PhDFlo commited on
Commit
98071b8
·
1 Parent(s): 77895c0

edit README

Browse files
Files changed (1) hide show
  1. README.md +32 -3
README.md CHANGED
@@ -1,6 +1,6 @@
1
  ---
2
  title: Mushroom Classifier
3
- emoji: 📉
4
  colorFrom: indigo
5
  colorTo: indigo
6
  sdk: gradio
@@ -8,7 +8,36 @@ sdk_version: 5.31.0
8
  app_file: app.py
9
  pinned: false
10
  license: apache-2.0
11
- short_description: Classifier between 4 types of mushrooms
12
  ---
13
 
14
- Check out the configuration reference at https://huggingface.co/docs/hub/spaces-config-reference
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
  ---
2
  title: Mushroom Classifier
3
+ emoji: 🍄
4
  colorFrom: indigo
5
  colorTo: indigo
6
  sdk: gradio
 
8
  app_file: app.py
9
  pinned: false
10
  license: apache-2.0
11
+ short_description: AI-powered mushroom classification for 4 popular species
12
  ---
13
 
14
+ # Mushroom Species Classifier
15
+
16
+ This is an AI-powered application that can classify four different types of mushrooms commonly found in Europe:
17
+
18
+ - Amanite (Amanita) - Including some of the most striking mushroom species
19
+ - Bolet (Boletus) - Including prized edible species like porcini
20
+ - Morille (Morchella) - Highly sought-after edible mushrooms
21
+ - Truffe (Tuber) - Prestigious underground fungi
22
+
23
+ ## How to Use
24
+
25
+ 1. Visit the Space's webpage
26
+ 2. Upload an image of a mushroom using the interface
27
+ 3. The model will analyze the image and provide probability scores for each mushroom type
28
+ 4. Results are displayed as percentages for each possible species
29
+
30
+ ## Technical Details
31
+
32
+ - Built using FastAI and PyTorch
33
+ - Uses a fine-tuned ResNet model
34
+ - Deployed using Gradio interface
35
+ - Training dataset includes numerous images of each mushroom type
36
+
37
+ ## Important Note
38
+
39
+ This classifier is for educational purposes only. Never use AI alone to identify edible mushrooms. Always consult expert mycologists or official guides for mushroom identification, as some species can be deadly if misidentified.
40
+
41
+ ## About
42
+
43
+ This Space was created as part of a FastAI course project to demonstrate practical applications of deep learning in nature classification tasks.