v0.10.6

Minor changes:

• We no longer automatically add the Camera-ID as Tag when auto uploading an image during detection.

Fix:

• Change Type hinting to support older python versions

v0.10.5

Fix a rare bug in detection uploading (detections were not uploaded if n_detections == upload_batch_size)

v0.10.4

Bugfix in detect via SocketIO:

• multiple fast detect calls were not throttled and could break the detector.
• this version uses a asyncio lock to make sure the detection processes are not executed in parallel

v0.10.3

Use provided ssl certificate for SIO connection to the learning loop host

v0.10.2

Introduce optional .env variable LOOP_SSL_CERT_PATH. This allows to specify the SSL certificate source used by the httpx.asyncclient

v0.10.1

Fixes a bug where no detections were uploaded after one detection file having 'batch_size' detections in it.

v0.10.0

In this version we refactored much of the code. The goal was to improve readability and to remove unused and redundant code.
There is only few changes in functionality, the most relevant one is that the trainer node now also receives the "model size" when downloading a model from the learning loop.

v0.9.3

New features:

• This version introduces the /about endpoint to provide introspection of what model is currently running on a detector node or if an update is in progress. This is a necessary precondition for zauberzeug/rosys#33.

v0.9.2

fix:

• check only ones for corrupted images before running detections

v0.9.1

Same as v0.9.0, but v0.9.0 used wrong commit