Robin Cole

In the sighthound integration we are disabling scanning with: ```python @property def should_poll(self): """Return the polling state.""" return False ``` Perhaps this should just be the default for `ImageProcessingEntity`

@arsaboo I am using that basic approach [here](https://www.hackster.io/robin-cole/motion-activated-image-capture-and-classification-of-birds-6ef1ce#toc-tying-it-all-together-8), with [folder_watcher](https://www.home-assistant.io/components/folder_watcher/) component to detect new saved files and display them on a local_file camera. It works but is a bit hacky....

Well we already let people save images, it is opt-in. I actually like your (scratched) suggestion in the other thread that the processed image (with bounding box) be displayed on...

OK so we have a range of opinions, how to progress forward to action here?

To update, I moved the bounding box save method to the image processing integration. I adopted the approach used by tensorflow. Now is a good time to make a decision...

Update: saving of images to disk is just creating so many tedious issues, I am now leaning away from this approach. Much better to have another camera that displays the...

+1 having this issue

No problem! I did not sign up for the competition but appears as it has finished I cannot. I tried downloading but as this is 53GB I guess I wont...

yes they are large gz. NP I will download elsewhere and create a NIR version for use here, thanks!

Attempt 1, am guessing and getting errors https://github.com/robmarkcole/fire-detection-from-images/blob/master/pytorch/icevision/icevision_firenet_faster_rcnn_anchors.ipynb