|
--- |
|
license: apache-2.0 |
|
base_model: google/vit-base-patch16-224-in21k |
|
tags: |
|
- generated_from_trainer |
|
metrics: |
|
- precision |
|
- recall |
|
model-index: |
|
- name: vit-fire-detection |
|
results: [] |
|
--- |
|
|
|
<!-- 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-fire-detection |
|
|
|
This model is a fine-tuned version of [google/vit-base-patch16-224-in21k](https://huggingface.co/google/vit-base-patch16-224-in21k) on an unknown dataset. |
|
It achieves the following results on the evaluation set: |
|
- Loss: 0.0147 |
|
- Precision: 0.9974 |
|
- Recall: 0.9974 |
|
|
|
## 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: 32 |
|
- eval_batch_size: 32 |
|
- seed: 42 |
|
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 |
|
- lr_scheduler_type: linear |
|
- lr_scheduler_warmup_steps: 100 |
|
- num_epochs: 10 |
|
|
|
### Training results |
|
|
|
| Training Loss | Epoch | Step | Validation Loss | Precision | Recall | |
|
|:-------------:|:-----:|:----:|:---------------:|:---------:|:------:| |
|
| 0.1049 | 1.0 | 190 | 0.0515 | 0.9856 | 0.9854 | |
|
| 0.0666 | 2.0 | 380 | 0.0396 | 0.9910 | 0.9907 | |
|
| 0.0209 | 3.0 | 570 | 0.0227 | 0.9947 | 0.9947 | |
|
| 0.0299 | 4.0 | 760 | 0.0126 | 0.9987 | 0.9987 | |
|
| 0.0196 | 5.0 | 950 | 0.0159 | 0.9961 | 0.9960 | |
|
| 0.0223 | 6.0 | 1140 | 0.0138 | 0.9974 | 0.9974 | |
|
| 0.0085 | 7.0 | 1330 | 0.0117 | 0.9974 | 0.9974 | |
|
| 0.0156 | 8.0 | 1520 | 0.0095 | 0.9987 | 0.9987 | |
|
| 0.0072 | 9.0 | 1710 | 0.0128 | 0.9974 | 0.9974 | |
|
| 0.0019 | 10.0 | 1900 | 0.0147 | 0.9974 | 0.9974 | |
|
|
|
|
|
### Framework versions |
|
|
|
- Transformers 4.35.0 |
|
- Pytorch 2.1.0+cu118 |
|
- Tokenizers 0.14.1 |
|
|
