Closed Christywl closed 4 years ago
I check the two models and found that both of them are mainly composed of FULLY_CONNECTED
. In the tfjs backend FULLY_CONNECTED
is executed by tf.matMul
which is not a binding operation from native C++ code but implemented by JavaScript in tfjs. So it's slower than the previous tflite wasm backend.
Test Env: webml-polyfill commit: https://github.com/intel/webml-polyfill/commit/a58f9f5340ca87eca4cda18db019f42752317f9e Platform: Windows(Dell XPS 13, Intel i5-8250U)
Actual Result: The inference time is larger than WASM(TFLite) for speech models:
How to Reproduce:
Speech Command-->KWS DNN(OpenVINO)
orSpeech Recognition-->wsj_dnn5b