larimei commited on
Commit
0436762
1 Parent(s): 4f66dbd

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +46 -0
README.md CHANGED
@@ -10,3 +10,49 @@ pinned: false
10
  ---
11
 
12
  Check out the configuration reference at https://huggingface.co/docs/hub/spaces-config-reference
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
10
  ---
11
 
12
  Check out the configuration reference at https://huggingface.co/docs/hub/spaces-config-reference
13
+
14
+ # Recipe Application Based on Food101
15
+
16
+ This application utilizes image recognition technology to identify food items from images and provides appropriate recipes. It leverages AI and machine learning to offer quick recipe suggestions based on the identified dish, making cooking more accessible and enjoyable.
17
+
18
+ ## Features
19
+
20
+ - Identify food items from images using deep learning models.
21
+ - Provide recipe suggestions based on the identified food item.
22
+ - Utilize the Food101 dataset for training and testing.
23
+ - Simple and user-friendly interface powered by Gradio.
24
+
25
+ ## Installation
26
+
27
+ To run this application locally, follow these steps:
28
+
29
+ ### 1. Clone the Repository
30
+
31
+ ```
32
+ git clone https://github.com/your-username/recipe-app.git
33
+ cd recipe-app
34
+ ```
35
+
36
+ ### 2. Install Requirements
37
+
38
+ ```
39
+ pip install -r requirements.txt
40
+ ```
41
+
42
+ ### 3. Run the Gradio App
43
+
44
+ ```
45
+ python app.py
46
+ ```
47
+
48
+ ## Usage
49
+ After running the script, you will see an output similar to this:
50
+
51
+ ```
52
+ Running on local URL: http://127.0.0.1:7860/
53
+ ```
54
+ Open the provided URL in your web browser to interact with the application. You can upload food images, and the app will identify the dish and provide recipe suggestions.
55
+
56
+ ## Data and Model
57
+ The application is based on the Food101 dataset, which includes 101,000 images across 101 categories of food. We use deep learning models like ResNet-50, Vision Transformer (ViT), and EfficientNet for image classification.
58
+