dataset = geometric_3d_dataset.Geometric3DDataset(patch_size=patch_size,
task=geometric_3d_dataset.Geometric3DDataset.CLASSIFICATION_TASK,
centered=True)
for e in range(nb_epoch):
train_iterator = dataset.iterator(batch_size=batch_size,
num_batches=nb_test_batches)
for b in range(nb_train_batches):
X_batch, Y_batch = train_iterator.next()
loss = model.train(X_batch, Y_batch)
print 'loss: ' + str(loss)
test_iterator = dataset.iterator(batch_size=batch_size,
num_batches=nb_train_batches)
for b in range(nb_test_batches):
X_batch, Y_batch = test_iterator.next()
error = model.test(X_batch, Y_batch)
print 'error: ' + str(error)
kernel_initializer=rnd_normal_init,
bias_initializer=rnd_normal_init))
model.add(Dropout(0.5))
model.add(
Dense(30,
activation='relu',
kernel_initializer=rnd_normal_init,
bias_initializer=rnd_normal_init))
model.add(Dropout(0.5))
model.add(
Dense(num_classes,
activation='softmax',
kernel_initializer=rnd_normal_init,
bias_initializer=rnd_normal_init))
model.summary()
model.compile(
loss='categorical_crossentropy', #sum_squared_error
optimizer=keras.optimizers.Adam(lr=0.1),
metrics=['categorical_accuracy'])
history = model.fit(x_train,
y_train,
batch_size=batch_size,
epochs=epochs,
verbose=2,
validation_data=(x_test_official, y_test_official))
score = model.test(x_test, y_test, verbose=0)
print('Test loss:', score[0])
print('Test accuracy:', score[1])
samplewise_std_normalization=False, # divide each input by its std
zca_whitening=False, # apply ZCA whitening
rotation_range=20, # randomly rotate images in the range (degrees, 0 to 180)
width_shift_range=0.2, # randomly shift images horizontally (fraction of total width)
height_shift_range=0.2, # randomly shift images vertically (fraction of total height)
horizontal_flip=True, # randomly flip images
vertical_flip=False,
) # randomly flip images
# compute quantities required for featurewise normalization
# (std, mean, and principal components if ZCA whitening is applied)
datagen.fit(X_train)
for e in range(nb_epoch):
print("-" * 40)
print("Epoch", e)
print("-" * 40)
print("Training...")
# batch train with realtime data augmentation
progbar = generic_utils.Progbar(X_train.shape[0])
for X_batch, Y_batch in datagen.flow(X_train, Y_train):
loss = model.train(X_batch, Y_batch)
progbar.add(X_batch.shape[0], values=[("train loss", loss)])
print("Testing...")
# test time!
progbar = generic_utils.Progbar(X_test.shape[0])
for X_batch, Y_batch in datagen.flow(X_test, Y_test):
score = model.test(X_batch, Y_batch)
progbar.add(X_batch.shape[0], values=[("test loss", score)])
model.add(Dropout(0.3))
model.add(Dense(50, 1, init='uniform'))
sgd = SGD(lr=0.001, decay=1e-6, momentum=0.5, nesterov=True)
rmsprop = RMSprop(lr=0.0001, rho=0.5, epsilon=1e-6)
model.compile(loss='mean_absolute_error', optimizer=rmsprop,class_mode='binary')
# In[25]:
model.fit(a_train, b_train, nb_epoch=500,show_accuracy=True)
score = model.evaluate(a_test, b_test)
# In[26]:
[loss, accuracy] = model.test(a_test, b_test, accuracy=True)
print ('loss:', loss)
print ('accuracy:', accuracy)
temp_pauaw = 0
# In[ ]:
class MelanomaModel:
def __init__(self, nb_train_batches, batch_size, is3D):
self.model = None
self.train_data_set=None
self.test_data_set=None
self.valid_data_set=None
self.is3D = is3D;
# compute the number of mini-batches for training, validation and testing
self.nb_train_batches=nb_train_batches
self.batch_size=batch_size
def create_model(self):
self.model = Sequential()
self.model.add(Convolution3D(16, stack_size=1, nb_row=11, nb_col=11, nb_depth=6, border_mode='valid'))
self.model.add(Activation('relu'))
self.model.add(MaxPooling3D(poolsize=(3, 3, 1)))
self.model.add(Convolution3D(32, stack_size=16, nb_row=5, nb_col=5, nb_depth=1, border_mode='valid' ))
self.model.add(Activation('relu'))
self.model.add(MaxPooling3D(poolsize=(3, 3, 1)))
self.model.add(Convolution3D(64, stack_size=32, nb_row=3, nb_col=3, nb_depth=1, border_mode='valid' ))
self.model.add(MaxPooling3D(poolsize=(3, 3, 1)))
self.model.add(Flatten3D())
self.model.add(Dense(4096, 1024, init='normal'))
self.model.add(Activation('relu'))
self.model.add(Dropout(0.5))
self.model.add(Dense(1024, 512, init='normal'))
self.model.add(Activation('relu'))
self.model.add(Dense(512, 2, init='normal'))
