Uncategorized

imageai object detection vs cat: Dog, cat, or toilet paper?

Image

Dog, cat, or toilet paper?

Click to enlarge

 

 2002  pip3 install tensorflow==1.14
 2003  pip3 install opencv-python
 2004  pip3 install keras
 2005  pip3 install imageai --upgrade

$ vi FirstDetection.py

from imageai.Detection import ObjectDetection
import os

execution_path = os.getcwd()

detector = ObjectDetection()
detector.setModelTypeAsRetinaNet()
detector.setModelPath( os.path.join(execution_path , "resnet50_coco_best_v2.0.1.h5"))
detector.loadModel()
detections = detector.detectObjectsFromImage(input_image=os.path.join(execution_path ,
                                                         "cat2.jpg"),
                                output_image_path=os.path.join(execution_path ,
                                                               "cat2_detect.jpg"))

for eachObject in detections:
    print(eachObject["name"] , " : " , eachObject["percentage_probability"] )


$ python FirstDetection.py

 

(Using Tensorflow 1.14, as most recent Tensorflow (v2) throws error.

https://github.com/OlafenwaMoses/ImageAI/issues/367

 

Bonus update (20 April 2020)