0

I'm tring to use CNN to classifiy 3 classes data, every data is 30*188. Class1 has 5794 data, class2 has 8471, class3 has 9092. When I train my model, the value of accuracy, loss , val_acc and val_loss don't change. Please help me to solve this problem.

import glob
import os
import librosa
import numpy as np
import matplotlib.pyplot as plt
from matplotlib.pyplot import specgram
import librosa.display
import sklearn
from keras.utils import to_categorical
import scipy.io as scio

path1 = 'class1_feature_array.mat'
data1 = scio.loadmat(path1)
class1_feature_array = data1['class1_feature_array']
class1_label = np.zeros((class1_feature_array.shape[0],))
class1_label=class1_label.astype(np.int32)
class1_label=class1_label.astype(np.str)

path2 = 'class2_feature_array.mat'
data2 = scio.loadmat(path2)
class2_feature_array = data2['class2_feature_array']
class2_label = np.ones((class2_feature_array.shape[0],))
class2_label=class2_label.astype(np.int32)
class2_label=class2_label.astype(np.str)

path3 = 'class3_feature_array.mat'
data3 = scio.loadmat(path3)
class3_feature_array = data3['class3_feature_array']
class3_label = np.ones((class3_feature_array.shape[0],))*2
class3_label=class3_label.astype(np.int32)
class3_label=class3_label.astype(np.str)

features, labels = np.empty((0,40,188)), np.empty(0)
features = np.append(features,class1_feature_array,axis=0)
features = np.append(features,class2_feature_array,axis=0)
features = np.append(features,class3_feature_array,axis=0)
features = np.array(features)

labels = np.append(labels,class1_label,axis=0)
labels = np.append(labels,class2_label,axis=0)
labels = np.append(labels,class3_label,axis=0)
labels = np.array(labels, dtype = np.int)

def one_hot_encode(labels):
    n_labels = len(labels)
    n_unique_labels = len(np.unique(labels))
    one_hot_encode = np.zeros((n_labels,n_unique_labels))
    print("one_hot_encode",one_hot_encode.shape)
    one_hot_encode[np.arange(n_labels), labels] = 1
    return one_hot_encode

labels = one_hot_encode(labels)

train_test_split = np.random.rand(len(features)) < 0.80
train_x = features[train_test_split]
train_y = labels[train_test_split]
test_x = features[~train_test_split]
test_y = labels[~train_test_split]

train_x = train_x.reshape(train_x.shape[0],train_x.shape[1],train_x.shape[2],1)
test_x = test_x.reshape(test_x.shape[0],test_x.shape[1],test_x.shape[2],1)

import sklearn
import keras
from keras.models import Sequential
from keras.layers import *
from keras.callbacks import LearningRateScheduler
from keras import optimizers

#LeNet
model = Sequential()

model.add(Conv2D(32,(5, 5),strides=(1,1),padding='valid',activation='relu',input_shape=(40,188,1),kernel_initializer='uniform'))
model.add(MaxPooling2D(pool_size=(2,2)))

model.add(Conv2D(64,(5,5),strides=(1,1),padding='valid',activation='relu',kernel_initializer='uniform'))
model.add(MaxPooling2D(pool_size=(2,2)))

model.add(Flatten())
model.add(Dense(100,activation='relu'))
model.add(Dense(3, activation='softmax'))

sgd = optimizers.SGD(lr=0.01, decay=1e-6, momentum=0.9, nesterov=True)
model.compile(optimizer=sgd,
            loss='binary_crossentropy',
            metrics=['accuracy'])
model.summary(line_length=80)

history = model.fit(train_x, train_y, epochs=100, batch_size=32, validation_data=(test_x, test_y))

The output after training is as shown below:

Train on 18625 samples, validate on 4732 samples

Epoch 1/100
18625/18625 [==============================] - 30s 2ms/step - loss: 8.0138 - accuracy: 0.5001 - val_loss: 8.1055 - val_accuracy: 0.4944

Epoch 2/100
18625/18625 [==============================] - 22s 1ms/step - loss: 8.0181 - accuracy: 0.4998 - val_loss: 8.1055 - val_accuracy: 0.4944

Epoch 3/100
18625/18625 [==============================] - 23s 1ms/step - loss: 8.0181 - accuracy: 0.4998 - val_loss: 8.1055 - val_accuracy: 0.4944

Epoch 4/100
18625/18625 [==============================] - 24s 1ms/step - loss: 8.0181 - accuracy: 0.4998 - val_loss: 8.1055 - val_accuracy: 0.4944

Epoch 5/100
18625/18625 [==============================] - 23s 1ms/step - loss: 8.0181 - accuracy: 0.4998 - val_loss: 8.1055 - val_accuracy: 0.4944

Epoch 6/100
18625/18625 [==============================] - 24s 1ms/step - loss: 8.0181 - accuracy: 0.4998 - val_loss: 8.1055 - val_accuracy: 0.4944

Epoch 7/100
18625/18625 [==============================] - 24s 1ms/step - loss: 8.0181 - accuracy: 0.4998 - val_loss: 8.1055 - val_accuracy: 0.4944

Epoch 8/100
18625/18625 [==============================] - 25s 1ms/step - loss: 8.0181 - accuracy: 0.4998 - val_loss: 8.1055 - val_accuracy: 0.4944

Epoch 9/100
18625/18625 [==============================] - 26s 1ms/step - loss: 8.0181 - accuracy: 0.4998 - val_loss: 8.1055 - val_accuracy: 0.4944

Epoch 10/100
18625/18625 [==============================] - 25s 1ms/step - loss: 8.0181 - accuracy: 0.4998 - val_loss: 8.1055 - val_accuracy: 0.4944

Epoch 11/100
18625/18625 [==============================] - 26s 1ms/step - loss: 8.0181 - accuracy: 0.4998 - val_loss: 8.1055 - val_accuracy: 0.4944

Epoch 12/100
18625/18625 [==============================] - 26s 1ms/step - loss: 8.0181 - accuracy: 0.4998 - val_loss: 8.1055 - val_accuracy: 0.4944
desertnaut
  • 57,590
  • 26
  • 140
  • 166
juzix
  • 1
  • Have you tried plotting your data? – Jamie Jun 04 '20 at 01:43
  • @Jamie Sorry, i don't know how to plot my data, can you tell what should i do – juzix Jun 04 '20 at 02:25
  • A certain mistake is that, since you have 3 classes, you should use `loss='categorical_crossentropy'`, and not `binary_crossentropy`; but [I doubt this is the reason for your issue](https://stackoverflow.com/questions/42081257/why-binary-crossentropy-and-categorical-crossentropy-give-different-performances/46038271#46038271). – desertnaut Jun 04 '20 at 10:47
  • @desertnaut Thank you for your help, i tried to change 'loss = 'binary_crossentropy'' to 'loss = 'categorical_crossentropy'', but it doesn't seem to work. – juzix Jun 04 '20 at 11:46
  • As I said - but it is a mistake nevertheless that you should correct. – desertnaut Jun 04 '20 at 11:47
  • @desertnaut Yes, I already know my mistake. Can you tell me how to solve the problem that acc and loss do not change？ – juzix Jun 04 '20 at 11:58
  • I think @Jamie was on to something. Do you have a sample of your data? – Desmond Cheong Jun 06 '20 at 14:35

0 Answers0