In [1]:

    

import numpy as np
import keras
from keras.models import Sequential
from keras.layers import Dense, Dropout, Flatten
from keras.layers import Conv2D, MaxPooling2D
from keras.optimizers import SGD
from keras.layers.normalization import BatchNormalization

from sklearn.preprocessing import StandardScaler
from sklearn.externals import joblib

from read_dataset import read_ceps1d_with_train_test
from read_saved_models import loadMfcc1dStanderdScaler


    

    




Using TensorFlow backend.

In [2]:

    

def getStanderizedData(data):
    data_shape = data.shape
    n = data_shape[0]
    reshaped_data = data.reshape(n, -1)
    saved_ss = loadMfcc1dStanderdScaler()
    trasformed_data = saved_ss.transform(reshaped_data)
    ret_data = trasformed_data.reshape(data_shape)
    return ret_data


    

In [3]:

    

X_train, X_test, y_train, y_test = read_ceps1d_with_train_test()


    

In [4]:

    

X_ss_train= getStanderizedData(X_train)
X_ss_test= getStanderizedData(X_test)


    

In [5]:

    

print(X_ss_train.shape)
print(X_ss_test.shape)
print(y_train.shape)
print(y_test.shape)


    

    




(600, 1, 30, 1293)
(400, 1, 30, 1293)
(600, 10)
(400, 10)

In [6]:

    

model = Sequential()

# the model is convolutional with layer of 30 * 1293
model.add(Conv2D(700, (10, 10), activation='relu',
                 input_shape=(1, 30, 1293),
                 data_format='channels_first'))
model.add(MaxPooling2D(pool_size=(5, 5)))
model.add(Dropout(0.6))
model.add(BatchNormalization())

model.add(Conv2D(100, (3, 3), activation='relu'))
model.add(MaxPooling2D(pool_size=(2, 2)))
model.add(Dropout(0.5))
model.add(BatchNormalization())

model.add(Flatten())
model.add(Dense(100, activation='relu'))
model.add(Dropout(0.4))
model.add(BatchNormalization())
    
model.add(Dense(10, activation='softmax'))

sgd = SGD(lr=0.01, decay=1e-6, momentum=0.9, nesterov=True)
model.compile(loss='categorical_crossentropy', optimizer=sgd, metrics=['accuracy', 'categorical_accuracy'])


    

In [7]:

    

result = model.fit(X_ss_train, y_train, batch_size=30, epochs=10, validation_split=0.2)


    

    




Train on 480 samples, validate on 120 samples
Epoch 1/10
480/480 [==============================] - 1269s - loss: 2.7437 - acc: 0.1417 - categorical_accuracy: 0.1417 - val_loss: 14.0703 - val_acc: 0.0917 - val_categorical_accuracy: 0.0917
Epoch 2/10
480/480 [==============================] - 1254s - loss: 2.1176 - acc: 0.2875 - categorical_accuracy: 0.2875 - val_loss: 10.0209 - val_acc: 0.1583 - val_categorical_accuracy: 0.1583
Epoch 3/10
480/480 [==============================] - 1276s - loss: 1.8354 - acc: 0.3708 - categorical_accuracy: 0.3708 - val_loss: 10.4818 - val_acc: 0.1833 - val_categorical_accuracy: 0.1833
Epoch 4/10
480/480 [==============================] - 1248s - loss: 1.7926 - acc: 0.3833 - categorical_accuracy: 0.3833 - val_loss: 9.2499 - val_acc: 0.1500 - val_categorical_accuracy: 0.1500
Epoch 5/10
300/480 [=================>............] - ETA: 399s - loss: 1.7820 - acc: 0.3867 - categorical_accuracy: 0.3867





    




---------------------------------------------------------------------------
KeyboardInterrupt                         Traceback (most recent call last)
<ipython-input-7-f770ed4429b8> in <module>()
----> 1 result = model.fit(X_ss_train, y_train, batch_size=30, epochs=10, validation_split=0.2)

/home/minato/.pyenv/versions/anaconda3-4.2.0/lib/python3.5/site-packages/keras/models.py in fit(self, x, y, batch_size, epochs, verbose, callbacks, validation_split, validation_data, shuffle, class_weight, sample_weight, initial_epoch, **kwargs)
    868                               class_weight=class_weight,
    869                               sample_weight=sample_weight,
--> 870                               initial_epoch=initial_epoch)
    871 
    872     def evaluate(self, x, y, batch_size=32, verbose=1,

