1. Learn a model with your own images
Once you have collected and selected your own images (see Collect images to improve the models), you can train your very own model with them.
This is an optional step and only suggested for advances users!
For training the model you will need a python and Jupyter installation.
All current labeled images you can find under ziffer_sortiert_raw
1.0.1 dig-class11 models (digits)
Fork and checkout neural-network-digital-counter-readout.
Install all requirements for running the notebooks.
pip install -r requirements.txt
Put your labeled images into /ziffer_sortiert_raw folder and run
It creates a dig-class11_xxxx_s2.tflite model, you can upload to the config folder on your device and test it.
1.0.2 dig-class100 / dig-cont models (digits)
Fork and checkout neural-network-digital-counter-readout.
All labeled images you can find under Images
Install all requirements for running the notebooks.
pip install -r requirements.txt
Put your labeled images into images/collected/<typeofdevice>/<your_short>/
Run dig-class100-s2.ipynb. The model to upload to your device you can find under '/output'.
1.0.3 ana-class100/ana-cont models (analog pointers)
Fork and checkout neural-network-analog-needle-readout.
All labeled images you can find under data_raw_all
Install all requirements for running the notebooks.
pip install -r requirements.txt
Put your labeled images into images/collected/<typeofdevice>/<your_short>/
After every adding of images you need to run Image_Preparation.ipynb before you train the models.
Run Train_CNN_Analog-Readout_100-Small1_Dropout.ipynb and/or Train_CNN_Analog-Readout_Version-Small2.ipynb. The model to upload to your device you can find in the project folder.
1.1 Share your images
If the results are good you can share the images as pull-request. Please images only!
See Share your images for details.