https://github.com/cloud-annotations/object-detection-live-stream
🔴 Real-Time Object Detection on a Livestream with TensorFlow.js
https://github.com/cloud-annotations/object-detection-live-stream
hls livestream machine-learning object-detection tensorflow
Last synced: 3 months ago
JSON representation
🔴 Real-Time Object Detection on a Livestream with TensorFlow.js
- Host: GitHub
- URL: https://github.com/cloud-annotations/object-detection-live-stream
- Owner: cloud-annotations
- License: mit
- Created: 2019-08-10T18:08:57.000Z (almost 6 years ago)
- Default Branch: master
- Last Pushed: 2020-04-13T13:08:49.000Z (about 5 years ago)
- Last Synced: 2025-03-23T06:11:19.878Z (3 months ago)
- Topics: hls, livestream, machine-learning, object-detection, tensorflow
- Language: HTML
- Homepage:
- Size: 27.2 MB
- Stars: 15
- Watchers: 3
- Forks: 2
- Open Issues: 4
-
Metadata Files:
- Readme: README.md
- License: LICENSE
Awesome Lists containing this project
README
# Object Detection Live Stream
## Setup
`git clone` the repo and `cd` into it by running the following command:
```bash
git clone https://github.com/cloud-annotations/object-detection-live-stream.git
cd object-detection-live-stream
```
### `npm install`
> **Note: You’ll need to have Node 8.10.0 or later on your local development machine.** You can use [nvm](https://github.com/creationix/nvm#installation) (macOS/Linux) or [nvm-windows](https://github.com/coreybutler/nvm-windows#node-version-manager-nvm-for-windows) to easily switch Node versions between different projects.
## Run the App
### `npm start`
Open [http://localhost:3000](http://localhost:3000) to view it in the browser.
## Bonus: Add a Custom TensorFlow.js Model to the App
You can find an in depth walkthrough for training a TensorFlow.js model [here](https://github.com/cloud-annotations/training/).
Once trained, copy the generated `model_web` directory and paste it into the `public` folder of this repo.