Computer Vision related operations, for example Object Detection on images. This project purely focused on cross-platform applications & we can run small AI/ML models on our mobile phones in offline mode.This project is buid onkivy,kivymdand usesonnxruntime,numpy,opencvetc. to perform the tasks. This is still at very early phase before this project matures at some level.
Image in local storage. It uses SSD-MobilenetV1Camera & detect objects on the image. It also uses the same model as above.Image Prediction: if you have an image of a single object & want to get top-5 predictions about the image, just upload & click Classify. It uses ResNet18 which has around 1000 categories.Identify Species from a photo. It uses Google SpeciesNet & it has around 2000 odd species.No Ads, completely open-source (free).trackers, no data collection etc. Actually you own your data & your app.DCIM or Downloads or Pictures or any subfolders of this three folders. Same goes while saving the output image too.Landscape mode only, so you may need to rotate your phone to capture it properly.Android 9git clone https://github.com/daslearning-org/vision-ai.git1cd vision-ai/onnx/
2pip install -r requirements.txt # virtual environment is recommended
3python main.pyWSL or any Virtual Machine. As of now the buildozer tool works on Python version 3.11 at maximum. I am going to use Python 3.111# add the python repository
2sudo add-apt-repository ppa:deadsnakes/ppa
3sudo apt update
4
5# install all dependencies.
6sudo apt install -y ant autoconf automake ccache cmake g++ gcc libbz2-dev libffi-dev libltdl-dev libtool libssl-dev lbzip2 make ninja-build openjdk-17-jdk patch patchelf pkg-config protobuf-compiler python3.11 python3.11-venv python3.11-dev
7
8# optionally we can default to python 3.11
9sudo ln -sf /usr/bin/python3.11 /usr/bin/python3
10sudo ln -sf /usr/bin/python3.11 /usr/bin/python
11sudo ln -sf /usr/bin/python3.11-config /usr/bin/python3-config
12
13# optionally you may check the java installation with below commands
14java -version
15javac -version
16
17# install python modules
18git clone https://github.com/daslearning-org/vision-ai.git
19cd vision-ai/onnx/
20python3.11 -m venv .env # create python virtual environment
21source .env/bin/activate
22pip install -r req_android.txt
23
24# build the android apk
25buildozer android debug # this may take a good amount of time for the first time & will generate the apk in the bin directory