nncf

import nncf import openvino as ov import torch from torchvision import datasets, transforms, models import os # 1. Load a pre-trained PyTorch model model = models.resnet18(weights=models.ResNet18_Weights.IMAGENET1K_V1) model.eval() # 2. Convert PyTorch model to OpenVINO Model # Create a dummy input for tracing dummy_input = torch.randn(1, 3, 224, 224) ov_model = ov.convert_model(model, example_input=dummy_input) # 3. Prepare a calibration dataset (example with random data) # In a real scenario, use representative data from your dataset class RandomDataset(torch.utils.data.Dataset): def __init__(self, size=300): self.size = size def __len__(self): return self.size def __getitem__(self, idx): return torch.randn(3, 224, 224), 0 # dummy label calibration_dataset = RandomDataset() # 4. Define a transformation function for the calibration dataset def transform_fn(data_item): return data_item[0].numpy() # NNCF expects NumPy array for OpenVINO PTQ # 5. Apply Post-Training Quantization (PTQ) print("Applying Post-Training Quantization...") quantized_ov_model = nncf.quantize( ov_model, nncf.Dataset(calibration_dataset, transform_fn) ) # 6. Save the quantized OpenVINO model output_dir = "./quantized_model" os.makedirs(output_dir, exist_ok=True) model_path = os.path.join(output_dir, "resnet18_quantized.xml") ov.save_model(quantized_ov_model, model_path) print(f"Quantized model saved to {model_path}") # To load and use the quantized model: # core = ov.Core() # loaded_model = core.read_model(model_path) # compiled_model = core.compile_model(loaded_model, "CPU") # # Inference goes here # print("Model loaded and compiled for inference.")