def getcomplexmodel(data, labels, verbose, epochs, name) -> Sequential:
# print("Data size: " + str(len(data)))
# print("No. of classes: " + str(len(labels)))
labels = np.asarray(labels).astype('float32')
model = Sequential()
model.add(Dense(32, activation='relu', input_dim=1))
model.add(Dense(32, activation='relu'))
model.add(Dense(1, activation='linear'))
model.compile(optimizer='adam',
loss='mse',
metrics=['mse', 'accuracy', 'mae'])
history = model.fit(
data,
labels,
verbose=verbose,
epochs=epochs,
# batch_size=512,
#validation_data=(x_val, y_val)
)
final_accuracy = history.history['acc'][-1]
final_loss = history.history['loss'][-1]
print("MODEL: {:15} | Loss: {:20} | Accuracy: {:20}".format(
name, final_loss, final_accuracy))
# with open(DATA_PATH + "modelaccuracy.data", "a") as f:
# f.write(name + "," + str(final_accuracy) + "\n")
kerasify.export_model(model, name + ".model")
return model
def create_model(input_dict_size,
output_dict_size,
input_length=DEFAULT_INPUT_LENGTH,
output_length=DEFAULT_OUTPUT_LENGTH):
encoder_input = Input(shape=(input_length, ))
decoder_input = Input(shape=(output_length, ))
encoder = Embedding(input_dict_size,
64,
input_length=input_length,
mask_zero=True)(encoder_input)
encoder = LSTM(64, return_sequences=False)(encoder)
decoder = Embedding(output_dict_size,
64,
input_length=output_length,
mask_zero=True)(decoder_input)
decoder = LSTM(64, return_sequences=True)(decoder,
initial_state=[encoder, encoder])
decoder = TimeDistributed(Dense(output_dict_size,
activation="softmax"))(decoder)
model = Model(inputs=[encoder_input, decoder_input], outputs=[decoder])
model.compile(optimizer='adam', loss='categorical_crossentropy')
return model
def generate_inceptionResnetv2_based_model():
irv2 = tf.keras.applications.inception_resnet_v2.InceptionResNetV2(
include_top=False)
irv2.trainable = False
# This returns a tensor
input1 = Input(shape=(299, 299, 3), name='input1')
input2 = Input(shape=(299, 299, 3), name='input2')
out1 = irv2(input1)
out2 = irv2(input2)
averPool = AveragePooling2D(pool_size=(8, 8))
out1 = averPool(out1)
out2 = averPool(out2)
y = concatenate([out1, out2])
dense = Dense(1)
y = dense(y)
activation = Activation('tanh')
y = activation(y)
y = Flatten()(y)
model = Model(inputs=[input1, input2], outputs=y)
return model
# 4th Convolutional Layer
model.add(
Conv2D(filters=384, kernel_size=(3, 3), strides=(1, 1), padding='valid'))
model.add(Activation('relu'))
# 5th Convolutional Layer
model.add(
Conv2D(filters=256, kernel_size=(3, 3), strides=(1, 1), padding='valid'))
model.add(Activation('relu'))
# Max Pooling
# Passing it to a Fully Connected layer
model.add(Flatten())
# 1st Fully Connected Layer
model.add(Dense(4096, input_shape=(200 * 200 * 3, )))
model.add(Activation('relu'))
# Add Dropout to prevent overfitting
model.add(Dropout(0.4))
# 2nd Fully Connected Layer
model.add(Dense(4096))
model.add(Activation('relu'))
# Add Dropout
model.add(Dropout(0.4))
# 3rd Fully Connected Layer
model.add(Dense(1000))
model.add(Activation('relu'))
# Add Dropout
model.add(Dropout(0.4))
import tensorflow as tf
from tensorflow._api.v1.keras import preprocessing
from tensorflow._api.v1.keras.layers import Input, Dense, Conv2D, MaxPool2D, Dropout, ReLU, BatchNormalization, concatenate, Flatten, GlobalAveragePooling2D
from tensorflow._api.v1.keras.models import Model
# This returns a tensor
inputs = Input(shape=(32, 32, 3))
pre_net = Conv2D(64, (7, 7), strides=(2, 2))
# a layer instance is callable on a tensor, and returns a tensor
x = Dense(64, activation='relu')(inputs)
x = Dense(64, activation='relu')(x)
predictions = Dense(10, activation='softmax')(x)
# This creates a model that includes
# the Input layer and three Dense layers
model = Model(inputs=inputs, outputs=predictions)
model.compile(optimizer='rmsprop',
loss='categorical_crossentropy',
metrics=['accuracy'])
