Hugging Face's logo

Spaces:
devisionx
/
auto-annotation-segmentation
Sleeping

App Files Community
sayedM commited on
Commit
6873ca3
·
1 Parent(s): 31fec0b

Upload 5 files

Browse files
Files changed (6) hide show
  1. .gitattributes +1 -0
  2. 3000.jpeg +3 -0
  3. app.py +154 -0
  4. original (8).jpg +0 -0
  5. requirements.txt +7 -0
  6. traffic.jpg +0 -0
.gitattributes CHANGED
@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
33
  *.zip filter=lfs diff=lfs merge=lfs -text
34
  *.zst filter=lfs diff=lfs merge=lfs -text
35
  *tfevents* filter=lfs diff=lfs merge=lfs -text
 
 
33
  *.zip filter=lfs diff=lfs merge=lfs -text
34
  *.zst filter=lfs diff=lfs merge=lfs -text
35
  *tfevents* filter=lfs diff=lfs merge=lfs -text
36
+ 3000.jpeg filter=lfs diff=lfs merge=lfs -text
3000.jpeg ADDED

Git LFS Details

  • SHA256: 11329d84f564f6f3bf3d28a59c885da3deb245f9a5372ec51f7d84ea4b311323
  • Pointer size: 132 Bytes
  • Size of remote file: 1.33 MB
app.py ADDED
@@ -0,0 +1,154 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ import base64
2
+ import io
3
+ import cv2
4
+ import requests
5
+ import json
6
+ import gradio as gr
7
+ import os
8
+ from PIL import Image
9
+ import numpy as np
10
+ from PIL import ImageOps
11
+
12
+ # Accessing a specific environment variable
13
+ api_key = os.environ.get('devisionx')
14
+
15
+ # Checking if the environment variable exists
16
+ if not api_key:
17
+ print("devisionx environment variable is not set.")
18
+ exit()
19
+
20
+ # Define a function to call the API and get the results
21
+
22
+ def base64str_to_PILImage(base64str):
23
+ base64_img_bytes = base64str.encode('utf-8')
24
+ base64bytes = base64.b64decode(base64_img_bytes)
25
+ bytesObj = io.BytesIO(base64bytes)
26
+ return ImageOps.exif_transpose(Image.open(bytesObj))
27
+
28
+ def get_results(image, prompt):
29
+ threshold = 0.5
30
+
31
+ # Convert the NumPy array to PIL image
32
+ image = Image.fromarray(image)
33
+
34
+ # Convert the image to base64 string
35
+ with io.BytesIO() as output:
36
+ image.save(output, format="JPEG")
37
+ base64str = base64.b64encode(output.getvalue()).decode("utf-8")
38
+
39
+ # Prepare the payload (Adjust this part according to the API requirements)
40
+ payload = json.dumps({"base64str": base64str, "classes": prompt})
41
+
42
+ # Send the request to the API
43
+ response = requests.put(api_key, data=payload)
44
+
45
+ # Parse the JSON response
46
+ data = response.json()
47
+ print(response.status_code)
48
+ print(data)
49
+
50
+ # Access the values (Adjust this part according to the API response format)
51
+ output_image_base64 = data['firstName'] # Assuming the API returns the output image as base64
52
+
53
+
54
+ # Convert the output image from base64 to PIL and then to NumPy array
55
+ output_image = base64str_to_PILImage(output_image_base64)
56
+ output_image = np.array(output_image)
57
+
58
+ return output_image
59
+
60
+
61
+ # Define the input components for Gradio (adding a new input for the prompt)
62
+ # image_input = gr.inputs.Image()
63
+ # text_input = gr.inputs.Textbox(label="Prompt") # New input for the text prompt
64
+
65
+
66
+ # # Define the output components for Gradio (including both image and text)
67
+ # outputs = gr.Image(type="numpy", label="Output Image")
68
+
69
+ # Define the text description within an HTML <div> element
70
+ description_html = """
71
+ <!DOCTYPE html>
72
+ <html>
73
+ <head>
74
+ <title>Tuba AI Auto-Annotation </title>
75
+ </head>
76
+ <body>
77
+ <h1>Tuba AI Auto-Annotation 🚀</h1>
78
+ <h2>Saving Time, Bounding Boxes at a Time </h2>
79
+ <h2>Introduction</h2>
80
+ <p>Welcome to the world of DevisionX, where AI meets vision to revolutionize annotation. Our mission is to make computer vision accessible to all, and this README is your gateway to understanding how our auto-annotation model can change the way you work.</p>
