Iván de Paz Centeno
Iván de Paz Centeno
The `steps_threshold` is a list of thresholds used for each stage respectively. If you play with the numbers, you can alter the face detection rate. You should adapt these values...
Are you closing the file descriptors of your images after predictions? can you supply a demo code for this bug?
Hello @Neltherion . Right now there isn't a way to process a batch of images, but I'll work on it. Thank you for the suggestion!
I could not reproduce this issue. What version of tensorflow do you have installed?
Can you please post what Python version are you using? also information regarding the operating system, and if you are using anaconda or not.
I could not reproduce this issue in a linux environment from scratch with Anaconda and Python 3.7. Could it be you installed mtcnn with a different pip version (one outside...
Hi, only the code is released under MIT. You are absolutely right, the weights of the network should not be used for commercial purposes, the model should be retrained in...
By the way, the model is an adapted version coming from the original https://github.com/kpzhang93/MTCNN_face_detection_alignment version, which is also released under MIT license. You might be interested in sending also this...
I don't know if it is the usual practice. I understand it is a good way to support custom or different models with the same architecture without the need to...
Hi, you could try adjusting the `steps_threshold` parameter in the MTCNN constructor (which by default is [0.6, 0.7, 0.7]) to better fit your images distribution. ```python from mtcnn import MTCNN...