model.summary()
print(img_data.shape)
img_data = np.rollaxis(img_data, 1, 0)
print(img_data.shape)
img_data = img_data[0]
print(img_data.shape)
num_classes = 6
train_X, test_X, train_Y, test_Y = train_test_split(img_data,
label_array,
test_size=0.10)
image_input = Input(shape=(224, 224, 3))
model = VGG19(input_tensor=image_input, include_top=True, weights=None)
last_layer = model.get_layer('fc2').output #VGG
# last_layer = model.get_layer('fc1000').output #RES
# last_layer = model.get_layer('predictions').output
last_layer = Dropout(0.5)(last_layer)
out = Dense(num_classes, activation="softmax", name="output")(last_layer)
model = Model(image_input, out)
for layer in model.layers[:-1]:
layer.trainable = False
model.summary()
model.compile(loss='sparse_categorical_crossentropy',
optimizer=Adam(lr=0.001,
beta_1=0.9,
beta_2=0.999,
epsilon=1e-08,
decay=0.0),
metrics=['accuracy'])
hist = model.fit(train_X,
train_Y,
pre_net = Conv2D(64, (7, 7), strides=(2, 2))(inputs)
pre_net = ReLU()(pre_net)
pre_net = MaxPool2D(pool_size=(3, 3), strides=(1, 1))(pre_net)
pre_net = BatchNormalization()(pre_net)
def feature_extractor(input_net):
net_1 = Conv2D(96, 1, 1)(input_net)
net_1 = ReLU()(net_1)
net_1 = Conv2D(208, 3, 1)(net_1)
net_1 = ReLU()(net_1)
net_2 = MaxPool2D(3, 1)(input_net)
net_2 = Conv2D(64, 1, 1)(net_2)
net_2 = ReLU()(net_2)
concat = concatenate(inputs=[net_1, net_2], axis=3)
pooling_out = MaxPool2D(3, 2)(concat)
return pooling_out
feat_ex_1 = feature_extractor(pre_net)
feat_ex_2 = feature_extractor(feat_ex_1)
net = GlobalAveragePooling2D()(feat_ex_2)
output = Dense(units=11, activation='softmax')(net)
model = Model(inputs=inputs, outputs=output)
#model.summary()
model.compile(optimizer='adam', loss='categorical_crossentropy', metrics=['accuracy'])
def main(train_epochs):
print('Hello Lenin Welcome to Transfer Learning with VGG16')
# Reading images to form X vector
labels_name = {'benign': 0, 'malignant': 1}
img_data, img_labels = read_dataset('/data_roi_single/train',
labels_dict=labels_name)
print(np.unique(img_labels, return_counts=True))
# categories_names = ['benign', 'malignant']
num_classes = 2
# labels = labelling_outputs(num_classes, img_data.shape[0])
# labels = labelling_mammo(num_classes, img_data.shape[0])
# converting class labels to one-hot encoding
y_one_hot = to_categorical(img_labels, num_classes)
#Shuffle data
x, y = shuffle(img_data, y_one_hot, random_state=2)
# Dataset split
xtrain, xtest, ytrain, ytest = train_test_split(x,
y,
test_size=0.2,
random_state=2)
#########################################################################################
# Custom_vgg_model_1
# Training the classifier alone
image_input = Input(shape=(224, 224, 3))
model = VGG16(input_tensor=image_input,
include_top=True,
weights='imagenet')
model.summary()
last_layer = model.get_layer('fc2').output
out = Dense(num_classes, activation='sigmoid',
name='vgg16TL')(last_layer) # sigmoid insted of softmax
custom_vgg_model = Model(image_input, out)
custom_vgg_model.summary()
# until this point the custom model is retrainable at all layers
# Now we freeze all the layers up to the last one
for layer in custom_vgg_model.layers[:-1]:
layer.trainable = False
custom_vgg_model.summary()
# custom_vgg_model.layers[3].trainable
# custom_vgg_model.layers[-1].trainable
# Model compilation
custom_vgg_model.compile(
loss='binary_crossentropy', optimizer='rmsprop',
metrics=['accuracy']) # binary cross entropy instead of categorical
print('Transfer Learning Training...')
t = time.time()
num_of_epochs = train_epochs # User defines number of epochs
hist = custom_vgg_model.fit(xtrain,
ytrain,
batch_size=64,
epochs=num_of_epochs,
verbose=1,
validation_data=(xtest, ytest))
print('Training time: %s' % (time.time() - t))
# Model saving parameters
custom_vgg_model.save('vgg16_tf_bc.h5')
print('Evaluation...')
