mtcnn
Here are 108 public repositories matching this topic...
-
Updated
Jul 5, 2020 - Python
-
Updated
Nov 23, 2018 - Python
-
Updated
Jun 1, 2019 - Python
o_net hard_example报错
lunar@lunar-virtual-machine:~/PycharmProjects/tensorflow_mtcnn/preprocess$ python gen_hard_example.py 24
2019-05-12 09:33:06.690596: I tensorflow/core/platform/cpu_feature_guard.cc:140] Your CPU supports instructions that this TensorFlow binary was not compiled to use: AVX2 FMA
载入数据
8247it [2:47:10, 1.26it/s]Traceback (most recent call last):
File "gen_hard_example.py", line 193, in <module
-
Updated
Oct 19, 2017 - C++
-
Updated
Jun 7, 2018 - C++
-
Updated
Jul 10, 2020 - C++
-
Updated
Mar 17, 2017 - Jupyter Notebook
-
Updated
Dec 3, 2019 - Python
-
Updated
Feb 10, 2018 - C++
-
Updated
Jun 19, 2018 - Jupyter Notebook
-
Updated
Apr 21, 2019 - Go
-
Updated
Nov 18, 2018 - C++
-
Updated
Aug 8, 2017 - C++
-
Updated
Nov 20, 2019 - Python
-
Updated
Jul 12, 2020 - Python
We caculate Correspondence by this fomula:
x1 = x1_map * 2 + 1,
y1 = y1_map * 2 + 1,
x2 = x1_map * 2 + 1 + 12,
y2 = y2_map * 2 + 1 + 12.
First, how do you derive the equations here? Second, the axis of Red box in original image is (1, 1, 13, 13), which Correspond to (0, 0) in feature map. How about (0,0,12,12)? That is the first convolutional region, which should map to (0,0) in the
-
Updated
Jul 11, 2018 - Java
-
Updated
Jul 22, 2018 - Python
-
Updated
Aug 13, 2019 - Python
-
Updated
Jun 3, 2020 - C++
Improve this page
Add a description, image, and links to the mtcnn topic page so that developers can more easily learn about it.
Add this topic to your repo
To associate your repository with the mtcnn topic, visit your repo's landing page and select "manage topics."
Dears,
if somebody has instructions , my target is to recognize a face using tensor flow but I didn't find a full instructions which scripts to use to do the following :
1- crop faces
2- Train images .
3- face recognition.
if examples or sample commands that would be appreciated!
I have Ubuntu Linux with python and tensor flow environment ready.
appreciate your steps to go forward