def my_cnn_network(width, dicom_path, masks_path, prag, train_dim, test_dim):
x_train, y_train = train_the_network(dicom_path, masks_path)
x_train = x_train.reshape(train_dim, width, width, 1)
y_train = y_train.reshape(train_dim, width, width, 1)
# arhitectura
inp = Input((width, width, 1))
l = Conv2D(32, (2, 2), padding='same')(inp)
l = BatchNormalization()(l)
l = Activation('relu')(l)
l = AveragePooling2D((2, 2))(l)
l = Conv2D(64, (3, 3), padding='same')(l)
l = BatchNormalization()(l)
l = Activation('relu')(l)
l = AveragePooling2D((2, 2))(l)
l = Conv2D(256, (3, 3), padding='same')(l)
l = BatchNormalization()(l)
l = Activation('relu')(l)
l = AveragePooling2D((2, 2))(l)
l = Conv2DTranspose(128, (3, 3), strides=2, padding='same')(l)
l = BatchNormalization()(l)
l = Activation('relu')(l)
l = Conv2DTranspose(64, (3, 3), strides=2, padding='same')(l)
l = BatchNormalization()(l)
l = Activation('relu')(l)
l = Conv2DTranspose(32, (3, 3), padding='same')(l)
l = BatchNormalization()(l)
l = Activation('relu')(l)
l = Conv2DTranspose(32, (3, 3), strides=2, padding='same')(l)
l = BatchNormalization()(l)
l = Activation('relu')(l)
decoded = Conv2D(1, (3, 3), activation='sigmoid', padding='same')(l)
l = BatchNormalization()(l)
l = Activation('softmax')(l)
MyModel = Model(inp, decoded)
MyModel.summary()
print()
MyModel.compile(optimizer='adagrad',
loss=losses.mse,
metrics=[
'accuracy',
metrics.Recall(),
metrics.Precision(),
metrics.TruePositives(),
metrics.TrueNegatives(),
metrics.FalseNegatives(),
metrics.FalsePositives()
])
MyModel.fit(x_train, y_train, batch_size=32, epochs=1000)
MyModel.save('model.h5')
def neural_net(train, test):
wandb.init(project="bachelor")
keras_model = Sequential()
keras_model.add(Dense(len(train[0][0]), activation="relu"))
keras_model.add(Dense(50, activation="relu"))
keras_model.add(Dense(1, activation="sigmoid"))
keras_model.compile(loss="binary_crossentropy",
optimizer="adam",
metrics=[
'accuracy',
metrics.TruePositives(),
metrics.TrueNegatives(),
metrics.FalsePositives(),
metrics.FalseNegatives()
])
keras_model.fit(train[0],
train[1],
batch_size=3,
epochs=20,
callbacks=[WandbCallback()])
loss, acc, tp, fp, tn, fn = keras_model.evaluate(
test[0], test[1], callbacks=[WandbCallback()])
p = tp / (tp + fp)
r = tp / (tp + fn)
print(f'f-score is: {(2 * p * r) / (p + r)}')
def test_weighted(self):
fp_obj = metrics.FalsePositives()
y_true = ((0, 1, 0, 1, 0), (0, 0, 1, 1, 1), (1, 1, 1, 1, 0), (0, 0, 0,
0, 1))
y_pred = ((0, 0, 1, 1, 0), (1, 1, 1, 1, 1), (0, 1, 0, 1, 0), (1, 1, 1,
1, 1))
sample_weight = (1., 1.5, 2., 2.5)
result = fp_obj(y_true, y_pred, sample_weight=sample_weight)
assert np.allclose(14., K.eval(result))
def test_unweighted_with_thresholds(self):
fp_obj = metrics.FalsePositives(thresholds=[0.15, 0.5, 0.85])
y_pred = ((0.9, 0.2, 0.8, 0.1), (0.2, 0.9, 0.7, 0.6),
(0.1, 0.2, 0.4, 0.3), (0, 1, 0.7, 0.3))
y_true = ((0, 1, 1, 0), (1, 0, 0, 0), (0, 0, 0, 0), (1, 1, 1, 1))
result = fp_obj(y_true, y_pred)
assert np.allclose([7., 4., 2.], K.eval(result))
def define_model():
hidden_nodes = int((DATASET.get_number_of_features() + DATASET.NUM_CLASSES) / 2)
# create and fit the DNN network
model = Sequential()
model.add(Dense(hidden_nodes, input_dim=DATASET.get_number_of_features(), activation='relu'))
