Closed njbuch closed 5 years ago
Saw same issue as described. Fix was changing line in requirements.txt and rebuilding
tensorflow==1.12.0
Yes this commit shoudl have fixed it: https://github.com/Azure-Samples/Custom-vision-service-iot-edge-raspberry-pi/commit/cf80d80bfd439ef5f30f17ca5bba50382a67ed4c#diff-49f375eebd2ba1e403c3a586f22c22fb
Please sync your repro and rebuild your solution. Let me know if you still hit this issue.
This issue is for a: (mark with an
x
)Minimal steps to reproduce
Any log messages given by the failure
NotFoundError (see above for traceback): No registered '_FusedConv2D' OpKernel for CPU devices compatible with node node conv1/conv1 (defined at /app/predict.py:56) . Registered:
2019-03-10 14:44:50.408362: E tensorflow/core/common_runtime/executor.cc:624] Executor failed to create kernel. Not found: No registered '_FusedConv2D' OpKernel for CPU devices compatible with node {{node conv1/conv1}} . Registered:
Expected/desired behavior
OS and Version?
Versions
Mention any other details that might be useful
The camera capture fails because it cannot create the socket to the image-classifier service.
This might be useful: https://github.com/tensorflow/tensorflow/issues/24732