Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Jump to bottom

rewrite get_unet #43

Open
wants to merge 3 commits into
base: master
Choose a base branch
from
Open

rewrite get_unet #43

Changes from all commits
Commits
Show all changes
3 commits
Select commit Hold shift + click to select a range
090b813
rewrite get_unet
Jun 30, 2017
6d0443c
Update train.py
Jun 30, 2017
f701ce0
Update train.py
Jun 30, 2017
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
72 changes: 37 additions & 35 deletions train.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -12,67 +12,69 @@

from data import load_train_data, load_test_data

K.set_image_data_format('channels_last') # TF dimension ordering in this code
K.set_image_data_format('channels_last') # Tensorflow dimension ordering in this code

img_rows = 96
img_cols = 96

smooth = 1.


def dice_coef(y_true, y_pred):
y_true_f = K.flatten(y_true)
y_pred_f = K.flatten(y_pred)
intersection = K.sum(y_true_f * y_pred_f)
return (2. * intersection + smooth) / (K.sum(y_true_f) + K.sum(y_pred_f) + smooth)


def dice_coef_loss(y_true, y_pred):
return -dice_coef(y_true, y_pred)

def conv3x3(kernel_size,input):
return Conv2D(kernel_size,(3,3),activation='relu',padding='same')(input)

def get_unet():
inputs = Input((img_rows, img_cols, 1))
conv1 = Conv2D(32, (3, 3), activation='relu', padding='same')(inputs)
conv1 = Conv2D(32, (3, 3), activation='relu', padding='same')(conv1)
pool1 = MaxPooling2D(pool_size=(2, 2))(conv1)
def concatenate2x2(kernel_size,first,second):
return concatenate([Conv2DTranspose(kernel_size, (2, 2), strides=[2, 2], padding='same')(first), second], axis=3)

conv2 = Conv2D(64, (3, 3), activation='relu', padding='same')(pool1)
conv2 = Conv2D(64, (3, 3), activation='relu', padding='same')(conv2)
pool2 = MaxPooling2D(pool_size=(2, 2))(conv2)
def get_unet():
inputs = Input((img_rows,img_cols,1))
conv1 = conv3x3(32,inputs)
conv1 = conv3x3(32,conv1)
pool1 = MaxPooling2D(pool_size=(2,2))(conv1)

conv3 = Conv2D(128, (3, 3), activation='relu', padding='same')(pool2)
conv3 = Conv2D(128, (3, 3), activation='relu', padding='same')(conv3)
pool3 = MaxPooling2D(pool_size=(2, 2))(conv3)
conv2 = conv3x3(64,pool1)
conv2 = conv3x3(64,conv2)
pool2 = MaxPooling2D(pool_size=(2,2))(conv2)

conv4 = Conv2D(256, (3, 3), activation='relu', padding='same')(pool3)
conv4 = Conv2D(256, (3, 3), activation='relu', padding='same')(conv4)
pool4 = MaxPooling2D(pool_size=(2, 2))(conv4)
conv3 = conv3x3(128,pool2)
conv3 = conv3x3(128,conv3)
pool3 = MaxPooling2D(pool_size=(2,2))(conv3)

conv5 = Conv2D(512, (3, 3), activation='relu', padding='same')(pool4)
conv5 = Conv2D(512, (3, 3), activation='relu', padding='same')(conv5)
conv4 = conv3x3(256,pool3)
conv4 = conv3x3(256,conv4)
pool4 = MaxPooling2D(pool_size=(2,2))(conv4)

up6 = concatenate([Conv2DTranspose(256, (2, 2), strides=(2, 2), padding='same')(conv5), conv4], axis=3)
conv6 = Conv2D(256, (3, 3), activation='relu', padding='same')(up6)
conv6 = Conv2D(256, (3, 3), activation='relu', padding='same')(conv6)
conv5 = conv3x3(512,pool4)
conv5 = conv3x3(512,conv5)

up7 = concatenate([Conv2DTranspose(128, (2, 2), strides=(2, 2), padding='same')(conv6), conv3], axis=3)
conv7 = Conv2D(128, (3, 3), activation='relu', padding='same')(up7)
conv7 = Conv2D(128, (3, 3), activation='relu', padding='same')(conv7)
up6 = concatenate2x2(256,conv5,conv4)
conv6 = conv3x3(256,up6)
conv6 = conv3x3(256,conv6)

up8 = concatenate([Conv2DTranspose(64, (2, 2), strides=(2, 2), padding='same')(conv7), conv2], axis=3)
conv8 = Conv2D(64, (3, 3), activation='relu', padding='same')(up8)
conv8 = Conv2D(64, (3, 3), activation='relu', padding='same')(conv8)
up7 = concatenate2x2(128,conv6,conv3)
conv7 = conv3x3(128,up7)
conv7 = conv3x3(128,conv7)

up9 = concatenate([Conv2DTranspose(32, (2, 2), strides=(2, 2), padding='same')(conv8), conv1], axis=3)
conv9 = Conv2D(32, (3, 3), activation='relu', padding='same')(up9)
conv9 = Conv2D(32, (3, 3), activation='relu', padding='same')(conv9)
up8 = concatenate2x2(64,conv7,conv2)
conv8 = conv3x3(64,up8)
conv8 = conv3x3(64,conv8)

conv10 = Conv2D(1, (1, 1), activation='sigmoid')(conv9)
up9 = concatenate2x2(32,conv8,conv1)
conv9 = conv3x3(32,up9)
conv9 = conv3x3(32,conv9)

model = Model(inputs=[inputs], outputs=[conv10])
conv10= Conv2D(1,(1,1),activation='sigmoid')(conv9)
model = Model(inputs= [inputs],outputs=[conv10])

model.compile(optimizer=Adam(lr=1e-5), loss=dice_coef_loss, metrics=[dice_coef])
model.compile(optimizer=Adam(lr=1e-5),loss=dice_coef,metrics=[dice_coef])

return model

Expand Down Expand Up @@ -114,7 +116,7 @@ def train_and_predict():
print('-'*30)
print('Fitting model...')
print('-'*30)
model.fit(imgs_train, imgs_mask_train, batch_size=32, nb_epoch=20, verbose=1, shuffle=True,
model.fit(imgs_train, imgs_mask_train, batch_size=32, epochs=20, verbose=1, shuffle=True,
validation_split=0.2,
callbacks=[model_checkpoint])

Expand Down