model.add(Dense(1, activation='sigmoid'))
model.compile(loss='binary_crossentropy', optimizer='adam',
metrics=["accuracy", km.TruePositives(), km.FalsePositives(), km.TrueNegatives(),
km.FalseNegatives()])
return model
def test_unweighted(self):
fp_obj = metrics.FalsePositives()
y_true = ((0, 1, 0, 1, 0), (0, 0, 1, 1, 1), (1, 1, 1, 1, 0), (0, 0, 0,
0, 1))
y_pred = ((0, 0, 1, 1, 0), (1, 1, 1, 1, 1), (0, 1, 0, 1, 0), (1, 1, 1,
1, 1))
result = fp_obj(y_true, y_pred)
assert np.allclose(7., K.eval(result))
def test_weighted_with_thresholds(self):
fp_obj = metrics.FalsePositives(thresholds=[0.15, 0.5, 0.85])
y_pred = ((0.9, 0.2, 0.8, 0.1), (0.2, 0.9, 0.7, 0.6),
(0.1, 0.2, 0.4, 0.3), (0, 1, 0.7, 0.3))
y_true = ((0, 1, 1, 0), (1, 0, 0, 0), (0, 0, 0, 0), (1, 1, 1, 1))
sample_weight = ((1.0, 2.0, 3.0, 5.0), (7.0, 11.0, 13.0, 17.0),
(19.0, 23.0, 29.0, 31.0), (5.0, 15.0, 10.0, 0))
result = fp_obj(y_true, y_pred, sample_weight=sample_weight)
assert np.allclose([125., 42., 12.], K.eval(result))
def test_config(self):
fp_obj = metrics.FalsePositives(name='my_fp', thresholds=[0.4, 0.9])
assert fp_obj.name == 'my_fp'
assert len(fp_obj.weights) == 1
assert fp_obj.thresholds == [0.4, 0.9]
# Check save and restore config
fp_obj2 = metrics.FalsePositives.from_config(fp_obj.get_config())
assert fp_obj2.name == 'my_fp'
assert len(fp_obj2.weights) == 1
assert fp_obj2.thresholds == [.4, 0.9]
def initializeNN():
from keras.models import Sequential
from keras.layers import Dense
from keras.layers import LeakyReLU
from keras.layers import Dropout
from keras import regularizers
from keras import metrics
#import tensorflow_addons as tfa
### Define metrics
metrics = [
metrics.CategoricalAccuracy(name="accuracy"),
metrics.FalseNegatives(name="fn"),
metrics.FalsePositives(name="fp"),
metrics.TrueNegatives(name="tn"),
metrics.TruePositives(name="tp"),
metrics.Precision(name="precision"),
metrics.Recall(name="recall"),
metrics.AUC(name='auc') #,
#tfa.metrics.CohenKappa(name='kappa')
]
# define the keras model
nn = Sequential()
nn.add(Dense(256, input_dim=102,
kernel_regularizer='l1')) #, activation='relu'))
nn.add(LeakyReLU(alpha=0.1))
nn.add(Dropout(0.1))
nn.add(Dense(128)) #, activation='relu'))#,kernel_regularizer='l1'))
nn.add(LeakyReLU(alpha=0.1))
nn.add(Dropout(0.1))
nn.add(Dense(64)) #, activation='relu'))#,kernel_regularizer='l1'))
nn.add(LeakyReLU(alpha=0.1))
nn.add(Dropout(0.1))
nn.add(Dense(64)) #, activation='relu'))#,kernel_regularizer='l1'))
nn.add(LeakyReLU(alpha=0.1))
nn.add(Dropout(0.1))
nn.add(Dense(31, activation='softmax'))
nn.compile(loss='categorical_crossentropy',
optimizer='Adamax',
metrics=metrics)
return nn
def train_cnn_model(x_train, y_train):
x_train = array(x_train)
x_train = x_train.reshape((len(x_train), 3, int(len(x_train[0])/3), 1))
y_train = array(y_train)
#create model
cnn_model = Sequential()
cnn_model.add(Conv2D(64,
kernel_size=3,
activation='relu',
input_shape=(3,21,1),
padding='same'))
cnn_model.add(layers.BatchNormalization(1))
cnn_model.add(Conv2D(64,
kernel_size=3,
activation='relu',
padding='same'))
cnn_model.add(layers.BatchNormalization(1))
cnn_model.add(MaxPooling2D(2,2))
cnn_model.add(Flatten())
cnn_model.add(Dense(512, activation = 'relu'))
