Mastering OpenCV 4 with Python

SqueezeNet for image classification

In the image_classification_opencv_squeezenet_caffe.py script, we perform image classification using the SqueezeNet architecture, which provides AlexNet-level accuracy with 50x fewer parameters. The output of this script can be seen in the following screenshot:

As shown in the previous screenshot, the top prediction corresponds to a church with a probability of 0.9967952371.

In this script, we are using SqueezeNet v1.1, which has 2.4x less computation than v1.0, but without sacrificing any accuracy.

The top 10 predictions are as follows:

• 1. label: church, probability: 0.9967952371
• 2. label: monastery, probability: ...