ch/Caps-Server
1
0
Fork 0
Code Issues Pull Requests Projects Releases Wiki Activity

Update training info in readme

Browse Source
This commit is contained in:
Christoph Hagen 2024-03-01 17:20:02 +01:00
parent e34845ab24
commit 7b3210169a
1 changed files with 1 additions and 25 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

26
Readme.md
View File

@ -51,31 +51,7 @@ Note: The data for the mosaic is currently not updated automatically, since Swif
## Classifier training ## Classifier training
The main server is running on Linux, which doesn't provide the CreateML framework required for classifier training. The main server is running on Linux, which doesn't provide the CreateML framework required for classifier training.
This has to be done on macOS using the `train.swift` script in the `Training` folder. This has to be done on macOS using the [Caps-Train](https://christophhagen.de/git/ch/Caps-Train) repository.
It will:
- Fetch the current image catalog by checking missing and changed images
- Train a classifier on the image set
- Increment the classifier version and upload the new model
- Update the list of caps which can be recognized using the classifier
- Create missing thumbnails for each cap for the cap grid
A configuration file is required to run the training, with a valid access token for the server:
```json
{
"imageDirectory": "../Public/images",
"classifierModelPath": "../Public/classifier.mlmodel",
"trainingIterations": 20,
"serverPath": "https://mydomain.com/caps",
"authenticationToken": "mysecretkey",
}
```
The configuration file `config.json` must be located in the folder from which the script is run.
```bash
swift train.swift
```
## Future work ## Future work
- Create thumbnails on the server using [JPEG](https://github.com/kelvin13/jpeg) - Create thumbnails on the server using [JPEG](https://github.com/kelvin13/jpeg)