cnn_model.add(Dense(1, activation='sigmoid'))
# compile and fit
cnn_model.compile(optimizer='Adam',
loss='binary_crossentropy',
metrics=['acc',
metrics.AUC(),
metrics.FalseNegatives(),
metrics.Recall(),
metrics.Precision(),
metrics.FalseNegatives(),
metrics.TrueNegatives(),
metrics.FalsePositives(),
metrics.TruePositives()])
cnn_history = cnn_model.fit(x_train, y_train,
epochs=100,
batch_size=16,
validation_split=0.2,
callbacks=[callbacks.EarlyStopping(monitor='val_loss', patience=5),
callbacks.LearningRateScheduler(scheduler)])
print("finish training cnn model")
return cnn_model, cnn_history
def all_experiment_model(hp):
PRE_TRAINED_MODEL = Xception(input_shape=(IMG_HEIGHT, IMG_WIDTH, 3),
include_top=False,
pooling='avg',
weights='imagenet')
for layer in PRE_TRAINED_MODEL.layers:
layer.trainable = False
x = layers.Flatten()(PRE_TRAINED_MODEL.output)
for i in range(
hp.Int('number_of_dense_dropout_blocks', min_value=0,
max_value=2)):
x = layers.Dense(hp.Int(f'dense_units_{i}',
min_value=1024,
max_value=4096,
step=512),
activation='relu')(x)
x = layers.Dropout(
hp.Float(f'dropout_probability_{i}',
min_value=0,
max_value=0.3,
step=0.05))(x)
x = layers.Dense(hp.Int(f'penultimate_dense_unit',
min_value=1024,
max_value=4096,
step=512),
activation='relu')(x)
x = layers.Dense(1, activation='sigmoid')(x)
MODEL = Model(PRE_TRAINED_MODEL.input, x)
chosen_loss = hp.Choice(
'loss', values=['SigmoidFocalCrossEntropy', 'BinaryCrossentropy'])
MODEL.compile(optimizer=hp.Choice('optimiser',
values=['Adam', 'RMSprop', 'SGD']),
loss=eval(chosen_loss)(),
metrics=[
metrics.BinaryAccuracy(name='acc'),
metrics.AUC(name='auc'),
metrics.FalsePositives(name='fp')
])
return MODEL
def optimiser_experiment_model(hp):
PRE_TRAINED_MODEL = Xception(input_shape=(IMG_HEIGHT, IMG_WIDTH, 3),
include_top=False,
pooling='avg',
weights='imagenet')
for layer in PRE_TRAINED_MODEL.layers:
layer.trainable = False
x = layers.Flatten()(PRE_TRAINED_MODEL.output)
x = layers.Dense(1, activation='sigmoid')(x)
MODEL = Model(PRE_TRAINED_MODEL.input, x)
MODEL.compile(optimizer=hp.Choice('optimiser',
values=['Adam', 'RMSprop', 'SGD']),
loss='binary_crossentropy',
metrics=[
metrics.BinaryAccuracy(name='acc'),
metrics.AUC(name='auc'),
metrics.FalsePositives(name='fp')
])
return MODEL
def train_lstm_model(x_train, y_train):
x_train = array(x_train)
x_train = x_train.reshape((len(x_train), 1, len(x_train[0])))
print("x_train.shape", x_train.shape)
print(x_train[0])
y_train = array(y_train)
print("y_train.shape", y_train.shape)
# imrpove log: use batch size 16 and add one more lstm layer
lstm_model = Sequential()
lstm_model.add(LSTM(16,
input_shape=(1, 63),
return_sequences=True))
lstm_model.add(LSTM(16, ))
lstm_model.add(layers.Dense(1, activation='sigmoid'))
lstm_model.compile(optimizer='rmsprop',
loss='binary_crossentropy',
metrics=['acc',
metrics.AUC(),
metrics.FalseNegatives(),
metrics.Recall(),
metrics.Precision(),
metrics.FalseNegatives(),
metrics.TrueNegatives(),
metrics.FalsePositives(),
metrics.TruePositives()])
lstm_history = lstm_model.fit(x_train, y_train,
epochs=100,
batch_size=16,
validation_split=0.2,
callbacks=[callbacks.EarlyStopping(monitor='val_loss', patience=5),
callbacks.LearningRateScheduler(scheduler)])
