def run(self, nb_epoch=10, batch_size=128, verbose=1):
data = self.data
model = self.model
fig = self.fig
history = self.fit(nb_epoch=nb_epoch, batch_size=batch_size, verbose=verbose)
score = model.evaluate(data.X_test, data.Y_test, verbose=0)
print('Confusion matrix')
Y_test_pred = model.predict(data.X_test, verbose=0)
y_test_pred = np.argmax(Y_test_pred, axis=1)
print(metrics.confusion_matrix(data.y_test, y_test_pred))
print('Test score:', score[0])
print('Test accuracy:', score[1])
# Save results
foldname = sfile.makenewfold(prefix='output_', type='datetime')
kkeras.save_history_history('history_history.npy', history.history, fold=foldname)
model.save_weights(os.path.join(foldname, 'dl_model.h5'))
print('Output results are saved in', foldname)
if fig:
plt.figure(figsize=(12, 4))
plt.subplot(1, 2, 1)
kkeras.plot_acc(history)
plt.subplot(1, 2, 2)
kkeras.plot_loss(history)
plt.show()
self.history = history
return foldname
def __init__(self,
X,
y,
Lx,
Ly,
nb_classes=2,
nb_epoch=5000,
batch_size=128,
verbose=0):
data = Data(X, y, Lx, Ly, nb_classes)
model = CNN(data.input_shape, nb_classes)
# model = CNN_opt(data.input_shape, nb_classes)
history = model.fit(data.X_train,
data.Y_train,
batch_size=batch_size,
epochs=nb_epoch,
verbose=verbose,
validation_data=(data.X_test, data.Y_test))
score = model.evaluate(data.X_test, data.Y_test, verbose=0)
print('Confusion metrix')
Y_test_pred = model.predict(data.X_test, verbose=0)
y_test_pred = np.argmax(Y_test_pred, axis=1)
print(metrics.confusion_matrix(data.y_test, y_test_pred))
print('Test score:', score[0])
print('Test accuracy:', score[1])
kkeras.plot_acc(history)
plt.show()
kkeras.plot_loss(history)
def fit(self, nb_epoch=10):
x_train, x_test, y_train, y_test = self.x_train, self.x_test, self.y_train, self.y_test
autoencoder = self.autoencoder
history = autoencoder.fit(x_train, y_train,
nb_epoch=nb_epoch,
batch_size=128,
shuffle=True,
verbose=0,
validation_data=(x_test, y_test))
kkeras.plot_loss(history)
def fit(self, nb_epoch=10):
x_train, x_test, y_train, y_test = self.x_train, self.x_test, self.y_train, self.y_test
autoencoder = self.autoencoder
history = autoencoder.fit(x_train,
y_train,
nb_epoch=nb_epoch,
batch_size=128,
shuffle=True,
verbose=0,
validation_data=(x_test, y_test))
kkeras.plot_loss(history)
def fit(self):
# Only required self parameters are used by localization
model = self.model
X_train, Y_train = self.X_train, self.Y_train
batch_size = self.batch_size
nb_epoch = self.nb_epoch
X_test, Y_test = self.X_test, self.Y_test
history = model.fit(X_train, Y_train, batch_size=batch_size, nb_epoch=nb_epoch,
verbose=0, validation_data=(X_test, Y_test)) # callbacks=[earlyStopping])
plt.subplot(1,2,1)
kkeras.plot_acc( history)
plt.subplot(1,2,2)
kkeras.plot_loss( history)
def run(self, nb_epoch=100):
(x_train_in, x_train), (x_test_in, x_test) = self.Data
x_train_in, x_test_in = update2(x_train_in, x_test_in)
x_train, x_test = update2(x_train, x_test)
self.modeling()
autoencoder = self.autoencoder
history = autoencoder.fit(x_train_in,
x_train,
nb_epoch=nb_epoch,
batch_size=128,
shuffle=True,
verbose=1,
validation_data=(x_test, x_test))
kkeras.plot_loss(history)
self.imshow()
def fit(self):
# Only required self parameters are used by localization
model = self.model
X_train, Y_train = self.X_train, self.Y_train
batch_size = self.batch_size
nb_epoch = self.nb_epoch
X_test, Y_test = self.X_test, self.Y_test
history = model.fit(
X_train,
Y_train,
batch_size=batch_size,
nb_epoch=nb_epoch,
verbose=0,
validation_data=(X_test, Y_test)) # callbacks=[earlyStopping])
plt.subplot(1, 2, 1)
kkeras.plot_acc(history)
plt.subplot(1, 2, 2)
kkeras.plot_loss(history)
def __init__(self, X, y, Lx, Ly, nb_classes=2, nb_epoch=5000, batch_size=128, verbose=0):
data = Data(X, y, Lx, Ly, nb_classes)
model = CNN(data.input_shape, nb_classes)
# model = CNN_opt(data.input_shape, nb_classes)
history = model.fit(data.X_train, data.Y_train, batch_size=batch_size, epochs=nb_epoch,
verbose=verbose, validation_data=(data.X_test, data.Y_test))
score = model.evaluate(data.X_test, data.Y_test, verbose=0)
print('Confusion metrix')
Y_test_pred = model.predict(data.X_test, verbose=0)
y_test_pred = np.argmax(Y_test_pred, axis=1)
print(metrics.confusion_matrix(data.y_test, y_test_pred))
print('Test score:', score[0])
print('Test accuracy:', score[1])
kkeras.plot_acc(history)
plt.show()
kkeras.plot_loss(history)
def run_dl_mgh_params_2cl(X, y, Lx, Ly, nb_epoch=5000,
batch_size = 128,
nb_classes = 2):
# input image dimensions
img_rows, img_cols = Lx, Ly
# number of convolutional filters to use
nb_filters = 8
