webml-polyfill
webml-polyfill copied to clipboard
intel
Deprecated, the Web Neural Network Polyfill project has been moved to https://github.com/webmachinelearning/webnn-polyfill
Our API now use explicit padding to process the 'valid' and 'same' PaddingCode, will cause that some new OpenVINO models (IR v10) such as FaceNet fail to run, error is...
https://github.com/acerwebai/VangoghCrazyWorld The TensorFlow Lite model: Tflite ops | polyfill | tfjs | webnn | contents | workaround -- | -- | -- | -- | -- | -- Transpose |...
**Test Env:** Platform: Android(Pixel 3) **Actual Result:** An error occurs for WebGL on Android: `Requested texture size [4128x4128] greater than WebGL maximum on this browser / GPU [4096x4096]` **How to...
It's Q4 IMBO, we must complete it, support INT8 models for Semantic Segmentation and Image Classification in Web AI Workload. @BruceDai @mingmingtasd @lisa0314
We need to optimize Deeplab performance in Q4. @ibelem will integration INT8 models based on @mingmingtasd and @lisa0314 's efforts in October.
Current we only use Image Classification with two models to run regression checking. TODO, compare output tensors with based output tensors for regression checking, this enhancement would benefit checking all...
End-users must select framework, category, model, backend, preference and iterations one by one then run the workload testing, even when they played for a while and went back. Please add...
Test Environments: • DNNL and Discrete IE-MKLDNN tested on [e306860](http://powerbuilder.sh.intel.com/project/webnn/nightly/e306860/win_x64_SUCCEED/) • Integrated IE-MKLDNN tested on [6f1b378](http://powerbuilder.sh.intel.com/project/webnn/nightly/6f1b378/win_x64_SUCCEED/) • Native OpenVINO IE-MKLDNN tested with openvino toolkit 2020.3 • CPU: Intel i7-1065G7 CPU...