print("finish training lstm model")
return lstm_model, lstm_history
def loss_experiment_model(hp):
PRE_TRAINED_MODEL = Xception(input_shape=(IMG_HEIGHT, IMG_WIDTH, 3),
include_top=False,
pooling='avg',
weights='imagenet')
for layer in PRE_TRAINED_MODEL.layers:
layer.trainable = False
x = layers.Flatten()(PRE_TRAINED_MODEL.output)
x = layers.Dense(1, activation='sigmoid')(x)
MODEL = Model(PRE_TRAINED_MODEL.input, x)
chosen_loss = hp.Choice(
'loss', values=['SigmoidFocalCrossEntropy', 'BinaryCrossentropy'])
MODEL.compile(optimizer='adam',
loss=eval(chosen_loss)(),
metrics=[
metrics.BinaryAccuracy(name='acc'),
metrics.AUC(name='auc'),
metrics.FalsePositives(name='fp')
])
return MODEL
def test_threshold_limit(self):
with pytest.raises(Exception):
metrics.FalsePositives(thresholds=[-1, 0.5, 2])
with pytest.raises(Exception):
metrics.FalsePositives(thresholds=[None])
imerg=HDF5Matrix(path+'imerg_2019_200_3h.h5','data')
goes=HDF5Matrix(path+'nor_goes_2019_800_3h_re.h5','data')
#gfs=HDF5Matrix(path+'nor_gfs_2019_100_3h.h5','data')
print(imerg.shape, label.shape,goes.shape, flush=True)
model=UNet()
print(model.summary(),flush=True)
model = multi_gpu_model(model,gpus=2)
metrics = [
metrics.FalseNegatives(name="fn"),
metrics.FalsePositives(name="fp"),
metrics.TrueNegatives(name="tn"),
metrics.TruePositives(name="tp"),
metrics.Precision(name="precision"),
metrics.Recall(name="recall"),
]
model.compile(optimizer="Adam", loss='binary_crossentropy', metrics=metrics)
epochs=500
batch_size=16
earlystopper = EarlyStopping(patience=50,verbose=1, monitor='val_loss')
checkpointer = ModelCheckpoint('model_ck_mse_new.h5', save_best_only=True, verbose=1)
history=model.fit([goes,imerg], label, epochs=epochs, batch_size=batch_size,
for layer in PRE_TRAINED_MODEL.layers:
layer.trainable = False
x = layers.Flatten()(PRE_TRAINED_MODEL.output)
x = layers.Dense(1024, activation = 'relu')(x)
x = layers.Dropout(0.2)(x)
x = layers.Dense(1, activation = 'sigmoid')(x)
MODEL = Model(PRE_TRAINED_MODEL.input, x)
MODEL.compile(optimizer = RMSprop(lr = LEARNING_RATE),
loss = 'binary_crossentropy',
metrics = [
metrics.BinaryAccuracy(name = 'acc'),
metrics.AUC(name = 'auc'),
metrics.FalsePositives(name = 'fp')
])
EARLY_STOPPING = EarlyStopping(monitor='fp',
verbose=1,
patience=50,
mode='max',
restore_best_weights=True)
CLASS_WEIGHT = {0: 0.001694915254237288,
1: 0.00017733640716439085}
# CLASS_WEIGHT = {0: 9,
# 1: 1}
# CLASS_WEIGHT = {0: 1,
# 1: 1}
model.add(Dense(units_11, activation=activation_11))
model.add(Dropout(dropout_11))
model.add(Dense(units_12, activation=activation_12))
model.add(Dropout(dropout_12))
model.add(Dense(nb_classes, activation='sigmoid'))
METRICS = [
metrics.BinaryAccuracy(name='ACCURACY'),
metrics.Precision(name='PRECISION'),
metrics.Recall(name='RECALL'),
metrics.AUC(name='AUC'),
metrics.TruePositives(name='TP'),
metrics.TrueNegatives(name='TN'),
metrics.FalsePositives(name='FP'),
metrics.FalseNegatives(name='FN')]
model.compile(loss='binary_crossentropy',
optimizer=compile_optimizer,
metrics=METRICS)
# GENERATORS
train_datagen = ImageDataGenerator(
rescale=1. / 255,
shear_range=0.2,
zoom_range=0.2,
horizontal_flip=True,
validation_split=validation_split)
test_datagen = ImageDataGenerator(rescale=1. / 255)
