jonathanoheix

from flask import Flask, render_template, Response
from camera import VideoCamera

app = Flask(__name__)

@app.route('/')
def index():
    return render_template('index.html')

def gen(camera):

jonathanoheix

from keras.models import model_from_json
import numpy as np

class FacialExpressionModel(object):

    EMOTIONS_LIST = ["Angry", "Disgust",
                     "Fear", "Happy",
                     "Neutral", "Sad",
                     "Surprise"]

jonathanoheix

import cv2
from model import FacialExpressionModel
import numpy as np

facec = cv2.CascadeClassifier('haarcascade_frontalface_default.xml')
model = FacialExpressionModel("model.json", "model_weights.h5")
font = cv2.FONT_HERSHEY_SIMPLEX

class VideoCamera(object):
    def __init__(self):

jonathanoheix

# show the confusion matrix of our predictions

# compute predictions
predictions = model.predict_generator(generator=validation_generator)
y_pred = [np.argmax(probas) for probas in predictions]
y_test = validation_generator.classes
class_names = validation_generator.class_indices.keys()

from sklearn.metrics import confusion_matrix
import itertools

jonathanoheix

# plot the evolution of Loss and Acuracy on the train and validation sets

import matplotlib.pyplot as plt

plt.figure(figsize=(20,10))
plt.subplot(1, 2, 1)
plt.suptitle('Optimizer : Adam', fontsize=10)
plt.ylabel('Loss', fontsize=16)
plt.plot(history.history['loss'], label='Training Loss')
plt.plot(history.history['val_loss'], label='Validation Loss')

jonathanoheix

# serialize model structure to JSON
model_json = model.to_json()
with open("model.json", "w") as json_file:
    json_file.write(model_json)

jonathanoheix

# number of epochs to train the NN
epochs = 50

from keras.callbacks import ModelCheckpoint

checkpoint = ModelCheckpoint("model_weights.h5", monitor='val_acc', verbose=1, save_best_only=True, mode='max')
callbacks_list = [checkpoint]

history = model.fit_generator(generator=train_generator,
                                steps_per_epoch=train_generator.n//train_generator.batch_size,

jonathanoheix

from keras.layers import Dense, Input, Dropout, GlobalAveragePooling2D, Flatten, Conv2D, BatchNormalization, Activation, MaxPooling2D
from keras.models import Model, Sequential
from keras.optimizers import Adam

# number of possible label values
nb_classes = 7

# Initialising the CNN
model = Sequential()

jonathanoheix

from keras.preprocessing.image import ImageDataGenerator

# number of images to feed into the NN for every batch
batch_size = 128

datagen_train = ImageDataGenerator()
datagen_validation = ImageDataGenerator()

train_generator = datagen_train.flow_from_directory(base_path + "train",
                                                    target_size=(pic_size,pic_size),

jonathanoheix

# count number of train images for each expression

for expression in os.listdir(base_path + "train"):
    print(str(len(os.listdir(base_path + "train/" + expression))) + " " + expression + " images")