State-of-the-art Computer Vision and Object Detection for TensorFlow.
Project description
State-of-the-art Computer Vision and Object Detection for TensorFlow.
sightseer provides state-of-the-art general-purpose architectures (YOLOv3, MaskRCNN, Fast/Faster RCNN, SSD...) for Computer Vision and Object Detection tasks with 30+ pretrained models written in TensorFlow 1.15.
Installation
sightseer
is written in Python 3.5+ and TensorFlow 1.15.
Ideally, sightseer
should be installed in a virtual environments. If you're unfamiliar with Python virtual environments, check out this tutorial on getting started.
Via PyPi
To use sightseer
, you must first have TensorFlow installed. To do so, follow the instructions on the TensorFlow installation page.
When your virtual environment is set up with TensorFlow, you can install sightseer
using pip
:
pip install sightseer
Model Architectures (as of now)
- YOLOv3 (Darknet by Joseph Redmon)
Facebook AI's Mask R-CNN will be out in the v1.1.0 release. For more information on model release, check out the Roadmap.
Components of sightseer
The package comes with 4 major components that help with different parts of the object detection process all the way from preparing your raw data to getting predictions and displaying them.
Component | Description |
---|---|
Sightseer | Obtains image data or video footage |
Proc | Provides image/frame-wise annotation and inter-format conversion tools |
Zoo | Stores the wrappers over all state-of-the-art models and configs |
Serve | Provides deployment and model serving protocols and services |
If not using custom datasets, Sightseer
and Zoo
are the submodules majorly used for generic predictions from pre-trained models. When there is custom data involved, you can use Proc
to annotate your datasets and even convert them between XML/JSON/CSV/TFRecord formats.
Serve
is an experimental productionising submodule that helps deploy your models on cloud services like AWS and GCP. For more details on future tools and services, check out the Roadmap.
Features
1. Loading images
Footage or raw images can be rendered using Sightseer
before being ingested into models or further preprocessed.
from sightseer import Sightseer
ss = Sightseer()
image = ss.load_image("path/to/image")
Support for video, webcam footage, and screen recording will be out in the coming v1.1.0 release.
2. Using models from sightseer.zoo
Once installed, any model offered by sightseer
can be accessed in less than 10 lines of code. For instance, the code to use the YOLOv3 (Darknet) model is as follows:
from sightseer import Sightseer
from sightseer.zoo import YOLOv3Client
from pprint import pprint
yolo = YOLOv3Client()
yolo.load_model() # downloads weights
# loading image from local system
ss = Sightseer()
image = ss.load_image("./images/road.jpg")
# getting labels, confidence scores, and bounding box data
preds, pred_img = yolo.predict(image, return_img=True)
pprint (preds)
ss.render_image(pred_img)
This can even be converted into a Command-line Interface (CLI) using arguments from argparse
.
Contributing
Suggestions, improvements, and enhancements are always welcome! If you have any issues, please do raise one in the Issues section. If you have an improvement, do file an issue to discuss the suggestion before creating a PR.
All ideas – no matter how outrageous – welcome!
Licence
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 sightseer-1.0.8-py3-none-any.whl
Algorithm | Hash digest | |
---|---|---|
SHA256 | 6c0355e56d8468a369e5769d669c0d171722592c65b0860c7cadb413324cbcc0 |
|
MD5 | 537950dfb1848d9ba1573e8e75cc7fb3 |
|
BLAKE2b-256 | ac6505fbb60d3b0bcf9f4337d95e2fba992f1a819bbad3c731f2caf622eb934b |