/intel-openvino-colab

Primary LanguageJupyter Notebook

Intel-OpenVINO-Colab

Using Google Colab to do inference using Intel OpenVINO.

Tutorial

Intel OpenVINO on Google Colab

How to use

Step 1: Importing Libraries. Ref: AllModels.ipynb

!pip install openvino

Step 2: Setting up environment. Ref: AllModels.ipynb

from openvino.inference_engine import IENetwork 
from openvino.inference_engine import IECore
import warnings
from google.colab.patches import cv2_imshow
warnings.filterwarnings("ignore", category=DeprecationWarning)

def load_IR_to_IE(model_xml):
    ### Load the Inference Engine API
    plugin = IECore()
    ### Loading the IR files to IENetwork class
    model_bin = model_xml[:-3]+"bin" 
    network = IENetwork(model=model_xml, weights=model_bin)
    ### Loading the network
    executable_net = plugin.load_network(network,"CPU")
    print("Network succesfully loaded into the Inference Engine")
    return executable_net
    
def synchronous_inference(executable_net, image):
    ### Get the input blob for the inference request
    input_blob = next(iter(executable_net.inputs))
    ### Perform Synchronous Inference
    result = executable_net.infer(inputs = {input_blob: image})
    return result

For use cases refer notebook.

Notebooks

Demo1: Inference Demo

Demo2: IE File Generation and inference

References

The model descriptions have been borrowed from Intel and code has been adapted from this repository.