This model is a deep convolutional neural network for emotion recognition in faces.

"Training Deep Networks for Facial Expression Recognition with Crowd-Sourced Label Distribution" arXiv:1608.01041

The model is trained on the FER+ annotations for the standard Emotion FER dataset, as described in the above paper.

The model is trained in CNTK, using the cross entropy training mode. You can find the source code here.

The model expects input of the shape (Nx1x64x64), where N is the batch size.

Given a numpy array img representing the image you would like to score:

import numpy as np

def preprocess(img):
  input_shape = (1, 64, 64)
  img = np.resize(img, input_shape)
  img = np.expand_dims(img, axis=0) #batchify
  return img

The model outputs a (1x8) array of scores corresponding to the 8 emotion classes, where the labels map as follows:
emotion_table = {'neutral':0, 'happiness':1, 'surprise':2, 'sadness':3, 'anger':4, 'disgust':5, 'fear':6, 'contempt':7}

Route the model output through a softmax function to map the aggregated activations across the network to probabilities across the 8 classes.

import numpy as np

def softmax(scores):
  # your softmax function
  
def postprocess(scores):
  ''' 
  This function takes the scores generated by the network and returns the class IDs in decreasing 
  order of probability.
  '''
  prob = softmax(scores)
  prob = np.squeeze(prob)
  classes = np.argsort(prob)[::-1]
  return classes

Sets of sample input and output files are provided in

• serialized protobuf TensorProtos (.pb), which are stored in the folders test_data_set_*/.

MIT