v1zh3d / WIDER-Face-Detection-using-MTCNN

This is my first Internship Project on Deep Learning. This is a challenge of WIDER Face Benchmark whose aim is to detect faces in the images in any condition of various poses, illuminations and occlusions. And we managed to get the accuracy of 91% in detecting every type of images.
17 stars 9 forks source link

Cannot import name 'PNet' from 'mtcnn' #2

Open Huxwell opened 3 years ago

Huxwell commented 3 years ago

When I run python tf_gen_12net_hard_example.py, mtcnn dependency you don't mention in readme is missing. I tried my luck with "pip install mtcnn" and it works, but then I will get:

ImportError: cannot import name 'PNet' from 'mtcnn'. Is there any particular version of this library that your code expects or is there any particular repository that should be used instead?

v1zh3d commented 3 years ago

It's been 2 years since I have done this project, and yeah, that time, I guess the MTCNN version was 0.9.0, so you can try that version.