tensorflow-serving-api

import grpc import numpy as np from tensorflow_serving.apis import prediction_service_pb2_grpc, predict_pb2 from tensorflow.core.framework import tensor_pb2 from tensorflow.python.framework import dtypes # for tf.float32, etc. (usually for older TF, or explicit type) # NOTE: This quickstart assumes a TensorFlow Serving server is already running. # For example, via Docker: # docker run -p 8500:8500 --name tfserving_test \ # --mount type=bind,source=/path/to/your/model,target=/models/your_model \ # -e MODEL_NAME=your_model -t tensorflow/serving & # Configuration for your model server SERVER_ADDRESS = 'localhost:8500' MODEL_NAME = 'your_model' SIGNATURE_NAME = 'serving_default' def make_prediction(input_data: np.ndarray): """Sends a prediction request to TensorFlow Serving via gRPC.""" channel = grpc.insecure_channel(SERVER_ADDRESS) stub = prediction_service_pb2_grpc.PredictionServiceStub(channel) request = predict_pb2.PredictRequest() request.model_spec.name = MODEL_NAME request.model_spec.signature_name = SIGNATURE_NAME # Convert NumPy array to TensorProto tensor_proto = tensor_pb2.TensorProto() tensor_proto.CopyFrom(np.asarray(input_data).astype(np.float32)._to_proto()) # TensorFlow 2.x often requires explicit type, e.g., using a dtypes enum # tensor_proto.dtype = dtypes.float32.as_datatype_enum # Example for explicit type request.inputs['input_tensor_name'].CopyFrom(tensor_proto) # Replace 'input_tensor_name' with your model's input name try: response = stub.Predict(request, 10.0) # 10-second timeout print("Prediction successful:") # Process response.outputs to get results # Example: print(response.outputs['output_tensor_name']) for key, val in response.outputs.items(): print(f" Output '{key}': {np.array(val.float_val) if val.float_val else val}") except grpc.RpcError as e: print(f"Error making prediction: {e.code()} - {e.details()}") if __name__ == '__main__': # Example usage: a simple 1x5 float array as input sample_input = np.array([[1.0, 2.0, 3.0, 4.0, 5.0]]) make_prediction(sample_input)