|
--- |
|
license: apache-2.0 |
|
base_model: microsoft/swin-base-patch4-window7-224 |
|
tags: |
|
- generated_from_trainer |
|
datasets: |
|
- imagefolder |
|
metrics: |
|
- accuracy |
|
- f1 |
|
- precision |
|
- recall |
|
model-index: |
|
- name: swin-finetuned-food101 |
|
results: |
|
- task: |
|
name: Image Classification |
|
type: image-classification |
|
dataset: |
|
name: imagefolder |
|
type: imagefolder |
|
config: default |
|
split: validation |
|
args: default |
|
metrics: |
|
- name: Accuracy |
|
type: accuracy |
|
value: 0.4166666666666667 |
|
- name: F1 |
|
type: f1 |
|
value: 0.5882352941176471 |
|
- name: Precision |
|
type: precision |
|
value: 0.4166666666666667 |
|
- name: Recall |
|
type: recall |
|
value: 1.0 |
|
--- |
|
|
|
<!-- 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. --> |
|
|
|
# swin-finetuned-food101 |
|
|
|
This model is a fine-tuned version of [microsoft/swin-base-patch4-window7-224](https://huggingface.co./microsoft/swin-base-patch4-window7-224) on the imagefolder dataset. |
|
It achieves the following results on the evaluation set: |
|
- Loss: 0.7046 |
|
- Accuracy: 0.4167 |
|
- F1: 0.5882 |
|
- Precision: 0.4167 |
|
- Recall: 1.0 |
|
- Auc: 0.5742 |
|
|
|
## 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: 0.001 |
|
- train_batch_size: 32 |
|
- eval_batch_size: 32 |
|
- seed: 42 |
|
- gradient_accumulation_steps: 2 |
|
- total_train_batch_size: 64 |
|
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 |
|
- lr_scheduler_type: linear |
|
- lr_scheduler_warmup_ratio: 0.06 |
|
- num_epochs: 5 |
|
|
|
### Training results |
|
|
|
| Training Loss | Epoch | Step | Validation Loss | Accuracy | F1 | Precision | Recall | Auc | |
|
|:-------------:|:-----:|:----:|:---------------:|:--------:|:------:|:---------:|:------:|:------:| |
|
| 0.6978 | 1.0 | 14 | 0.6847 | 0.5833 | 0.0 | 0.0 | 0.0 | 0.5717 | |
|
| 0.7025 | 2.0 | 28 | 0.7120 | 0.4167 | 0.5882 | 0.4167 | 1.0 | 0.5570 | |
|
| 0.6946 | 3.0 | 42 | 0.6955 | 0.4167 | 0.5882 | 0.4167 | 1.0 | 0.5662 | |
|
| 0.6935 | 4.0 | 56 | 0.7047 | 0.4167 | 0.5882 | 0.4167 | 1.0 | 0.5644 | |
|
| 0.6935 | 5.0 | 70 | 0.7046 | 0.4167 | 0.5882 | 0.4167 | 1.0 | 0.5742 | |
|
|
|
|
|
### Framework versions |
|
|
|
- Transformers 4.36.2 |
|
- Pytorch 2.1.2+cu118 |
|
- Datasets 2.15.0 |
|
- Tokenizers 0.15.0 |
|
|
