mini-vision 0.1.0__tar.gz

This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
@@ -0,0 +1,9 @@
1
+ Metadata-Version: 2.4
2
+ Name: mini_vision
3
+ Version: 0.1.0
4
+ Summary: YOLO segmentation utilities for video streams
5
+ Author: Seu Nome
6
+ Requires-Dist: ultralytics
7
+ Requires-Dist: opencv-python
8
+ Requires-Dist: websockets
9
+ Requires-Dist: numpy
@@ -0,0 +1,79 @@
1
+ # mini_vision
2
+
3
+ Simple Python library for **object segmentation in video streams** using YOLO models.
4
+
5
+ The goal of this library is to provide a modular pipeline to:
6
+
7
+ - consume video streams
8
+ - perform object segmentation
9
+ - render contours or masks
10
+
11
+ The library follows **data-oriented design** and **low coupling principles**, allowing easy replacement of computer vision models.
12
+
13
+ ---
14
+
15
+ ## Installation
16
+
17
+ Clone the repository:
18
+
19
+ ```
20
+ git clone https://github.com/DeividManfre/mini_vision.git
21
+ ```
22
+
23
+ ```
24
+ cd mini_vision
25
+ ```
26
+
27
+ ```
28
+ pip install .
29
+ ```
30
+
31
+ ## Usage
32
+
33
+ Example showing how to use vision-seg to consume a video stream, run YOLO segmentation, and render object contours.
34
+
35
+ ### Import the library
36
+
37
+ ```
38
+ from vision_seg import (
39
+ YoloSegmenter,
40
+ SegmentationRenderer,
41
+ WSFrameClient
42
+ )
43
+ ```
44
+
45
+ ### Components:
46
+
47
+ | Component | Description |
48
+ | ---------------------- | -------------------------------------------------------- |
49
+ | `YoloSegmenter` | Runs object segmentation using a YOLO segmentation model |
50
+ | `SegmentationRenderer` | Draws segmentation contours on the frame |
51
+ | `WSFrameClient` | Connects to a WebSocket video stream and yields frames |
52
+
53
+
54
+ #### YoloSegmenter
55
+
56
+ Runs object segmentation using a YOLO segmentation model.
57
+
58
+ ```
59
+ segmenter = YoloSegmenter("yolov8n-seg.pt")
60
+ detections = segmenter.segment(frame)
61
+ ```
62
+
63
+ #### SegmentationRenderer
64
+
65
+ Responsible for rendering segmentation contours on frames.
66
+
67
+ ````
68
+ renderer = SegmentationRenderer()
69
+ frame = renderer.draw_contours(frame, detections)
70
+ ````
71
+
72
+ #### WSFrameClient
73
+
74
+ Connects to a WebSocket video stream and yields frames.
75
+
76
+ ```
77
+ client = WSFrameClient("ws://127.0.0.1:8000/ws/frames")
78
+ async for frame in client.frames():
79
+ ```
@@ -0,0 +1,9 @@
1
+ Metadata-Version: 2.4
2
+ Name: mini_vision
3
+ Version: 0.1.0
4
+ Summary: YOLO segmentation utilities for video streams
5
+ Author: Seu Nome
6
+ Requires-Dist: ultralytics
7
+ Requires-Dist: opencv-python
8
+ Requires-Dist: websockets
9
+ Requires-Dist: numpy
@@ -0,0 +1,7 @@
1
+ README.md
2
+ pyproject.toml
3
+ mini_vision.egg-info/PKG-INFO
4
+ mini_vision.egg-info/SOURCES.txt
5
+ mini_vision.egg-info/dependency_links.txt
6
+ mini_vision.egg-info/requires.txt
7
+ mini_vision.egg-info/top_level.txt
@@ -0,0 +1,4 @@
1
+ ultralytics
2
+ opencv-python
3
+ websockets
4
+ numpy
@@ -0,0 +1,20 @@
1
+ [build-system]
2
+ requires = ["setuptools", "wheel"]
3
+ build-backend = "setuptools.build_meta"
4
+
5
+ [project]
6
+ name = "mini_vision"
7
+ version = "0.1.0"
8
+ description = "YOLO segmentation utilities for video streams"
9
+ authors = [
10
+ {name="Seu Nome"}
11
+ ]
12
+ dependencies = [
13
+ "ultralytics",
14
+ "opencv-python",
15
+ "websockets",
16
+ "numpy"
17
+ ]
18
+
19
+ [tool.setuptools.packages.find]
20
+ where = ["."]
@@ -0,0 +1,4 @@
1
+ [egg_info]
2
+ tag_build =
3
+ tag_date = 0
4
+