A Python Library for Computer-Vision related Tasks
Project description
Xtreme-Vision
Xtreme-Vision is a Python Library which is built with simplicity in mind for Computer Vision Tasks, such as Object-Detection, Human-Pose-Estimation, Image-Segmentation Tasks, it provides the support of a list of state-of-the-art algorithms, You can Start Detecting with Pretrained Weights as well as You can train the Models On Custom Dataset.
Currently, It Provides the Solution for the following Tasks:
- Object-Detection
- Pose-Estimation
For Detection with pre-trained models it provides:
- RetinaNet
- CenterNet
- YOLOv4
- TinyYOLOv4
For Custom Training It Provides:
- YOLOv4
- TinyYOLOv4
In Future it will provide solution for a wide variety of Computer-Vision Tasks such as Object-Detection, Pose-Estimation, Image-Segmentation, Image-Prediction, Auto-Encoders and GANs.
If You Like this Project Please do support it by donating here
Dependencies:
- Tensorflow >= 2.3.0
- Keras
- Opencv-python
- Numpy
- Pillow
- Matplotlib
- Pandas
- Scikit-learn
- Progressbar2
- Scipy
- H5Py
Get Started:
!pip install xtreme-vision
For More Tutorials of Xtreme-Vision, Click
Here
RetinaNet
Example
Image Object_Detection
Using RetinaNet
from xtreme_vision.Detection import Object_Detection
model = Object_Detection()
model.Use_RetinaNet()
model.Detect_From_Image(input_path='kite.jpg',
output_path='./retinanet.jpg',
extract_objects=True)
from PIL import Image
Image.open('retinanet.jpg')
Project details
Release history Release notifications | RSS feed
Download files
Download the file for your platform. If you're not sure which to choose, learn more about installing packages.
Source Distribution
Built Distribution
Hashes for xtreme_vision-1.2-py3-none-any.whl
Algorithm | Hash digest | |
---|---|---|
SHA256 | 63ec4e0ba1d97bd35a18783b5deec68c3a9ec217d492eb1946e52575bf516422 |
|
MD5 | 62445a927528daf4b7398972e66fde60 |
|
BLAKE2b-256 | 18c137b8db39f728e40ecaa2db205d425409e754c9684112661125a2c6cde5ac |