OpenCV 3 Computer Vision with Python Cookbook

How to do it...

For this recipe, you need to complete the following steps:

1. Import the modules we're going to use:

import cv2import numpy as np

2. Open an input image, preprocess it, and convert it to a tensor:

image = cv2.imread('../data/Lena.png', cv2.IMREAD_COLOR)tensor = cv2.dnn.blobFromImage(image, 1.0, (224, 224),                               (104, 117, 123), False, False);

3. Convert two images to tensors with preliminary preprocessing:

tensor = cv2.dnn.blobFromImages([image, image], 1.0, (224, 224),                                (104, 117, 123), False, True);

4. Load a trained neural network model:

net = cv2.dnn.readNetFromCaffe('../data/bvlc_googlenet.prototxt',                                '../data/bvlc_googlenet.caffemodel')

5. Set an input for the loaded model and perform an inference:

net.setInput(tensor);prob = net.forward(); ...