WITHOUT TENSORFLOW, JUST INFERENCE
Code written in this repository are taken from https://github.com/djmv/MobilNet_SSD_opencv so please refer to that link if you want to use this code. Please read https://ebenezertechs.com/mobilenet-ssd-using-opencv-3-4-1-deep-learning-module-python/ for more information.
The whole point in uploading these files here is to remind myself that if I already have caffemodel trained and its corresponding prototxt file, it can run in any machine with only Python, Numpy, and OpenCV (No Tensorflow or Caffe installation required) It is simple, just those two files and a simple python code. Feel free to use these code, but please cite DJMV or Ebenezer if you are using these code (not me)
Tested in Win 7 (Python 3.6.5, openCV 3.4.0), Win 10 (Python 3.6.5, openCV 3.4.1), and Ubuntu 16.04 (Python 3.5.2, openCV 4.2.0). My guess is that it might works just as well with any version of python and opencv 3+