(loss, accuracy) = custom_vgg_model.evaluate(xtest,
ytest,
batch_size=10,
verbose=1)
print("[INFO] loss={:.4f}, accuracy: {:.4f}%".format(loss, accuracy * 100))
print("Finished")
# Model Training Graphics
# Visualizing losses and accuracy
train_loss = hist.history['loss']
val_loss = hist.history['val_loss']
train_acc = hist.history['acc']
val_acc = hist.history['val_acc']
xc = range(num_of_epochs) # Este valor esta anclado al numero de epocas
plt.figure(1, figsize=(7, 5))
plt.plot(xc, train_loss)
plt.plot(xc, val_loss)
plt.xlabel('num of epochs')
plt.ylabel('loss')
plt.title('train_loss vs val_loss')
plt.grid(True)
plt.legend(['train', 'val'])
plt.style.use(['classic']) # revisar que mas hay
plt.savefig('vgg16_train_val_loss.jpg')
plt.figure(2, figsize=(7, 5))
plt.plot(xc, train_acc)
plt.plot(xc, val_acc)
plt.xlabel('num of epochs')
plt.ylabel('accuracy')
plt.title('train_accuracy vs val_accuracy')
plt.grid(True)
plt.legend(['train', 'val'], loc=4)
plt.style.use(['classic']) # revisar que mas hay
plt.savefig('vgg16_train_val_acc.jpg')
plt.show()
X, y = data
X = X / 255.0
print(len(X))
model = Sequential()
model.add(Conv2D(64, (3, 3), input_shape=X.shape[1:]))
model.add(Activation("relu"))
model.add(MaxPooling2D(pool_size=(2, 2)))
model.add(Conv2D(64, (3, 3)))
model.add(Activation("relu"))
model.add(MaxPooling2D(pool_size=(2, 2)))
model.add(Flatten())
model.add(Dense(64))
model.add(Activation('relu'))
model.add(Dense(1))
model.add(Activation('sigmoid'))
model.compile(loss='binary_crossentropy',
optimizer='adam',
metrics=['accuracy'])
model.fit(X,
y,
batch_size=32,
epochs=1,
validation_split=0.3,
callbacks=[tensorboard])
(X_train, y_train), (X_test, y_test) = mnist.load_data()
# image check
plt.imshow(X_train[0])
plt.show()
print(X_train)
X_train = X_train.reshape(60000, 28, 28, 1)
X_test = X_test.reshape(10000, 28, 28, 1)
y_train = to_categorical(y_train)
y_test = to_categorical(y_test)
# CNN
from tensorflow._api.v1.keras.models import Sequential
from tensorflow._api.v1.keras.layers import Dense, Conv2D, Flatten
model = Sequential()
model.add(Conv2D(64, kernel_size=3, activation='relu',
input_shape=(28, 28, 1)))
model.add(Conv2D(32, kernel_size=3, activation='relu'))
model.add(Flatten())
model.add(Dense(10, activation='softmax'))
model.compile(optimizer='adam',
loss='categorical_crossentropy',
metrics=['accuracy'])
model.fit(X_train, y_train, validation_data=(X_test, y_test), epochs=3)
target_size=(200, 200))
from tensorflow._api.v1.keras.models import Sequential
from tensorflow._api.v1.keras.layers import Dense, Conv2D, Flatten, MaxPooling2D, Dropout
model = Sequential()
model.add(
Conv2D(32, kernel_size=3, activation='relu', input_shape=(200, 200, 3)))
model.add(MaxPooling2D(pool_size=(3, 3), strides=(2, 2), padding='valid'))
model.add(Conv2D(64, kernel_size=3, activation='relu'))
model.add(MaxPooling2D(pool_size=(3, 3), strides=(2, 2), padding='valid'))
model.add(Conv2D(64, kernel_size=3, activation='relu'))
model.add(MaxPooling2D(pool_size=(3, 3), strides=(2, 2), padding='valid'))
model.add(Flatten())
model.add(Dense(512, activation='relu'))
model.add(Dropout(0.5))
model.add(Dense(512, activation='relu'))
model.add(Dropout(0.5))
model.add(Dense(2, activation='softmax'))
model.compile(optimizer='adam',
loss='categorical_crossentropy',
metrics=['accuracy'])
STEP_SIZE_TRAIN = train_gen.n // train_gen.batch_size
STEP_SIZE_VALID = valid_gen.n // valid_gen.batch_size
STEP_SIZE_TEST = ceil(test_gen.n / test_gen.batch_size)
history = model.fit_generator(generator=train_gen,
steps_per_epoch=STEP_SIZE_TRAIN,