Jason Mayes

Any updates on this one if feasible for the future to look into?

Team is currently discussing issue to see what may be best path of action for this as WebGL seems to be shared resource unlike like CPU on WebWorker which separates...

I made a slightly simplified version of the code to the demo the original reporter created here: https://codepen.io/jasonmayes/project/editor/DBYaRj Executing this - click the big button at the bottom - and...

The original user who reported the issue can not share their model / all code so instead for now has shared the demo code you see above and put some...

So the team have been researching into how to reduce GPU load when loading models / inference to give time back to browser render to reduce freezing of GUI etc....

I shall let @lina128 reply as she is currently working on the final solution to this which looks very promising in terms of that initial load blocking issue you mentioned...

So this new fix should be out shortly - please tune into our TensorFlow.js updates in May, that is all we can say for now but we look forward to...

Having same issue in this example reported by a user: https://snack.expo.dev/@ageron/tfjs-test-2 Can anyone advise?

Ah interesting. Yes currently Twitter Fetcher is not a class, more like a singleton using the module design pattern originally. I shall add this as something to look into for...

Do you know what size image your code returns?