RPI3: Executor failed to create kernel _FusedConv2D

[njbuch]

Please provide us with the following information:

This issue is for a: (mark with an x)

- [x ] bug report -> please search issues before submitting
- [ ] feature request
- [ ] documentation issue or request
- [ ] regression (a behavior that used to work and stopped in a new release)

Minimal steps to reproduce

• download the complete project
• build and push
• deploy and check logs

Any log messages given by the failure

Caused by op 'conv1/conv1', defined at: File "/usr/lib/python3.5/threading.py", line 882, in _bootstrap self._bootstrap_inner() 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/lib/python3.5/socketserver.py", line 625, in process_request_thread self.finish_request(request, client_address) File "/usr/lib/python3.5/socketserver.py", line 354, in finish_request self.RequestHandlerClass(request, client_address, self) File "/usr/lib/python3.5/socketserver.py", line 681, in init self.handle() File "/usr/local/lib/python3.5/dist-packages/werkzeug/serving.py", line 293, in handle rv = BaseHTTPRequestHandler.handle(self) File "/usr/lib/python3.5/http/server.py", line 422, in handle self.handle_one_request() File "/usr/local/lib/python3.5/dist-packages/werkzeug/serving.py", line 328, in handle_one_request return self.run_wsgi() File "/usr/local/lib/python3.5/dist-packages/werkzeug/serving.py", line 270, in run_wsgi execute(self.server.app) File "/usr/local/lib/python3.5/dist-packages/werkzeug/serving.py", line 258, in execute application_iter = app(environ, start_response) File "/usr/local/lib/python3.5/dist-packages/flask/app.py", line 2309, in call return self.wsgi_app(environ, start_response) File "/usr/local/lib/python3.5/dist-packages/flask/app.py", line 2292, in wsgi_app response = self.full_dispatch_request() File "/usr/local/lib/python3.5/dist-packages/flask/app.py", line 1813, in full_dispatch_request rv = self.dispatch_request() File "/usr/local/lib/python3.5/dist-packages/flask/app.py", line 1799, in dispatch_request return self.view_functions[rule.endpoint](req.view_args) File "app.py", line 41, in predict_image_handler results = predict_image(img) File "/app/predict.py", line 56, in predict_image tf.import_graph_def(graph_def, name='') File "/usr/local/lib/python3.5/dist-packages/tensorflow/python/util/deprecation.py", line 507, in new_func return func(args, **kwargs) File "/usr/local/lib/python3.5/dist-packages/tensorflow/python/framework/importer.py", line 442, in import_graph_def _ProcessNewOps(graph) File "/usr/local/lib/python3.5/dist-packages/tensorflow/python/framework/importer.py", line 235, in _ProcessNewOps for new_op in graph._add_new_tf_operations(compute_devices=False): # pylint: disable=protected-access File "/usr/local/lib/python3.5/dist-packages/tensorflow/python/framework/ops.py", line 3433, in _add_new_tf_operations for c_op in c_api_util.new_tf_operations(self) File "/usr/local/lib/python3.5/dist-packages/tensorflow/python/framework/ops.py", line 3433, in for c_op in c_api_util.new_tf_operations(self) File "/usr/local/lib/python3.5/dist-packages/tensorflow/python/framework/ops.py", line 3325, in _create_op_from_tf_operation ret = Operation(c_op, self) File "/usr/local/lib/python3.5/dist-packages/tensorflow/python/framework/ops.py", line 1801, in init self._traceback = tf_stack.extract_stack()

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:

 [[node conv1/conv1 (defined at /app/predict.py:56) ]]

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

The image classifier should be able to classify images... ;)

OS and Version?

Building and pushing from Win 10. Running edge device is Rpi 3+

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

---

Thanks! We'll be in touch soon.

[nanowireUK]

Saw same issue as described. Fix was changing line in requirements.txt and rebuilding tensorflow==1.12.0

[emmanuel-bv]

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.