OmAlve commited on
Commit
407d01e
1 Parent(s): f672421

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +8 -4
README.md CHANGED
@@ -10,17 +10,21 @@ license: apache-2.0
10
  ## Model Details
11
 
12
  **Model Name:** Swin Transformer (swin_s3_base_224)
 
13
  **Architecture:** Swin Transformer
 
14
  **Pre-trained Model:** Swin Transformer Base (swin_base_patch4_window7_224)
15
- **Fine-tuning Dataset:** Foods-101
 
16
 
17
  ## Model Description
18
 
19
- 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.
 
20
 
21
- The pre-trained Swin Transformer Base model was fine-tuned on the Foods-101 dataset, which consists of 101 food categories with 101,000 images. The fine-tuning process involved updating the weights of the pre-trained model to adapt it to the food classification task.
22
 
23
  ## Intended Use
24
 
25
- 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 mor
26
 
 
10
  ## Model Details
11
 
12
  **Model Name:** Swin Transformer (swin_s3_base_224)
13
+
14
  **Architecture:** Swin Transformer
15
+
16
  **Pre-trained Model:** Swin Transformer Base (swin_base_patch4_window7_224)
17
+
18
+ **Fine-tuning Dataset:** Food-101
19
 
20
  ## Model Description
21
 
22
+ This model is a fine-tuned version of the Swin Transformer Base model (swin_base_patch4_window7_224) on the Foods-101 dataset.
23
+ The Swin Transformer is a powerful vision transformer architecture that introduces a hierarchical Swin Transformer block to efficiently model long-range dependencies in images.
24
 
25
+ The pre-trained Swin Transformer Base model was fine-tuned on the Foods-101 dataset, which consists of 101 food categories.
26
 
27
  ## Intended Use
28
 
29
+ 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
30