|
--- |
|
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-renovation |
|
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: 0.6666666666666666 |
|
--- |
|
|
|
<!-- 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 renovations dataset. |
|
It achieves the following results on the evaluation set: |
|
- Loss: 1.0025 |
|
- Accuracy: 0.6667 |
|
|
|
## 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 | |
|
|:-------------:|:-----:|:----:|:---------------:|:--------:| |
|
| 0.382 | 0.2 | 25 | 1.1103 | 0.6073 | |
|
| 0.5741 | 0.4 | 50 | 1.0628 | 0.6210 | |
|
| 0.5589 | 0.6 | 75 | 1.0025 | 0.6667 | |
|
| 0.4074 | 0.81 | 100 | 1.1324 | 0.6073 | |
|
| 0.3581 | 1.01 | 125 | 1.1935 | 0.6438 | |
|
| 0.2618 | 1.21 | 150 | 1.8300 | 0.5023 | |
|
| 0.1299 | 1.41 | 175 | 1.2577 | 0.6301 | |
|
| 0.2562 | 1.61 | 200 | 1.0924 | 0.6895 | |
|
| 0.2573 | 1.81 | 225 | 1.1285 | 0.6849 | |
|
| 0.2471 | 2.02 | 250 | 1.3387 | 0.6256 | |
|
| 0.0618 | 2.22 | 275 | 1.2246 | 0.6667 | |
|
| 0.0658 | 2.42 | 300 | 1.4132 | 0.6347 | |
|
| 0.0592 | 2.62 | 325 | 1.4326 | 0.6530 | |
|
| 0.0464 | 2.82 | 350 | 1.2484 | 0.6849 | |
|
| 0.0567 | 3.02 | 375 | 1.5350 | 0.6347 | |
|
| 0.0269 | 3.23 | 400 | 1.4797 | 0.6667 | |
|
| 0.0239 | 3.43 | 425 | 1.4444 | 0.6530 | |
|
| 0.0184 | 3.63 | 450 | 1.4474 | 0.6575 | |
|
| 0.0286 | 3.83 | 475 | 1.4621 | 0.6667 | |
|
|
|
|
|
### Framework versions |
|
|
|
- Transformers 4.38.2 |
|
- Pytorch 2.2.1+cu121 |
|
- Datasets 2.18.0 |
|
- Tokenizers 0.15.2 |
|
|
