metadata
license: apache-2.0
tags:
- generated_from_trainer
datasets:
- food101
metrics:
- accuracy
model-index:
- name: swin-finetuned-food101
results:
- task:
name: Image Classification
type: image-classification
dataset:
name: food101
type: food101
config: default
split: train
args: default
metrics:
- name: Accuracy
type: accuracy
value: 0.9225346534653466
swin-finetuned-food101
This model is a fine-tuned version of microsoft/swin-base-patch4-window7-224 on the food101 dataset. It achieves the following results on the evaluation set:
- Loss: 0.2749
- Accuracy: 0.9225
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
- gradient_accumulation_steps: 4
- 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: 0.1
- num_epochs: 3
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|---|---|---|---|---|
| 0.5704 | 1.0 | 1183 | 0.3810 | 0.8905 |
| 0.307 | 2.0 | 2366 | 0.2971 | 0.9149 |
| 0.1213 | 3.0 | 3549 | 0.2749 | 0.9225 |
Framework versions
- Transformers 4.25.1
- Pytorch 1.13.0+cu116
- Datasets 2.7.1
- Tokenizers 0.13.2