|
--- |
|
license: apache-2.0 |
|
base_model: google/vit-base-patch16-224-in21k |
|
tags: |
|
- generated_from_trainer |
|
datasets: |
|
- imagefolder |
|
metrics: |
|
- accuracy |
|
model-index: |
|
- name: image_classification |
|
results: |
|
- task: |
|
name: Image Classification |
|
type: image-classification |
|
dataset: |
|
name: imagefolder |
|
type: imagefolder |
|
config: en-US |
|
split: train |
|
args: en-US |
|
metrics: |
|
- name: Accuracy |
|
type: accuracy |
|
value: 0.55 |
|
--- |
|
|
|
<!-- 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. --> |
|
|
|
# image_classification |
|
|
|
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 imagefolder dataset. |
|
It achieves the following results on the evaluation set: |
|
- Loss: 1.2586 |
|
- Accuracy: 0.55 |
|
|
|
## 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: 5e-05 |
|
- train_batch_size: 16 |
|
- eval_batch_size: 16 |
|
- seed: 42 |
|
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 |
|
- lr_scheduler_type: linear |
|
- num_epochs: 50 |
|
|
|
### Training results |
|
|
|
| Training Loss | Epoch | Step | Validation Loss | Accuracy | |
|
|:-------------:|:-----:|:----:|:---------------:|:--------:| |
|
| No log | 1.0 | 40 | 1.8677 | 0.3688 | |
|
| No log | 2.0 | 80 | 1.5622 | 0.3625 | |
|
| No log | 3.0 | 120 | 1.4344 | 0.5375 | |
|
| No log | 4.0 | 160 | 1.2909 | 0.5 | |
|
| No log | 5.0 | 200 | 1.2146 | 0.6 | |
|
| No log | 6.0 | 240 | 1.2457 | 0.55 | |
|
| No log | 7.0 | 280 | 1.2429 | 0.5563 | |
|
| No log | 8.0 | 320 | 1.2015 | 0.5375 | |
|
| No log | 9.0 | 360 | 1.2393 | 0.5188 | |
|
| No log | 10.0 | 400 | 1.1908 | 0.5687 | |
|
| No log | 11.0 | 440 | 1.1580 | 0.6188 | |
|
| No log | 12.0 | 480 | 1.1608 | 0.575 | |
|
| 1.0532 | 13.0 | 520 | 1.2468 | 0.5687 | |
|
| 1.0532 | 14.0 | 560 | 1.2747 | 0.5188 | |
|
| 1.0532 | 15.0 | 600 | 1.3293 | 0.525 | |
|
| 1.0532 | 16.0 | 640 | 1.3720 | 0.525 | |
|
| 1.0532 | 17.0 | 680 | 1.4374 | 0.5125 | |
|
| 1.0532 | 18.0 | 720 | 1.3092 | 0.5687 | |
|
| 1.0532 | 19.0 | 760 | 1.4143 | 0.5437 | |
|
| 1.0532 | 20.0 | 800 | 1.5023 | 0.4938 | |
|
| 1.0532 | 21.0 | 840 | 1.4033 | 0.575 | |
|
| 1.0532 | 22.0 | 880 | 1.4476 | 0.5437 | |
|
| 1.0532 | 23.0 | 920 | 1.3089 | 0.5813 | |
|
| 1.0532 | 24.0 | 960 | 1.3866 | 0.5813 | |
|
| 0.3016 | 25.0 | 1000 | 1.3748 | 0.5875 | |
|
| 0.3016 | 26.0 | 1040 | 1.5846 | 0.5312 | |
|
| 0.3016 | 27.0 | 1080 | 1.3451 | 0.5875 | |
|
| 0.3016 | 28.0 | 1120 | 1.5289 | 0.5062 | |
|
| 0.3016 | 29.0 | 1160 | 1.6067 | 0.5125 | |
|
| 0.3016 | 30.0 | 1200 | 1.5002 | 0.5375 | |
|
| 0.3016 | 31.0 | 1240 | 1.5404 | 0.55 | |
|
| 0.3016 | 32.0 | 1280 | 1.5542 | 0.5563 | |
|
| 0.3016 | 33.0 | 1320 | 1.4320 | 0.6062 | |
|
| 0.3016 | 34.0 | 1360 | 1.6465 | 0.5312 | |
|
| 0.3016 | 35.0 | 1400 | 1.7259 | 0.5062 | |
|
| 0.3016 | 36.0 | 1440 | 1.5655 | 0.5687 | |
|
| 0.3016 | 37.0 | 1480 | 1.4517 | 0.6188 | |
|
| 0.1764 | 38.0 | 1520 | 1.5884 | 0.575 | |
|
| 0.1764 | 39.0 | 1560 | 1.4692 | 0.5813 | |
|
| 0.1764 | 40.0 | 1600 | 1.5062 | 0.6125 | |
|
| 0.1764 | 41.0 | 1640 | 1.5122 | 0.6 | |
|
| 0.1764 | 42.0 | 1680 | 1.5859 | 0.6 | |
|
| 0.1764 | 43.0 | 1720 | 1.6816 | 0.525 | |
|
| 0.1764 | 44.0 | 1760 | 1.5594 | 0.6062 | |
|
| 0.1764 | 45.0 | 1800 | 1.7011 | 0.5375 | |
|
| 0.1764 | 46.0 | 1840 | 1.5676 | 0.575 | |
|
| 0.1764 | 47.0 | 1880 | 1.5260 | 0.6 | |
|
| 0.1764 | 48.0 | 1920 | 1.5711 | 0.575 | |
|
| 0.1764 | 49.0 | 1960 | 1.7095 | 0.5563 | |
|
| 0.1256 | 50.0 | 2000 | 1.7625 | 0.5188 | |
|
|
|
|
|
### Framework versions |
|
|
|
- Transformers 4.33.2 |
|
- Pytorch 2.0.1+cu118 |
|
- Datasets 2.14.5 |
|
- Tokenizers 0.13.3 |
|
|
