'--protocol', type=str, required=False, default='HTTP', help='Protocol (HTTP/gRPC) used to communicate with ' + 'the inference service. Default is HTTP.') parser.add_argument('image_filename', type=str, help='Input image.') FLAGS = parser.parse_args() try: if FLAGS.protocol.lower() == "grpc": # Create gRPC client for communicating with the server triton_client = grpcclient.InferenceServerClient(FLAGS.url) else: # Create HTTP client for communicating with the server triton_client = httpclient.InferenceServerClient(FLAGS.url) except Exception as e: print("context creation failed: " + str(e)) sys.exit() # Make sure the model matches our requirements, and get some # properties of the model that we need for preprocessing try: model_metadata = triton_client.get_model_metadata( model_name=FLAGS.model_name, model_version=FLAGS.model_version) except InferenceServerException as e: print("failed to retrieve the metadata: " + str(e)) sys.exit() try: model_config = triton_client.get_model_config(
'--verbose', action="store_true", required=False, default=False, help='Enable verbose output') parser.add_argument( '-u', '--url', type=str, required=False, default='localhost:8000', help='Inference server URL. Default is localhost:8000.') FLAGS = parser.parse_args() try: triton_client = httpclient.InferenceServerClient(url=FLAGS.url, verbose=FLAGS.verbose) except Exception as e: print("context creation failed: " + str(e)) sys.exit() model_name = 'simple' # Infer inputs = [] outputs = [] inputs.append(httpclient.InferInput('INPUT0', [1, 16], "INT32")) inputs.append(httpclient.InferInput('INPUT1', [1, 16], "INT32")) # Create the data for the two input tensors. Initialize the first # to unique integers and the second to all ones. input0_data = np.arange(start=0, stop=16, dtype=np.int32)