Na Li comments

Results 17 comments of


                                            Na Li

Blazeface result is not correct on WASM backend

Hi @deepanshusharma012 , thank you for reporting this. I tested it with our own demo, same problem. Actually we're working on a new BlazeFace model, which is going to be...

Blazeface result is not correct on WASM backend

Sorry, I actually meant Q4. I replied in September, and we are already thinking for Q4 :) Sorry for the confusion.

Blazeface result is not correct on WASM backend

Added @ahmedsabie who is working on it.

Blazeface result is not correct on WASM backend

We have deprecated blazeface API, please use face-detection instead: https://github.com/tensorflow/tfjs-models/tree/master/face-detection

Blazeface result is not correct on WASM backend

Thank you for testing out the new API, I will investigate.

method `toPixels` is not optimized for `webgl` or `webgpu` backends

Thank you for the example contribution @vladmandic . Can we reference your example in the API doc?

[Perf] The time of Conv2DBackpropInput is very long in BlazePose/hand_detector models in WebGL

This is very informative, thank you @qjia7 ! In the GPUPrograms column, is Conv2DDerInputProgram the packed version and UnpackProgram the unpacked version, both from WebGL backend?

As of v1.5.0 karma-browserstack-launcher often times out

We are also having timeout issue, and we are using 1.4.0.

As of v1.5.0 karma-browserstack-launcher often times out

In our case, we have a very large test suite. This PR that prevent browser inactive looks promising: https://github.com/karma-runner/karma-browserstack-launcher/pull/168 When is it going to be released?

As of v1.5.0 karma-browserstack-launcher often times out

We also experienced the same recently. Upgraded to 1.5.1, and seeing a lot of timeout. Hope this PR can fix the problem.