StevenBanama
StevenBanama
In my opnion, It's better to use "os.getevn" rather than "os.environ".
you`d better change your python version and all requirment. It had been solved when env changed.
That's impossible! You can get bins of ages.
@MoonBunnyZZZ Problem (I): You can use only once detection with rotation. if you use alignment for face, meanwhile you should change the postion of landmarks. The second detection is just...
cascad_imgs, padding = [], 200 #### step 1. add extra padding for aliagn image!!!!!! new_bd_img = cv2.copyMakeBorder(img, padding, padding, padding, padding, cv2.BORDER_CONSTANT) #### offset for add for extra padding, so...
> > @MoonBunnyZZZ Problem (I): You can use only once detection with rotation. if you use alignment for face, meanwhile you should change the postion of landmarks. The second detection...
can you provide your runningtime enviroment
it may work: pip3 install opencv-python-headless https://stackoverflow.com/questions/54297627/qt-could-not-find-the-platform-plugin-cocoa
it cause by input of video capture.
Can you provide your enviroments (tensorflow version) ? I have test it locally (tensorflow 2.1), and work well.