State-of-the-art Computer Vision and Object Detection for TensorFlow.

Made by Rishabh Anand • https://rish-16.github.io

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.

I'd like to fully credit Huynh Ngoc Anh for their YOLOv3 model architecture code. I've repackaged that chunk as a callable python API wrapper under the model zoo. This project would not be possible without their contribution.

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 Clients (as of now)

1. YOLOv3Client (Darknet by Joseph Redmon)

By popular demand, Tiny YOLO will be out in the v1.2.0 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

Footage or raw images can be rendered using Sightseer before being ingested into models or further preprocessed.

1a. Loading images

fromsightseerimportSightseerss=Sightseer()
image=ss.load_image("path/to/image") # return numpy array representation of image

1b. Loading videos

fromsightseerimportSightseerss=Sightseer()
frames=ss.load_vidsource("path/to/video") # returns nested array of frames

Support for video, webcam footage, and screen recording will be out in the coming v1.2.0 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:

fromsightseerimportSightseerfromsightseer.zooimportYOLOv3Clientyolo=YOLOv3Client()
yolo.load_model() # downloads weights# loading image from local systemss=Sightseer()
image=ss.load_image("./assets/road.jpg")
# getting labels, confidence scores, and bounding box datapreds, pred_img=yolo.predict(image, return_img=True)
ss.render_image(pred_img)

To run the model on frames from a video, you can use the framewise_predict method:

fromsightseerimportSightseerfromsightseer.zooimportYOLOv3Clientyolo=YOLOv3Client()
yolo.load_model() # downloads weights# loading video from local systemss=Sightseer()
frames=ss.load_vidsource("./assets/video.mp4")
"""For best results, run on a GPU"""# getting labels, confidence scores, and bounding box datapreds, pred_frames=yolo.framewise_predict(frames)
ss.render_footage(pred_frames) # plays the video and saves the footage

The module can even be repurposed into a Command-line Interface (CLI) app using the argparse library.

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!

Before committing, please check the Roadmap to see if proposed features are already in-development or not.

Note: Please commit all changes to the development experimentation branch instead of master.

Licence

Apache Licencse 2.0