Save and Load OpenVINO Model#
This example illustrates how to save and load a model accelerated by openVINO.
In this example, we use a pretrained ResNet18 model. Then, by calling
trace(..., accelerator="openvino"), we can obtain a model accelarated by openVINO method provided by BigDL-Nano for inference. By calling
save(model=..., path=...) , we could save the Nano optimized model to a folder. By calling
load(path=...), we could load the OpenVINO optimized model from a folder.
First, prepare model. We need to load the pretrained ResNet18 model:
import torch from torchvision.models import resnet18 model_ft = resnet18(pretrained=True)
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))
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
Load the Optimized Model#
loaded_model = InferenceOptimizer.load("./optimized_model_ov")
For a model accelerated by OpenVINO, we save the structure of its network. So, the original model is not needed when we load the optimized model.
Inference with the Loaded Model#
with InferenceOptimizer.get_context(loaded_model): x = torch.rand(2, 3, 224, 224) y_hat = loaded_model(x) predictions = y_hat.argmax(dim=1) print(predictions)
📚 Related Readings