How to do it...

You need to complete these steps:

1. Import the modules:

import cv2
import numpy as np

2. Import the Caffe model:

model = cv2.dnn.readNetFromCaffe('../data/fcn8s-heavy-pascal.prototxt',
                                 '../data/fcn8s-heavy-pascal.caffemodel')

3. Load the image and perform inference:

frame = cv2.imread('../data/scenetext01.jpg')
blob = cv2.dnn.blobFromImage(frame, 1, (frame.shape[1],frame.shape[0]))
model.setInput(blob)
output = model.forward()

4. Compute the image with per-pixel class labels:

labels = output[0].argmax(0)

5. Visualize the results:

plt.figure(figsize=(14,10))
plt.subplot(121)
plt.axis('off')
plt.title('original')
plt.imshow(frame[:,:,[2,1,0]])
plt.subplot(122)
plt.axis('off')
plt.title('segmentation')
plt.imshow(labels)
plt.tight_layout()
plt.show()