# size of pooling area for max pooling
pool_size = (10, 10)
# convolution kernel size
kernel_size = (20, 20)
# the data, shuffled and split between train and test sets
X_train, X_test, y_train, y_test = model_selection.train_test_split(X,y, test_size=0.2, random_state=0)
if K.image_dim_ordering() == 'th':
X_train = X_train.reshape(X_train.shape[0], 1, img_rows, img_cols)
X_test = X_test.reshape(X_test.shape[0], 1, img_rows, img_cols)
input_shape = (1, img_rows, img_cols)
else:
X_train = X_train.reshape(X_train.shape[0], img_rows, img_cols, 1)
X_test = X_test.reshape(X_test.shape[0], img_rows, img_cols, 1)
input_shape = (img_rows, img_cols, 1)
X_train = X_train.astype('float32')
X_test = X_test.astype('float32')
X_train /= 255
X_test /= 255
print('X_train shape:', X_train.shape)
print(X_train.shape[0], 'train samples')
print(X_test.shape[0], 'test samples')
# convert class vectors to binary class matrices
Y_train = np_utils.to_categorical(y_train, nb_classes)
Y_test = np_utils.to_categorical(y_test, nb_classes)
model = Sequential()
model.add(Convolution2D(nb_filters, kernel_size[0], kernel_size[1],
border_mode='valid',
input_shape=input_shape))
model.add(BatchNormalization())
# model.add(Activation('relu'))
model.add(Activation('tanh'))
model.add(MaxPooling2D(pool_size=pool_size))
#model.add(Dropout(0.25))
model.add(Convolution2D(5, 5, 5, border_mode='valid'))
model.add(BatchNormalization())
model.add(Activation('tanh'))
model.add(MaxPooling2D(pool_size=(5,5)))
model.add(Flatten())
model.add(Dense(4))
model.add(BatchNormalization())
model.add(Activation('tanh'))
#model.add(Activation('relu'))
#model.add(Dropout(0.5))
model.add(Dense(nb_classes))
model.add(Activation('softmax'))
model.compile(loss='categorical_crossentropy',
optimizer='adadelta',
metrics=['accuracy'])
# earlyStopping=callbacks.EarlyStopping(monitor='val_loss', patience=3, verbose=1, mode='auto')
history = model.fit(X_train, Y_train, batch_size=batch_size, nb_epoch=nb_epoch,
verbose=0, validation_data=(X_test, Y_test)) #, callbacks=[earlyStopping])
score = model.evaluate(X_test, Y_test, verbose=0)
Y_test_pred = model.predict(X_test, verbose=0)
print('Confusion metrix')
y_test_pred = np_utils.categorical_probas_to_classes(Y_test_pred)
print(metrics.confusion_matrix(y_test, y_test_pred))
print('Test score:', score[0])
print('Test accuracy:', score[1])
kkeras.plot_acc( history)
plt.show()
kkeras.plot_loss( history)
def _run_dl_mgh_params_r0(X,
y,
Lx,
Ly,
nb_epoch=5000,
batch_size=128,
nb_classes=2):
# input image dimensions
img_rows, img_cols = Lx, Ly
# number of convolutional filters to use
nb_filters = 8
# size of pooling area for max pooling
pool_size = (50, 50)
# convolution kernel size
kernel_size = (20, 20)
# the data, shuffled and split between train and test sets
X_train, X_test, y_train, y_test = model_selection.train_test_split(
X, y, test_size=0.2, random_state=0)
if K.image_dim_ordering() == 'th':
X_train = X_train.reshape(X_train.shape[0], 1, img_rows, img_cols)
X_test = X_test.reshape(X_test.shape[0], 1, img_rows, img_cols)
input_shape = (1, img_rows, img_cols)
else:
X_train = X_train.reshape(X_train.shape[0], img_rows, img_cols, 1)
X_test = X_test.reshape(X_test.shape[0], img_rows, img_cols, 1)
input_shape = (img_rows, img_cols, 1)
X_train = X_train.astype('float32')
X_test = X_test.astype('float32')
X_train /= 255
X_test /= 255
print('X_train shape:', X_train.shape)
print(X_train.shape[0], 'train samples')
print(X_test.shape[0], 'test samples')
# convert class vectors to binary class matrices
Y_train = np_utils.to_categorical(y_train, nb_classes)
Y_test = np_utils.to_categorical(y_test, nb_classes)
model = Sequential()
model.add(
Convolution2D(nb_filters,
kernel_size[0],
kernel_size[1],
border_mode='valid',
input_shape=input_shape))
model.add(Activation('relu'))
model.add(MaxPooling2D(pool_size=pool_size))
model.add(Dropout(0.25))
model.add(Flatten())
model.add(Dense(4))
model.add(Activation('relu'))
model.add(Dropout(0.5))
model.add(Dense(nb_classes))
model.add(Activation('softmax'))
model.compile(loss='categorical_crossentropy',
optimizer='adadelta',
metrics=['accuracy'])
earlyStopping = callbacks.EarlyStopping(monitor='val_loss',
patience=3,
verbose=1,
mode='auto')
history = model.fit(
X_train,
Y_train,
batch_size=batch_size,
nb_epoch=nb_epoch,
verbose=0,
validation_data=(X_test, Y_test)) #, callbacks=[earlyStopping])
score = model.evaluate(X_test, Y_test, verbose=0)
print('Test score:', score[0])
print('Test accuracy:', score[1])
kkeras.plot_acc(history)
plt.show()
kkeras.plot_loss(history)