# let's train the self.model using SGD + momentum(how original).
sgd = RMSprop(rho=0.9, epsilon=1e-3, lr=0.001)
self.model.compile(loss='mean_squared_error', optimizer=sgd)
def load_model(self, model_file_path):
model_file = open(model_file_path)
self.model = cPickle.load(model_file)
def load_melanoma_dataset(self, data_dir, training_perc):
# Preparing melanoma dataset
# data directory folder path
file_names = ([data_dir + filename for filename in os.listdir(data_dir) if ".h5" in filename])
random.shuffle(file_names)
train_file_names = file_names[0:int(training_perc*len(file_names))]
test_file_names = file_names[int(training_perc*len(file_names)):]
if self.is3D:
self.train_data_set = MelanomaDataset3D(data_dir, examples=train_file_names)
self.test_data_set = MelanomaDataset3D(data_dir, examples=test_file_names)
else:
self.train_data_set = MelanomaDataset2D(data_dir, examples=train_file_names)
self.test_data_set = MelanomaDataset2D(data_dir, examples=test_file_names)
# storing and printing average error over all the mini-batches in an epoch
def train_model(self, nb_epoch, model_starting_id, model_snapshot_freq, stats_snapshot_freq):
losses = []
errors = []
last_error = float("inf")
for e in range(nb_epoch):
print " Performing Epoch no : " + str(e)+".......",
train_iterator = self.train_data_set.iterator(batch_size=self.batch_size,
num_batches=self.nb_train_batches,
mode='even_shuffled_sequential')
for b in range(self.nb_train_batches):
X_batch, Y_batch = train_iterator.next()
loss = self.model.train(X_batch, Y_batch)
sys.stdout.write("Loss: %f%% \r" % (loss))
sys.stdout.flush()
losses.append(loss)
test_iterator = self.test_data_set.iterator(batch_size=self.batch_size,
mode='sequential')
errors1 = []
while test_iterator.has_next():
X_batch, Y_batch, bacth_files = test_iterator.next()
error = self.model.test(X_batch, Y_batch)
errors1.append(error)
mean_error = np.mean(errors1)
errors.append(mean_error)
print "error: "+ str(mean_error)
if mean_error < last_error:
last_error = mean_error
pickle.dump(self.model, open("best_model_"+str(e)+".pkl","wc"))
if(e % stats_snapshot_freq == 0 and e > 0):
pickle.dump(losses, open("loss.pkl", "wc"))
pickle.dump(errors, open("error.pkl", "wc"))
if(e % model_snapshot_freq == 0 and e > 0):
pickle.dump(self.model, open("trained_model.pkl","wc"))
model_starting_id += 1
model.add(Flatten(nb_filter * 14 * 14 * 14))
model.add(Dense(nb_filter * 14 * 14 * 14, nb_classes, init='normal'))
model.add(Activation('softmax'))
