model_training.py file

Backend/classifer.py

+import cv2
+from tensorflow.keras.models import Sequential
+from tensorflow.keras.layers import Conv2D, MaxPooling2D, Dense, Dropout, Flatten
+from tensorflow.keras.optimizers import Adam
+from tensorflow.keras.preprocessing.image import ImageDataGenerator
+
+# Initialize image data generator with rescaling
+train = ImageDataGenerator(rescale=1. / 255)
+validation = ImageDataGenerator(rescale=1. / 255)
+
+# Preprocess all test images
+trainGen = train.flow_from_directory(
+    'data/train',
+    target_size=(48, 48),
+    batch_size=64,
+    color_mode="grayscale",
+    class_mode='categorical')
+
+# Preprocess all train images
+valGen = validation.flow_from_directory(
+    'data/test',
+    target_size=(48, 48),
+    batch_size=64,
+    color_mode="grayscale",
+    class_mode='categorical')
+
+# create model structure
+model = Sequential()
+
+model.add(Conv2D(32, kernel_size=(3, 3), activation='relu', input_shape=(48, 48, 1)))
+model.add(Conv2D(64, kernel_size=(3, 3), activation='relu'))
+model.add(MaxPooling2D(pool_size=(2, 2)))
+model.add(Dropout(0.25))
+
+model.add(Conv2D(128, kernel_size=(3, 3), activation='relu'))
+model.add(MaxPooling2D(pool_size=(2, 2)))
+model.add(Conv2D(128, kernel_size=(3, 3), activation='relu'))
+model.add(MaxPooling2D(pool_size=(2, 2)))
+model.add(Dropout(0.25))
+
+model.add(Flatten())
+model.add(Dense(1024, activation='relu'))
+model.add(Dropout(0.5))
+model.add(Dense(7, activation='softmax'))
+
+cv2.ocl.setUseOpenCL(False)
+
+model.compile(loss='categorical_crossentropy', optimizer=Adam(lr=0.0001, decay=1e-6), metrics=['accuracy'])
+
+# Train the neural network/model
+model_info = model.fit_generator(
+    trainGen,
+    steps_per_epoch=28709 // 64,
+    epochs=5,
+    validation_data=valGen,
+    validation_steps=7178 // 64)
+
+# save model structure in jason file
+model_json = model.to_json()
+with open("emotion_model.json", "w") as json_file:
+    json_file.write(model_json)
+
+# save trained model weight in .h5 file
+model.save_weights('emotion_model.h5')