View the runnable example on GitHub

Save and Load OpenVINO Model#

This example illustrates how to save and load a model accelerated by openVINO. In this example, we use a ResNet18 model pretrained. Then, by calling trace(model, accelerator="openvino"...), we can obtain a model accelarated by openVINO method provided by BigDL-Nano for inference. By calling save(model_name, path) , we could save the model to a folder. By calling load(path), we could load the model from a folder.

To inference using Bigdl-nano InferenceOptimizer, the following packages need to be installed first. We recommend you to use Miniconda to prepare the environment and install the following packages in a conda environment.

You can create a conda environment by executing:

# "nano" is conda environment name, you can use any name you like.
conda create -n nano python=3.7 setuptools=58.0.4
conda activate nano

📝 Note:

During your installation, there may be some warnings or errors about version, just ignore them.

[ ]:

# Necessary packages for inference accelaration
!pip install --pre --upgrade bigdl-nano[pytorch,inference]

First, prepare model. We use a pretrained ResNet18 model(model_ft in following code) in this example.

[ ]:

import torch
from torchvision.models import resnet18

model_ft = resnet18(pretrained=True)
model_ft.eval()

Accelerate Inference Using OpenVINO

[ ]:

from bigdl.nano.pytorch import InferenceOptimizer

ov_model = InferenceOptimizer.trace(model_ft,
                                    accelerator="openvino",
                                    input_sample=torch.rand(1, 3, 224, 224))

with InferenceOptimizer.get_context(ov_model):
    x = torch.rand(2, 3, 224, 224)
    y_hat = ov_model(x)
    predictions = y_hat.argmax(dim=1)
    print(predictions)

Save Optimized Model The saved model files will be saved at “./optimized_model_ov” directory There are 3 files in optimized_model_ov, users only need to take “.bin” and “.xml” file for further usage:

  • nano_model_meta.yml: meta information of the saved model checkpoint

  • ov_saved_model.bin: contains the weights and biases binary data of model

  • ov_saved_model.xml: model checkpoint for general use, describes model structure

[ ]:

InferenceOptimizer.save(ov_model, "./optimized_model_ov")

Load the Optimized Model

[ ]:

loaded_model = InferenceOptimizer.load("./optimized_model_ov")

Inference with the Loaded Model

[ ]:

with InferenceOptimizer.get_context(loaded_model):
    y_hat = loaded_model(x)
    predictions = y_hat.argmax(dim=1)
    print(predictions)