OpenViSTAI · Agents · Blockchain · Crypto
Submit a project
Menu
Image & Video AI

Celestial Bodies Detection

Celestial Bodies Detection is a TensorFlow image-classification project with a Flask web app for identifying broad categories of celestial objects, including planets, galaxies, satellites and comets. The interface accepts an uploaded image or an image URL, then presents the image with classification labels and related information.

Explore the practical guide ↓

Independent OpenViST project profile, based on linked sources.

Celestial Bodies Detection — OpenViST project profile in Image & Video AI.
OpenViST project illustration. See the linked sources for product details.
Understand the project

Practical overview

When it fits

Use the hosted interface for image classification, or the repository when you want to evaluate the included model, inspect the Flask app, or follow its retraining instructions.

Who it is for

  • People exploring image classification through astronomy-themed examples.
  • Python developers studying or adapting a TensorFlow model and Flask interface.

Documented uses

  • Submit an image or image URL for celestial-object classification.
  • View labels and class-percentage results for an image.
  • Evaluate the included model on an image or retrain it using an image directory.
Before you choose

Requirements & limits

  • The repository identifies its license as GPL-3.0.
  • The documented stack includes Python, TensorFlow and Flask.
  • The README's setup example lists TensorFlow 1.14, Wikipedia and PyYAML; its conda example specifies Python 3.9.

Check current requirements in the official documentation. Source-based guidance does not mean OpenViST has run or independently tested this project.

Source-based practical guide

Evaluate an image with the included model

Run the repository's documented single-image evaluation command.

Before you start

  • The repository's trained files
  • Python and the project's dependencies, including TensorFlow

Steps

  1. Set up a Python environment and install the listed requirements.

  2. From the repository, run the command below, or substitute another image path.

    Documented command
    python label_image.py test_data/uranus/000.jpg

Expected outcome

The model evaluates the selected image for classification.

Guide limitations

  • The README documents evaluation with its included test images or another image path; it does not specify expected accuracy.
Documentation 1 ↗
Source-based practical guide

Retrain the classifier on an image directory

Start the repository's documented model-retraining process with an image directory.

Before you start

  • Python environment with the listed requirements installed
  • An image directory organized for training

Steps

  1. Set up the Python environment and install the repository requirements.

  2. Run the documented the command below command with its bottleneck, model, summary, graph, label and image-directory arguments.

    Documented command
    python retrain.py

Expected outcome

The command is configured to retrain the classifier and write graph and label output files.

Guide limitations

  • The README says Inception is downloaded automatically during training.
  • Its example GPU setup is optional and specifically references an Nvidia GTX 1080.
Documentation 1 ↗
Evidence and transparency

Sources & review

Official repository ↗
Source record details
Source availability
Active
Sources checked
12 October 2026
Original website title
ritwik12/Celestial-bodies-detection · Official homepage title · retained in its source language
How we review sourcesSuggest a correction