zerishdorelser commited on
Commit
0d84d65
Β·
verified Β·
1 Parent(s): fa5a8bc

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +68 -54
README.md CHANGED
@@ -1,55 +1,69 @@
1
- # πŸ“± Nano AI Image Analyzer
2
-
3
- this is a Gen-AI project. that utilizes various AI models to analyze a picture.
4
-
5
- ### steps
6
- 1. create your virtual environment (venv) [optional]
7
- > Set-ExecutionPolicy -ExecutionPolicy RemoteSigned -Scope CurrentUser <br/>
8
- > .\venv\Scripts\Activate.ps1 #powershell <br/>
9
- > venv\Scripts\activate.bat #cmd <br/>
10
-
11
- 1. install all modules under `requirements.txt` using -->
12
- > pip install -r requirements.txt
13
-
14
- 2. run the app using
15
- > streamlit run app.py <br/>
16
-
17
- make sure to check `.streamlit/config.toml` for your streamlit settings
18
-
19
-
20
- ## features offered
21
-
22
- <h3>πŸ” Detect Objects</h3>
23
- detects person, car, watch, TV etc <br/>
24
- creates a bounded box around it <br />
25
- provides a table with rows representing object type, box coordinates, score
26
-
27
- <h3>πŸ“ Describe Image</h3>
28
- generates a very small caption
29
-
30
- <h3>πŸ“– Generate Story</h3>
31
- creates a story based on caption
32
-
33
- <h3>πŸ’¬ Chat system</h3>
34
- ask about image
35
-
36
-
37
- ## models used πŸ€–πŸ’»
38
- why don't you read the `apps.py`? 😁
39
-
40
- ## file structure
41
- ```
42
- |-- .streamlit
43
- | |-- config.toml --> streamlit configuration
44
- |
45
- |-- app.py --> main app
46
- |-- functions.py --> functions used in the app. (it is not a module)
47
- |-- instruction.txt --> draft of README.md
48
- |-- requirements.txt --> all the pakages under venv. generated using `pip freeze`
49
- |-- type2.py \
50
- |-- type3.py --> some extra template i used while developing
51
- |-- type4.py /
52
- ```
53
-
54
- ## link of streamlit cloud
 
 
 
 
 
 
 
 
 
 
 
 
 
 
55
  [will be added](#)
 
1
+ ---
2
+ license: mit
3
+ title: Nano AI Image Analyzer
4
+ sdk: streamlit
5
+ emoji: πŸ“ˆ
6
+ colorFrom: indigo
7
+ colorTo: red
8
+ pinned: false
9
+ short_description: analyze image using gen ai
10
+ ---
11
+
12
+
13
+
14
+
15
+ # πŸ“± Nano AI Image Analyzer
16
+
17
+ this is a Gen-AI project. that utilizes various AI models to analyze a picture.
18
+
19
+ ### steps
20
+ 1. create your virtual environment (venv) [optional]
21
+ > Set-ExecutionPolicy -ExecutionPolicy RemoteSigned -Scope CurrentUser <br/>
22
+ > .\venv\Scripts\Activate.ps1 #powershell <br/>
23
+ > venv\Scripts\activate.bat #cmd <br/>
24
+
25
+ 1. install all modules under `requirements.txt` using -->
26
+ > pip install -r requirements.txt
27
+
28
+ 2. run the app using
29
+ > streamlit run app.py <br/>
30
+
31
+ make sure to check `.streamlit/config.toml` for your streamlit settings
32
+
33
+
34
+ ## features offered
35
+
36
+ <h3>πŸ” Detect Objects</h3>
37
+ detects person, car, watch, TV etc <br/>
38
+ creates a bounded box around it <br />
39
+ provides a table with rows representing object type, box coordinates, score
40
+
41
+ <h3>πŸ“ Describe Image</h3>
42
+ generates a very small caption
43
+
44
+ <h3>πŸ“– Generate Story</h3>
45
+ creates a story based on caption
46
+
47
+ <h3>πŸ’¬ Chat system</h3>
48
+ ask about image
49
+
50
+
51
+ ## models used πŸ€–πŸ’»
52
+ why don't you read the `apps.py`? 😁
53
+
54
+ ## file structure
55
+ ```
56
+ |-- .streamlit
57
+ | |-- config.toml --> streamlit configuration
58
+ |
59
+ |-- app.py --> main app
60
+ |-- functions.py --> functions used in the app. (it is not a module)
61
+ |-- instruction.txt --> draft of README.md
62
+ |-- requirements.txt --> all the pakages under venv. generated using `pip freeze`
63
+ |-- type2.py \
64
+ |-- type3.py --> some extra template i used while developing
65
+ |-- type4.py /
66
+ ```
67
+
68
+ ## link of streamlit cloud
69
  [will be added](#)