101-tensorflow-to-openvino: TensorFlow to OpenVINO Model Conversion Tutorial


Thu Jun 09 2022 16:58:46 GMT+0000 (UTC)

Saved by @OpenVINOtoolkit #python #openvino #openvino-notebook #tensorflow

# Imports
import time
from pathlib import Path

import cv2
import matplotlib.pyplot as plt
import numpy as np
from IPython.display import Markdown
from openvino.runtime import Core

# Settings
# The paths of the source and converted models
model_path = Path("model/v3-small_224_1.0_float.pb")
ir_path = Path(model_path).with_suffix(".xml")

# Convert TensorFlow Model to OpenVINO IR Format
# Construct the command for Model Optimizer
mo_command = f"""mo
                 --input_model "{model_path}" 
                 --input_shape "[1,224,224,3]" 
                 --data_type FP16 
                 --output_dir "{model_path.parent}"
mo_command = " ".join(mo_command.split())
print("Model Optimizer command to convert TensorFlow to OpenVINO:")

# Run Model Optimizer if the IR model file does not exist
if not ir_path.exists():
    print("Exporting TensorFlow model to IR... This may take a few minutes.")
    ! $mo_command
    print(f"IR model {ir_path} already exists.")

# Load the Model
ie = Core()
model = ie.read_model(model=ir_path, weights=ir_path.with_suffix(".bin"))
compiled_model = ie.compile_model(model=model, device_name="CPU")

# Get Model Information
input_key = compiled_model.input(0)
output_key = compiled_model.output(0)
network_input_shape = input_key.shape

# Load an Image
# The MobileNet network expects images in RGB format
image = cv2.cvtColor(cv2.imread(filename="data/coco.jpg"), code=cv2.COLOR_BGR2RGB)

# Resize image to network input image shape
resized_image = cv2.resize(src=image, dsize=(224, 224))

# Transpose image to network input shape
input_image = np.expand_dims(resized_image, 0)


# Do Inference
result = compiled_model([input_image])[output_key]
result_index = np.argmax(result)

# Convert the inference result to a class name.
imagenet_classes = open("utils/imagenet_2012.txt").read().splitlines()

# The model description states that for this model, class 0 is background,
# so we add background at the beginning of imagenet_classes
imagenet_classes = ['background'] + imagenet_classes


# Timing
num_images = 1000

start = time.perf_counter()

for _ in range(num_images):

end = time.perf_counter()
time_ir = end - start

    f"IR model in Inference Engine/CPU: {time_ir/num_images:.4f} "
    f"seconds per image, FPS: {num_images/time_ir:.2f}"

This short tutorial shows how to convert a TensorFlow MobileNetV3 image classification model to OpenVINO's Intermediate Representation (IR) format using the Model Optimizer tool. After creating the IR, we load the model in OpenVINO's Inference Engine and perform inference with a sample image. If you have not yet installed OpenVINO™, please follow the Installation Guide to install all required dependencies. https://github.com/openvinotoolkit/openvino_notebooks/blob/main/README.md#-installation-guide Link to .bin and .xml files: https://github.com/openvinotoolkit/open_model_zoo/blob/master/models/public/mobilenet-v3-small-1.0-224-tf/model.yml