Avi

> you'd probably also convert the [0,255] range to [0,1] with a tf.div(255). Interesting, by adding ```diff - const buffer = tf.browser.fromPixels(elImage); + const buffer = tf.browser.fromPixels(elImage).div(255); ``` and having...

@danwexler What do I do next?

@vladmandic > example of a pre&post processing for object detection of a non-strided model: https://github.com/vladmandic/mb3-centernet > example of a pre&post processing for object detection of a strided model: https://github.com/vladmandic/nanodet I'm...

I think I can get the required info regarding the inputs, based on the Python model How can I keep in touch so I can share Drive files with you?

In Text Extractor's case I can copy as usual, but it will simply not be listed in the clips list

Last time I tried, I _was_ able to paste

[`--target`](https://extensionworkshop.com/documentation/develop/web-ext-command-reference/#web-ext-run:~:text=variable%3A%20%24WEB_EXT_PREF-,%2D%2Dtarget,-%2C%20%2Dt) supports `chromium`, `firefox-desktop`, `firefox-android`, but not Edge

Very cool, this works nicely: ```bash web-ext run --no-config-discovery --start-url URL --verbose --target chromium --source-dir build/chrome-mv3-dev --chromium-binary "%ProgramFiles(x86)%\Microsoft\Edge\Application\msedge.exe" ``` Adding such an example snippet to the documentation and/or README would...

Does it work the same way on Linux/macOS? I.e. I provide the binary location?

The reason I made my [browser extension](https://github.com/avi12/youtube-downloader) in the first place is that it doesn't need a server to work but instead use the user's computational power