81
+ <h2>Meet Tuba.AI - Your Partner in Vision</h2>
82
+ <h3>What is Tuba?</h3>
83
+ <p>Tuba is the secret sauce behind DevisionX, your no-code/low-code companion for all things computer vision. It's your toolkit for labeling, training data, and deploying AI-vision applications faster and easier than ever before.</p>
84
+ <ul>
85
+ <li>No-Code/Low-Code: Say goodbye to complex coding. Tuba's user-friendly interface makes it accessible to everyone.</li>
86
+ <li>Labeling Made Easy: Annotate your data effortlessly with Tuba's intuitive tools.</li>
87
+ <li>Faster Deployment: Deploy your AI models with ease, whether you're building a standalone app or integrating within an existing one.</li>
88
+ <li>State-of-the-Art Technology: Tuba is powered by the latest AI tech and follows production-ready standards.</li>
89
+ </ul>
90
+ <h2>The DevisionX Auto-Annotation</h2>
91
+ <p>Our auto-annotation model is a game-changer. It takes input text and images, weaving them together to generate precise bounding boxes. This AI marvel comes with a plethora of benefits:</p>
92
+ <ul>
93
+ <li>Time Saver: Say goodbye to hours of manual annotation. Let our model do the heavy lifting.</li>
94
+ <li>Annotation Formats: It speaks the language of YOLO and COCO, making it versatile for various projects.</li>
95
+ <li>Human Assistance: While it's incredibly efficient, it also respects human creativity and can be your reliable assistant.</li>
96
+ </ul>
97
+ <h2>Let's Build Together</h2>
98
+ <p>We are here to redefine the way you approach computer vision. Join us in this exciting journey, where AI meets creativity, and innovation knows no bounds.</p>
99
+ <p>Get started today and be a part of the future of vision.</p>
100
+ </body>
101
+ </html>
102
+
103
+
104
+
105
+ """
106
+ title = "autoannotation"
107
+
108
+ description = "This is a project description. It demonstrates how to use Gradio with an image and text input to interact with an API."
109
+
110
+ import os
111
+ examples = [
112
+ ["traffic.jpg", 'person,car,traffic sign,traffic light'],
113
+ ["3000.jpeg",'person,car,traffic sign,traffic light']
114
+ ]
115
+
116
+
117
+
118
+
119
+ # Create a Blocks object and use it as a context manager
120
+ with gr.Blocks() as demo:
121
+ gr.Markdown(
122
+ """
123
+ <div style="text-align: center;">
124
+ <h1>Tuba Autoannotation Demo</h1>
125
+ <h3>A prompt based controllable model for auto annotation </h3>
126
+ <h3>Saving Time, Bounding Boxes at a Time </h3>
127
+ Powered by <a href="https://Tuba.ai">Tuba</a>
128
+ </div>
129
+ """
130
+ )
131
+ # Define the input components and add them to the layout
132
+
133
+ with gr.Row():
134
+ image_input = gr.inputs.Image()
135
+ output = gr.Image(type="numpy", label="Output Image")
136
+
137
+ # Define the output component and add it to the layout
138
+ with gr.Row():
139
+ text_input = gr.inputs.Textbox(label="Prompt")
140
+ with gr.Row():
141
+ button = gr.Button("Run")
142
+
143
+ # Define the event listener that connects the input and output components and triggers the function
144
+ button.click(fn=get_results, inputs=[image_input, text_input], outputs=output, api_name="get_results")
145
+ # Add the description below the layout
146
+ gr.Examples(
147
+ fn=get_results,
148
+ examples=examples,
149
+ inputs=[image_input, text_input],
150
+ outputs=[output]
151
+ )
152
+ gr.Markdown(description_html)
153
+ # Launch the app
154
+ demo.launch(share=False)
original (8).jpg ADDED
requirements.txt ADDED
@@ -0,0 +1,7 @@
 
 
 
 
 
 
 
 
1
+ numpy
2
+ pydantic
3
+ matplotlib
4
+ opencv-python
5
+ DateTime
6
+ requests
7
+ gradio
traffic.jpg ADDED