136 lines
4.1 KiB
Python
136 lines
4.1 KiB
Python
import json
|
|
from python_speech_features.python_speech_features.base import mfcc
|
|
import numpy as np
|
|
from sklearn.model_selection import train_test_split
|
|
import tensorflow as tf
|
|
import tensorflow.keras as keras
|
|
from pathlib import Path
|
|
import pandas as pd
|
|
import matplotlib.pyplot as plt
|
|
|
|
# path to json file that stores MFCCs and subject labels for each processed sample
|
|
DATA_PATH = str(Path.cwd()) + "/mfcc_data.json"
|
|
|
|
def load_data_from_json(data_path):
|
|
|
|
with open(data_path, "r") as fp:
|
|
data = json.load(fp)
|
|
|
|
# convert lists to numpy arraysls
|
|
X = np.array(data['mfcc'])
|
|
X = X.reshape(X.shape[0], 1, X.shape[1])
|
|
#print(X.shape)
|
|
|
|
y = np.array(data["labels"])
|
|
y = y.reshape(y.shape[0], 1)
|
|
#print(y.shape)
|
|
|
|
|
|
print("Data succesfully loaded!")
|
|
|
|
return X, y
|
|
|
|
|
|
def plot_history(history):
|
|
"""Plots accuracy/loss for training/validation set as a function of the epochs
|
|
:param history: Training history of model
|
|
:return:
|
|
"""
|
|
|
|
fig, axs = plt.subplots(2)
|
|
|
|
# create accuracy sublpot
|
|
axs[0].plot(history.history["accuracy"], label="train accuracy")
|
|
axs[0].plot(history.history["val_accuracy"], label="test accuracy")
|
|
axs[0].set_ylabel("Accuracy")
|
|
axs[0].legend(loc="lower right")
|
|
axs[0].set_title("Accuracy eval")
|
|
|
|
# create error sublpot
|
|
axs[1].plot(history.history["loss"], label="train error")
|
|
axs[1].plot(history.history["val_loss"], label="test error")
|
|
axs[1].set_ylabel("Error")
|
|
axs[1].set_xlabel("Epoch")
|
|
axs[1].legend(loc="upper right")
|
|
axs[1].set_title("Error eval")
|
|
|
|
plt.show()
|
|
|
|
|
|
def prepare_datasets(test_size=0.25, validation_size=0.2):
|
|
"""Loads data and splits it into train, validation and test sets.
|
|
:param test_size (float): Value in [0, 1] indicating percentage of data set to allocate to test split
|
|
:param validation_size (float): Value in [0, 1] indicating percentage of train set to allocate to validation split
|
|
:return X_train (ndarray): Input training set
|
|
:return X_validation (ndarray): Input validation set
|
|
:return X_test (ndarray): Input test set
|
|
:return y_train (ndarray): Target training set
|
|
:return y_validation (ndarray): Target validation set
|
|
:return y_test (ndarray): Target test set
|
|
"""
|
|
|
|
# load data
|
|
X, y = load_data(DATA_PATH)
|
|
|
|
# create train, validation and test split
|
|
X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=test_size)
|
|
X_train, X_validation, y_train, y_validation = train_test_split(X_train, y_train, test_size=validation_size)
|
|
|
|
return X_train, X_validation, X_test, y_train, y_validation, y_test
|
|
|
|
|
|
def build_model(input_shape, nr_classes=5):
|
|
"""Generates RNN-LSTM model
|
|
:param input_shape (tuple): Shape of input set
|
|
:return model: RNN-LSTM model
|
|
"""
|
|
|
|
# build network topology
|
|
model = keras.Sequential()
|
|
|
|
# 2 LSTM layers
|
|
model.add(keras.layers.LSTM(64, input_shape=input_shape, return_sequences=True))
|
|
model.add(keras.layers.LSTM(64))
|
|
|
|
# dense layer
|
|
model.add(keras.layers.Dense(64, activation='relu'))
|
|
model.add(keras.layers.Dropout(0.3))
|
|
|
|
# output layer
|
|
model.add(keras.layers.Dense(nr_classes, activation='softmax'))
|
|
|
|
return model
|
|
|
|
|
|
if __name__ == "__main__":
|
|
|
|
# get train, validation, test splits
|
|
X_train, X_validation, X_test, y_train, y_validation, y_test = prepare_datasets(0.25, 0.2)
|
|
|
|
print(X_train.shape[1], X_train.shape[2])
|
|
# create network
|
|
|
|
input_shape = (X_train.shape[1], X_train.shape[2]) # (~2800), 1, 208
|
|
model = build_model(input_shape)
|
|
|
|
# compile model
|
|
optimiser = keras.optimizers.Adam(learning_rate=0.0001)
|
|
model.compile(optimizer=optimiser,
|
|
loss='sparse_categorical_crossentropy',
|
|
metrics=['accuracy'])
|
|
|
|
model.summary()
|
|
|
|
# train model
|
|
history = model.fit(X_train, y_train, validation_data=(X_validation, y_validation), batch_size=64, epochs=30)
|
|
|
|
# plot accuracy/error for training and validation
|
|
plot_history(history)
|
|
|
|
# evaluate model on test set
|
|
test_loss, test_acc = model.evaluate(X_test, y_test, verbose=2)
|
|
print('\nTest accuracy:', test_acc)
|
|
|
|
|
|
|