|
--- |
|
base_model: |
|
- timm/swin_s3_base_224.ms_in1k |
|
tags: |
|
- image-classification |
|
- timm |
|
library_name: timm |
|
license: apache-2.0 |
|
datasets: |
|
- food101 |
|
metrics: |
|
- accuracy |
|
--- |
|
# Model card for swin_s3_base_224-Foods-101 |
|
|
|
## Model Details |
|
|
|
**Model Name:** Swin Transformer (swin_s3_base_224) |
|
|
|
**Architecture:** Swin Transformer |
|
|
|
**Pre-trained Model:** Swin Transformer Base (swin_base_patch4_window7_224) |
|
|
|
**Fine-tuning Dataset:** Food-101 |
|
|
|
## Model Description |
|
|
|
This model is a fine-tuned version of the Swin Transformer Base model (swin_base_patch4_window7_224) on the Foods-101 dataset. |
|
The Swin Transformer is a powerful vision transformer architecture that introduces a hierarchical Swin Transformer block to efficiently model long-range dependencies in images. |
|
|
|
The pre-trained Swin Transformer Base model was fine-tuned on the Foods-101 dataset, which consists of 101 food categories. |
|
|
|
## Intended Use |
|
|
|
This fine-tuned model can be used for classifying food images into one of the 101 categories present in the Foods-101 dataset. It can be employed in various applications related to food recognition, dietary analysis, recipe recommendation systems, and more |
