.2384 | 0.6027 | |
|
| 0.5153 | 0.4 | 50 | 1.4060 | 0.5845 | |
|
| 0.2792 | 0.6 | 75 | 1.3026 | 0.5936 | |
|
| 0.5516 | 0.81 | 100 | 1.3999 | 0.6027 | |
|
| 0.4247 | 1.01 | 125 | 1.2621 | 0.5982 | |
|
| 0.1556 | 1.21 | 150 | 1.5661 | 0.5571 | |
|
| 0.1458 | 1.41 | 175 | 1.3459 | 0.6347 | |
|
| 0.1595 | 1.61 | 200 | 1.5278 | 0.5982 | |
|
| 0.1195 | 1.81 | 225 | 1.5303 | 0.6256 | |
|
| 0.1507 | 2.02 | 250 | 1.7701 | 0.5845 | |
|
| 0.023 | 2.22 | 275 | 1.5354 | 0.6301 | |
|
| 0.028 | 2.42 | 300 | 1.6535 | 0.6301 | |
|
| 0.0698 | 2.62 | 325 | 1.6772 | 0.6438 | |
|
| 0.0516 | 2.82 | 350 | 1.4380 | 0.6804 | |
|
| 0.0136 | 3.02 | 375 | 1.6561 | 0.6484 | |
|
| 0.0325 | 3.23 | 400 | 1.6028 | 0.6621 | |
|
| 0.0149 | 3.43 | 425 | 1.6261 | 0.6621 | |
|
| 0.0082 | 3.63 | 450 | 1.6615 | 0.6621 | |
|
| 0.0093 | 3.83 | 475 | 1.6878 | 0.6530 | |
|
|
|
|
|
### Framework versions |
|
|
|
- Transformers 4.38.2 |
|
- Pytorch 2.2.1+cu121 |
|
- Datasets 2.18.0 |
|
- Tokenizers 0.15.2 |
