The TensorFlow library was compiled to use AVX instructions, but these aren't available on your machine.

[Technerder]

Is there a binary release file in this repository which uses a Tensorflow installation which runs on CPU's without AVX instructions?

CPU: Intel i7 620m

Full error: ALSA lib pcm.c:2495:(snd_pcm_open_noupdate) Unknown PCM cards.pcm.rear ALSA lib pcm.c:2495:(snd_pcm_open_noupdate) Unknown PCM cards.pcm.center_lfe ALSA lib pcm.c:2495:(snd_pcm_open_noupdate) Unknown PCM cards.pcm.side ALSA lib pcm_route.c:867:(find_matching_chmap) Found no matching channel map ALSA lib pcm_route.c:867:(find_matching_chmap) Found no matching channel map ALSA lib pcm_route.c:867:(find_matching_chmap) Found no matching channel map ALSA lib pcm_route.c:867:(find_matching_chmap) Found no matching channel map Warning: Failed to load parameters from model.pb.params 2019-05-05 22:46:21.461690: F tensorflow/core/platform/cpu_feature_guard.cc:37] The TensorFlow library was compiled to use AVX instructions, but these aren't available on your machine. Exception in thread Thread-1: Traceback (most recent call last): File "/usr/lib/python3.5/threading.py", line 914, in _bootstrap_inner self.run() File "/usr/lib/python3.5/threading.py", line 862, in run self._target(*self._args, **self._kwargs) File "/usr/local/lib/python3.5/dist-packages/precise_runner/runner.py", line 197, in _handle_predictions prob = self.engine.get_prediction(chunk) File "/usr/local/lib/python3.5/dist-packages/precise_runner/runner.py", line 65, in get_prediction return float(self.proc.stdout.readline()) ValueError: could not convert string to float:

[LuggyLuke]

If you check the forks, i did one some time back where i used an older version of tensorflow.

[Technerder]

@LuggyLuke I'm trying to use your fork however I'm running into an issue when trying to run the example code

Error: Precise/libpython3.6m.so.1.0': dlopen: /lib/x86_64-linux-gnu/libc.so.6: versionGLIBC_2.25' not found (required by Precise/libpython3.6m.so.1.0)`

Also, would you happen to have an updated version of your fork which I would be able to use?

[LuggyLuke]

Its quite a while since i forked that and for now it runs on my server. So i dont have any intentions to update. There are a cpuple of issue comments where you can find out how to do it as well. Sadly i couldnt even tell you how to build it. As for your error, i wont be any help either since i am in no way an expert :-(. My only guess would be to check your dependencies and versions.

[Technerder]

The latest version works perfectly fine on my raspberry pi from what I can tell. But it still really sucks how the current builds won't work on machines without AVX support. Hopefully someone will build a non AVX build for the repo. (I'd do it myself but compiling tensorflow myself has not been working out so far)