openvino

import openvino.runtime as ov import numpy as np import os # 1. Create a Core object to manage devices and models core = ov.Core() # 2. Create a dummy model for demonstration # In a real scenario, you would load from .xml/.bin using: # model = core.read_model("path/to/model.xml") input_shape = [1, 3, 224, 224] # Batch, Channels, Height, Width output_shape = [1, 1000] # Batch, Class_count input_node = ov.opset12.parameter(input_shape, ov.Type.f32, name="input") output_node = ov.opset12.result(input_node) # Simple identity model model = ov.Model([output_node], [input_node], "dummy_model") # 3. Compile the model for a specific device # Use os.environ.get for dynamic device selection in production device = os.environ.get("OPENVINO_DEVICE", "CPU") # Example: "GPU", "NPU" print(f"Compiling model for device: {device}") compiled_model = core.compile_model(model, device) # 4. Create an inference request infer_request = compiled_model.create_infer_request() # 5. Prepare input data (random data for dummy model) input_data = np.random.rand(*input_shape).astype(np.float32) infer_request.set_input_tensor(ov.Tensor(input_data)) # 6. Perform inference infer_request.infer() # 7. Get output data output_tensor = infer_request.get_output_tensor() output_data = output_tensor.data print(f"Inference successful. Output shape: {output_data.shape}") print(f"First 5 output values: {output_data.flatten()[:5]}")