This adds direct javascript access to the camera (with permission requests). Capturing an image with the camera now happens right on the detect page and not a separate window.
This also opens the possibility of live detection on the web app.
Reviewed-on: Georgi_Lab/ALVINN_f7#116
This updates the local detection to yolov8-based models from the older yolov5 based models.
This includes significant additional post-processing of the raw yolov8 output, but also means that the smaller nano yolo model is available as well as all of the updated ALVINN thorax training data.
Signed-off-by: Justin Georgi <justin.georgi@gmail.com>
Reviewed-on: Georgi_Lab/ALVINN_f7#115
Tensorflow fetch failed on android with basic configuration. More specific protocol and location for model.json required.
Signed-off-by: Justin Georgi <justin.georgi@gmail.com>
Reviewed-on: Georgi_Lab/ALVINN_f7#99
Closes: #92
This adds a new link to the left panel to open a contact form. Filling out the form will allow the user to submit a comment which will be registered as a new issue on this repo.
Reviewed-on: Georgi_Lab/ALVINN_f7#98
Each region now has an appropriate placeholder image instead of a generic image and the get image button is a more obvious icon.
Reviewed-on: Georgi_Lab/ALVINN_f7#84
Closes: #77
If the user clocks on the image, any detections present at that location will be selecting in descending order of confidence.
Signed-off-by: Justin Georgi <justin.georgi@gmail.com>
Reviewed-on: Georgi_Lab/ALVINN_f7#78
Closes: #70
Adds a prelaoder animation to the results container while the image is loading and being processed for detections.
Signed-off-by: Justin Georgi <justin.georgi@gmail.com>
Reviewed-on: Georgi_Lab/ALVINN_f7#72
Closes#71
I *think* AGPL makes the most sense based on what I've seen. GPL might work too, but as I understand it this extends GPL to server and service usages as well which could very well include ALVINN in the end.
Signed-off-by: Justin Georgi <justin.georgi@gmail.com>
Reviewed-on: Georgi_Lab/ALVINN_f7#73
The pre app disclaimer makes more sense initialized by the app and not the home page. This PR moves the popup to the app and adds basic store functionality to give global access to the state of the apps agreement.
Signed-off-by: Justin Georgi <justin.georgi@gmail.com>
Reviewed-on: Georgi_Lab/ALVINN_f7#68
The same disclaimer language on the about page now appears in a modal popup the first time the user loads alvinn. Further function is not available until the user agrees to the disclaimer
Signed-off-by: Justin Georgi <justin.georgi@gmail.com>
Reviewed-on: Georgi_Lab/ALVINN_f7#66
Moving panel to page element was resulting in opening errors after more than one page opened.
viewedAll computer property was returning errors before result data was fetched.
Signed-off-by: Justin Georgi <justin.georgi@gmail.com>
Reviewed-on: Georgi_Lab/ALVINN_f7#65
Closes: #48
This PR should allow the user to upload an image that has been taken with the camera and the associated detection information to a file server. These file can then be used to add data to ALVINN's models.
Current upload destination is set to a file drop folder in Georgi Lab Nextcloud, but eventually (maybe) should be changed to some dedicated ALVINN backend.
Also, prediction data is still not formatted in any specific way. It is just a JSON array of (top, left, bottom, right, label) objects.
Reviewed-on: Georgi_Lab/ALVINN_f7#56
Closes: #29
Fixes access to the camera in the android cordova build and maintains access when using the vite build.
Reviewed-on: Georgi_Lab/ALVINN_f7#45