# let's train the model using SGD + momentum (how original).
sgd = SGD(lr=0.01, decay=1e-6, momentum=0.9, nesterov=True)
model.compile(loss='categorical_crossentropy', optimizer=sgd)
dataset = geometric_3d_dataset.Geometric3DDataset(
patch_size=patch_size,
task=geometric_3d_dataset.Geometric3DDataset.CLASSIFICATION_TASK,
centered=True)
for e in range(nb_epoch):
train_iterator = dataset.iterator(batch_size=batch_size,
num_batches=nb_test_batches)
for b in range(nb_train_batches):
X_batch, Y_batch = train_iterator.next()
loss = model.train(X_batch, Y_batch)
print 'loss: ' + str(loss)
test_iterator = dataset.iterator(batch_size=batch_size,
num_batches=nb_train_batches)
for b in range(nb_test_batches):
X_batch, Y_batch = test_iterator.next()
error = model.test(X_batch, Y_batch)
print 'error: ' + str(error)
model.add(Dense(input_dimesion, 250, init='uniform'))
model.add(Activation('sigmoid'))
model.add(Dropout(0.5))
model.add(Dense(250, 50, init='uniform'))
model.add(Dense(50, 1, init='uniform'))
'''
define the optimization function and compile it:
'''
#sgd = SGD(lr=0.001, decay=1e-6, momentum=0.5, nesterov=True)
rmsprop = RMSprop(lr=0.0001, rho=0.5, epsilon=1e-6)
model.compile(loss='mean_absolute_error', optimizer=rmsprop,class_mode='binary')
'''
train the mocdel
'''
print model.fit(a_train, b_train, nb_epoch=500,show_accuracy=True,verbose=1)
'''
test the model
'''
print model.test(a_test, b_test, accuracy=True)
samplewise_center=False, # set each sample mean to 0
featurewise_std_normalization=True, # divide inputs by std of the dataset
samplewise_std_normalization=False, # divide each input by its std
zca_whitening=False, # apply ZCA whitening
rotation_range=20, # randomly rotate images in the range (degrees, 0 to 180)
width_shift_range=0.2, # randomly shift images horizontally (fraction of total width)
height_shift_range=0.2, # randomly shift images vertically (fraction of total height)
horizontal_flip=True, # randomly flip images
vertical_flip=False) # randomly flip images
# compute quantities required for featurewise normalization
# (std, mean, and principal components if ZCA whitening is applied)
datagen.fit(X_train)
for e in range(nb_epoch):
print('-'*40)
print('Epoch', e)
print('-'*40)
print("Training...")
# batch train with realtime data augmentation
progbar = generic_utils.Progbar(X_train.shape[0])
for X_batch, Y_batch in datagen.flow(X_train, Y_train):
loss = model.train(X_batch, Y_batch)
progbar.add(X_batch.shape[0], values=[("train loss", loss)])
print("Testing...")
# test time!
progbar = generic_utils.Progbar(X_test.shape[0])
for X_batch, Y_batch in datagen.flow(X_test, Y_test):
score = model.test(X_batch, Y_batch)
progbar.add(X_batch.shape[0], values=[("test loss", score)])
model = Sequential()
#Input shape: 2D tensor with shape: (nb_samples, input_dim):
# i guess that the nb_samples is the samples dimension
model.add(Dense(input_dimesion, 250, init='uniform'))
model.add(Activation('sigmoid'))
model.add(Dropout(0.5))
model.add(Dense(250, 50, init='uniform'))
model.add(Dropout(0.3))
model.add(Dense(50, 1, init='uniform'))
sgd = SGD(lr=0.001, decay=1e-6, momentum=0.5, nesterov=True)
rmsprop = RMSprop(lr=0.0001, rho=0.5, epsilon=1e-6)
model.compile(loss='mean_absolute_error',
optimizer=rmsprop,
class_mode='binary')
# In[25]:
model.fit(a_train, b_train, nb_epoch=500, show_accuracy=True)
score = model.evaluate(a_test, b_test)
# In[26]:
[loss, accuracy] = model.test(a_test, b_test, accuracy=True)
print('loss:', loss)
print('accuracy:', accuracy)
temp_pauaw = 0
# In[ ]:
