Downloads · 30 days
9
1% of all-time downloads
swin-food102
juliensimon/swin-food102
swin-food102 is a image classification model from juliensimon. Use it when you need a label for an image. It is set up for transformers.
This model is a fine-tuned version of juliensimon/autotrain-food101-1471154053 on the food102 dataset, namely the food101 dataset with an extra class generated with a Stable Diffusion model.
All-time downloads
794
Public
Parameters
86.9M
696 MB on disk
Likes
1
Public
Repo makeup
Click a slice to open those files.
.bin348 MB · 50%
Parameter types
How the weights are stored.
F3286.8M · 100%
Datasets
Model card
From the Hugging Face model README
swin-food102
This model is a fine-tuned version of juliensimon/autotrain-food101-1471154053 on the food102 dataset, namely the food101 dataset with an extra class generated with a Stable Diffusion model.
A detailed walk-through is available on YouTube.
The achieves the following results on the evaluation set:
- Loss: 0.2510
- Accuracy: 0.9338
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: 1e-05
- train_batch_size: 16
- eval_batch_size: 64
- seed: 42
- gradient_accumulation_steps: 8
- total_train_batch_size: 128
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 3
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|---|---|---|---|---|
| 1.1648 | 1.0 | 597 | 0.3118 | 0.9218 |
| 0.31 | 2.0 | 1194 | 0.2606 | 0.9322 |
| 0.2488 | 3.0 | 1791 | 0.2510 | 0.9338 |
Framework versions
- Transformers 4.23.1
- Pytorch 1.12.1+cu102
- Datasets 2.4.0
- Tokenizers 0.13.1
- Task
- Image Classification
- Library
- transformers
- Type
- swin
- Created
- Oct 26, 2022
- Updated
- Apr 4, 2023