/home/minato/.pyenv/versions/anaconda3-4.2.0/lib/python3.5/site-packages/keras/engine/training.py in fit(self, x, y, batch_size, epochs, verbose, callbacks, validation_split, validation_data, shuffle, class_weight, sample_weight, initial_epoch, **kwargs)
   1505                               val_f=val_f, val_ins=val_ins, shuffle=shuffle,
   1506                               callback_metrics=callback_metrics,
-> 1507                               initial_epoch=initial_epoch)
   1508 
   1509     def evaluate(self, x, y, batch_size=32, verbose=1, sample_weight=None):

/home/minato/.pyenv/versions/anaconda3-4.2.0/lib/python3.5/site-packages/keras/engine/training.py in _fit_loop(self, f, ins, out_labels, batch_size, epochs, verbose, callbacks, val_f, val_ins, shuffle, callback_metrics, initial_epoch)
   1154                 batch_logs['size'] = len(batch_ids)
   1155                 callbacks.on_batch_begin(batch_index, batch_logs)
-> 1156                 outs = f(ins_batch)
   1157                 if not isinstance(outs, list):
   1158                     outs = [outs]

/home/minato/.pyenv/versions/anaconda3-4.2.0/lib/python3.5/site-packages/keras/backend/tensorflow_backend.py in __call__(self, inputs)
   2267         updated = session.run(self.outputs + [self.updates_op],
   2268                               feed_dict=feed_dict,
-> 2269                               **self.session_kwargs)
   2270         return updated[:len(self.outputs)]
   2271 

/home/minato/.pyenv/versions/anaconda3-4.2.0/lib/python3.5/site-packages/tensorflow/python/client/session.py in run(self, fetches, feed_dict, options, run_metadata)
    776     try:
    777       result = self._run(None, fetches, feed_dict, options_ptr,
--> 778                          run_metadata_ptr)
    779       if run_metadata:
    780         proto_data = tf_session.TF_GetBuffer(run_metadata_ptr)

/home/minato/.pyenv/versions/anaconda3-4.2.0/lib/python3.5/site-packages/tensorflow/python/client/session.py in _run(self, handle, fetches, feed_dict, options, run_metadata)
    980     if final_fetches or final_targets:
    981       results = self._do_run(handle, final_targets, final_fetches,
--> 982                              feed_dict_string, options, run_metadata)
    983     else:
    984       results = []

/home/minato/.pyenv/versions/anaconda3-4.2.0/lib/python3.5/site-packages/tensorflow/python/client/session.py in _do_run(self, handle, target_list, fetch_list, feed_dict, options, run_metadata)
   1030     if handle is None:
   1031       return self._do_call(_run_fn, self._session, feed_dict, fetch_list,
-> 1032                            target_list, options, run_metadata)
   1033     else:
   1034       return self._do_call(_prun_fn, self._session, handle, feed_dict,

/home/minato/.pyenv/versions/anaconda3-4.2.0/lib/python3.5/site-packages/tensorflow/python/client/session.py in _do_call(self, fn, *args)
   1037   def _do_call(self, fn, *args):
   1038     try:
-> 1039       return fn(*args)
   1040     except errors.OpError as e:
   1041       message = compat.as_text(e.message)

/home/minato/.pyenv/versions/anaconda3-4.2.0/lib/python3.5/site-packages/tensorflow/python/client/session.py in _run_fn(session, feed_dict, fetch_list, target_list, options, run_metadata)
   1019         return tf_session.TF_Run(session, options,
   1020                                  feed_dict, fetch_list, target_list,
-> 1021                                  status, run_metadata)
   1022 
   1023     def _prun_fn(session, handle, feed_dict, fetch_list):

KeyboardInterrupt: 

In [8]:

    

score = model.evaluate(X_ss_test, y_test, batch_size=30)
print(model.metrics_names)
print(score)


    

    




400/400 [==============================] - 599s    
['loss', 'acc', 'categorical_accuracy']
[6.519633865356445, 0.30250000841915609, 0.30250000841915609]

In [9]:

    

model_filepath = "./savedModels/ceps_cnn1d_model.h5"
model.save(model_filepath)


    

In [10]:

    

from matplotlib import pyplot as plt
%matplotlib inline

plt.plot(range(10), result.history['acc'], label='train accuracy')
plt.plot(range(10), result.history['val_acc'], label='test accuracy')
plt.legend(loc='center left', bbox_to_anchor=(1, 0.5))


    

    




---------------------------------------------------------------------------
NameError                                 Traceback (most recent call last)
<ipython-input-10-1ab3061293eb> in <module>()
      2 get_ipython().magic('matplotlib inline')
      3 
----> 4 plt.plot(range(10), result.history['acc'], label='train accuracy')
      5 plt.plot(range(10), result.history['val_acc'], label='test accuracy')
      6 plt.legend(loc='center left', bbox_to_anchor=(1, 0.5))

NameError: name 'result' is not defined