Error happened when using WASM/WebGL backend of tfjs 2.0.1 to run Image Classification example.

[BruceDai]

Error: The highest priority backend 'wasm' has not yet been initialized. Make sure to await tf.ready() or await tf.setBackend() before calling other methods

@NALLEIN @akineeic please help investigate and fix it, thanks.

[akineeic]

The tfjs-backend-wasm module try to find simd binary when I specify a wasm file. I open an issue to upstream and this seems to an issue will be fixed in next release. This issue can be temporarily fixed by adding code as following to webpack the simd binary: import simdPath from '../../../node_modules/@tensorflow/tfjs-backend-wasm/dist/tfjs-backend-wasm-simd.wasm';

Or we can just back to the old version and wait for their new release.

[huningxin]

Thanks @akineeic , please send a PR to implement the workaround for current release. We can upgrade to the next release when it is available.

[ibelem]

@BruceDai please track the upstream bug status.

[akineeic]

I tried with the newest version(2.3.0) of tfjs-beckend-wasm but some errors still appeared. We need to wait for the next release as the developer said. Track with the upstream issue.

[BruceDai]

@akineeic Thanks for this information.