There is an imbalance two class classification problem with 12750 samples for class 0 and 2550 samples for class 1. I've gotten class weights using class_weight.compute_class_weight and fed them to model.fit. I've tested many loss and optimizer functions. The accuracy on test data is reasonable but loss and accuracy curves aren't normal, which are shown as below. I was wonder if some one give me a suggestion that how can I smooth the curves and fix this problem.
Thank you
import tensorflow as tf
import keras
import numpy as np
from keras.models import Sequential
from keras.layers import Dense, Flatten
from keras.layers import Conv2D, MaxPooling2D, UpSampling2D,Dropout, Conv1D
from sklearn.utils import class_weight
import scipy.io
from sklearn.model_selection import train_test_split
from sklearn.utils import shuffle
import sklearn.metrics as metrics
from sklearn.utils import class_weight
#General Variables
batch_size = 32
epochs = 100
num_classes = 2
#Load Data
# X_p300 = scipy.io.loadmat('D:/P300_challenge/BCI data- code 2005/code2005/p300Cas.mat',variable_names='p300Cas').get('p300Cas')
# X_np300 = scipy.io.loadmat('D:/P300_challenge/BCI data- code 2005/code2005/np300Cas.mat',variable_names='np300Cas').get('np300Cas')
X_p300 = scipy.io.loadmat('/content/drive/MyDrive/p300/p300Cas.mat',variable_names='p300Cas').get('p300Cas')
X_np300 = scipy.io.loadmat('/content/drive/MyDrive/p300/np300Cas.mat',variable_names='np300Cas').get('np300Cas')
X_np300=X_np300[:,:]
X_p300=X_p300[:,:]
X=np.concatenate((X_p300,X_np300))
X = np.expand_dims(X,2)
Y=np.zeros((15300,))
Y[0:2550]=1
#Shuffle data as it is now in order by row colunm index
print('Shuffling...')
X, Y = shuffle(X, Y)
#Split data between 80% Training and 20% Testing
print('Splitting...')
x_train, x_test, y_train, y_test = train_test_split(
X, Y, train_size=.8, test_size=.2, shuffle=True)
# determine the weight of each class
class_weights = class_weight.compute_class_weight('balanced',
np.unique(y_train),
y_train)
class_weights = {i:class_weights[i] for i in range(2)}
y_train = tf.keras.utils.to_categorical(y_train, num_classes)
y_test = tf.keras.utils.to_categorical(y_test, num_classes)
model = Sequential()
model.add(Conv1D(256,kernel_size=3,activation='relu', input_shape =(1680, 1)))
# model.add(Dropout(.5))
model.add(Flatten())
model.add(Dense(200, activation='relu'))
model.add(Dense(50, activation='relu'))
model.add(Dense(2, activation='softmax'))
model.compile(loss='mse',
optimizer='sgd',
metrics= ['acc'])
## use it when you want to apply weight of the classes
history = model.fit(x_train, y_train,class_weight=class_weights, validation_split = 0.3, epochs = epochs, verbose = 1)
#model.fit(x_train, y_train,batch_size=32,validation_split = 0.1, epochs = epochs, verbose = 1)
import matplotlib.pyplot as plt
history_dict = history.history
history_dict.keys()
loss_values = history_dict['loss']
val_loss_values = history_dict['val_loss']
acc = history_dict.get('acc')
epochs = range(1, len(acc) + 1)
plt.plot(epochs, loss_values, 'r--', label = 'Training loss')
plt.plot(epochs, val_loss_values, 'b', label = 'Validation_loss')
plt.title('Training and Validation Loss')
plt.xlabel('Epochs')
plt.ylabel('Loss')
plt.legend()
plt.show()
acc_values = history_dict['acc']
val_acc_values = history_dict['val_acc']
plt.plot(epochs, acc, 'r--', label = 'Training acc')
plt.plot(epochs, val_acc_values, 'b', label = 'Validation acc')
plt.title('Training and Validation accuracy')
plt.xlabel('Epochs')
plt.ylabel('accuracy')
plt.legend()
plt.show()
model.summary()
test_loss, test_acc = model.evaluate(x_test, y_test)
print('test_acc:', test_acc)
