search

danduncan / HappyNet

Convolutional neural network that does real-time emotion recognition. HappyNet detects faces in video and images, classifies the emotion on each face, then replaces each face with the correct emoji for that emotion. Based on Caffe and the "Emotions in the Wild" network available on Caffe model zoo.
https://youtu.be/MDHtzOdnSgA
130 stars 59 forks source link

About the Caffe model #5

Open zuanshiyuanbao opened 7 years ago

zuanshiyuanbao commented 7 years ago

Hi, I am new to caffe. When I searched for the caffe model on the Github, they have several version of caffe model. Such as EmotiW with RGB, EmotiW with LBP etc. Which version of Caffe model I should choose? Thanks!

GarryWan commented 6 years ago

so am I

GarryWan commented 6 years ago

Hi, I am new to caffe. When I searched for the caffe model on the Github, they have several version of caffe model. Such as EmotiW with RGB, EmotiW with LBP etc. Which version of Caffe model I should choose? Thanks!

anmolsinghsuag commented 6 years ago

You should use EmotiW with RGB if you are going to use colored image frame as inputs. Converting RGB to LBP is also possible, Levi has provided a script, but it slows down the real-time prediction due to image processing.