Skip to content
This repository has been archived by the owner on Mar 19, 2023. It is now read-only.

Commit

Permalink
Update readme links
Browse files Browse the repository at this point in the history
  • Loading branch information
robmarkcole committed Sep 14, 2019
1 parent 612c821 commit 99a09d4
Showing 1 changed file with 3 additions and 3 deletions.
6 changes: 3 additions & 3 deletions README.md
Original file line number Diff line number Diff line change
@@ -1,12 +1,12 @@
# HASS-Deepstack-object
[Home Assistant](https://www.home-assistant.io/) custom components for using Deepstack object detection. [Deepstack](https://www.deepquestai.com/insider/) is a service which runs in a docker container and exposes deep-learning models via a REST API. There is no cost for using Deepstack, although you will need a machine with 8 GB RAM. On your machine with docker, pull the latest image (approx. 2GB):
[Home Assistant](https://www.home-assistant.io/) custom components for using Deepstack object detection. [Deepstack](https://python.deepstack.cc/) is a service which runs in a docker container and exposes deep-learning models via a REST API. There is no cost for using Deepstack, although you will need a machine with 8 GB RAM. On your machine with docker, pull the latest image (approx. 2GB):

```
sudo docker pull deepquestai/deepstack
```
**Recommended OS** Deepstack docker containers are optimised for Linux or Windows 10 Pro. Mac and regular windows users my experience performance issues.

**GPU users** Note that if your machine has an Nvidia GPU you can get a 5 x 20 times performance boost by using the GPU, [read the docs here](https://deepstackpython.readthedocs.io/en/latest/gpuinstall.html#gpuinstall).
**GPU users** Note that if your machine has an Nvidia GPU you can get a 5 x 20 times performance boost by using the GPU.

**Legacy machine users** If you are using a machine that doesn't support avx or you are having issues with making requests, Deepstack has a specific build for these systems. Use `deepquestai/deepstack:noavx` instead of `deepquestai/deepstack` when you are installing or running Deepstack.

Expand All @@ -28,7 +28,7 @@ This should return the predictions for that image.
Place the `custom_components` folder in your configuration directory (or add its contents to an existing `custom_components` folder). Then configure object detection. Note that at we use `scan_interval` to (optionally) limit computation, [as described here](https://www.home-assistant.io/components/image_processing/#scan_interval-and-optimising-resources).

## Object Detection
Deepstack [object detection](https://deepstackpython.readthedocs.io/en/latest/objectdetection.html) can identify 80 different kinds of objects, including people (`person`) and animals. On you machine with docker, run Deepstack with the object detection service active on port `5000`:
Deepstack [object detection](https://python.deepstack.cc/object-detection) can identify 80 different kinds of objects, including people (`person`) and animals. On you machine with docker, run Deepstack with the object detection service active on port `5000`:
```
sudo docker run -e VISION-DETECTION=True -e API-KEY="Mysecretkey" -v localstorage:/datastore -p 5000:5000 deepquestai/deepstack
```
Expand Down

0 comments on commit 99a09d4

Please sign in to comment.