Here in this code UpSampling2D
and Conv2DTranspose
seem to be used interchangeably. I want to know why this is happening.
# u-net model with up-convolution or up-sampling and weighted binary-crossentropy as loss func
from keras.models import Model
from keras.layers import Input, Conv2D, MaxPooling2D, UpSampling2D, concatenate, Conv2DTranspose, BatchNormalization, Dropout
from keras.optimizers import Adam
from keras.utils import plot_model
from keras import backend as K
def unet_model(n_classes=5, im_sz=160, n_channels=8, n_filters_start=32, growth_factor=2, upconv=True,
class_weights=[0.2, 0.3, 0.1, 0.1, 0.3]):
droprate=0.25
n_filters = n_filters_start
inputs = Input((im_sz, im_sz, n_channels))
#inputs = BatchNormalization()(inputs)
conv1 = Conv2D(n_filters, (3, 3), activation='relu', padding='same')(inputs)
conv1 = Conv2D(n_filters, (3, 3), activation='relu', padding='same')(conv1)
pool1 = MaxPooling2D(pool_size=(2, 2))(conv1)
#pool1 = Dropout(droprate)(pool1)
n_filters *= growth_factor
pool1 = BatchNormalization()(pool1)
conv2 = Conv2D(n_filters, (3, 3), activation='relu', padding='same')(pool1)
conv2 = Conv2D(n_filters, (3, 3), activation='relu', padding='same')(conv2)
pool2 = MaxPooling2D(pool_size=(2, 2))(conv2)
pool2 = Dropout(droprate)(pool2)
n_filters *= growth_factor
pool2 = BatchNormalization()(pool2)
conv3 = Conv2D(n_filters, (3, 3), activation='relu', padding='same')(pool2)
conv3 = Conv2D(n_filters, (3, 3), activation='relu', padding='same')(conv3)
pool3 = MaxPooling2D(pool_size=(2, 2))(conv3)
pool3 = Dropout(droprate)(pool3)
n_filters *= growth_factor
pool3 = BatchNormalization()(pool3)
conv4_0 = Conv2D(n_filters, (3, 3), activation='relu', padding='same')(pool3)
conv4_0 = Conv2D(n_filters, (3, 3), activation='relu', padding='same')(conv4_0)
pool4_1 = MaxPooling2D(pool_size=(2, 2))(conv4_0)
pool4_1 = Dropout(droprate)(pool4_1)
n_filters *= growth_factor
pool4_1 = BatchNormalization()(pool4_1)
conv4_1 = Conv2D(n_filters, (3, 3), activation='relu', padding='same')(pool4_1)
conv4_1 = Conv2D(n_filters, (3, 3), activation='relu', padding='same')(conv4_1)
pool4_2 = MaxPooling2D(pool_size=(2, 2))(conv4_1)
pool4_2 = Dropout(droprate)(pool4_2)
n_filters *= growth_factor
conv5 = Conv2D(n_filters, (3, 3), activation='relu', padding='same')(pool4_2)
conv5 = Conv2D(n_filters, (3, 3), activation='relu', padding='same')(conv5)
n_filters //= growth_factor
if upconv:
up6_1 = concatenate([Conv2DTranspose(n_filters, (2, 2), strides=(2, 2), padding='same')(conv5), conv4_1])
else:
up6_1 = concatenate([UpSampling2D(size=(2, 2))(conv5), conv4_1])
up6_1 = BatchNormalization()(up6_1)
conv6_1 = Conv2D(n_filters, (3, 3), activation='relu', padding='same')(up6_1)
conv6_1 = Conv2D(n_filters, (3, 3), activation='relu', padding='same')(conv6_1)
conv6_1 = Dropout(droprate)(conv6_1)
n_filters //= growth_factor
if upconv:
up6_2 = concatenate([Conv2DTranspose(n_filters, (2, 2), strides=(2, 2), padding='same')(conv6_1), conv4_0])
else:
up6_2 = concatenate([UpSampling2D(size=(2, 2))(conv6_1), conv4_0])
up6_2 = BatchNormalization()(up6_2)
conv6_2 = Conv2D(n_filters, (3, 3), activation='relu', padding='same')(up6_2)
conv6_2 = Conv2D(n_filters, (3, 3), activation='relu', padding='same')(conv6_2)
conv6_2 = Dropout(droprate)(conv6_2)
n_filters //= growth_factor
if upconv:
up7 = concatenate([Conv2DTranspose(n_filters, (2, 2), strides=(2, 2), padding='same')(conv6_2), conv3])
else:
up7 = concatenate([UpSampling2D(size=(2, 2))(conv6_2), conv3])
up7 = BatchNormalization()(up7)
conv7 = Conv2D(n_filters, (3, 3), activation='relu', padding='same')(up7)
conv7 = Conv2D(n_filters, (3, 3), activation='relu', padding='same')(conv7)
conv7 = Dropout(droprate)(conv7)
n_filters //= growth_factor
if upconv:
up8 = concatenate([Conv2DTranspose(n_filters, (2, 2), strides=(2, 2), padding='same')(conv7), conv2])
else:
up8 = concatenate([UpSampling2D(size=(2, 2))(conv7), conv2])
up8 = BatchNormalization()(up8)
conv8 = Conv2D(n_filters, (3, 3), activation='relu', padding='same')(up8)
conv8 = Conv2D(n_filters, (3, 3), activation='relu', padding='same')(conv8)
conv8 = Dropout(droprate)(conv8)
n_filters //= growth_factor
if upconv:
up9 = concatenate([Conv2DTranspose(n_filters, (2, 2), strides=(2, 2), padding='same')(conv8), conv1])
else:
up9 = concatenate([UpSampling2D(size=(2, 2))(conv8), conv1])
conv9 = Conv2D(n_filters, (3, 3), activation='relu', padding='same')(up9)
conv9 = Conv2D(n_filters, (3, 3), activation='relu', padding='same')(conv9)
conv10 = Conv2D(n_classes, (1, 1), activation='sigmoid')(conv9)
model = Model(inputs=inputs, outputs=conv10)
def weighted_binary_crossentropy(y_true, y_pred):
class_loglosses = K.mean(K.binary_crossentropy(y_true, y_pred), axis=[0, 1, 2])
return K.sum(class_loglosses * K.constant(class_weights))
model.compile(optimizer=Adam(), loss=weighted_binary_crossentropy)
return model
UpSampling2D is just a simple scaling up of the image by using nearest neighbour or bilinear upsampling, so nothing smart. Advantage is it's cheap.
Conv2DTranspose is a convolution operation whose kernel is learnt (just like normal conv2d operation) while training your model. Using Conv2DTranspose will also upsample its input but the key difference is the model should learn what is the best upsampling for the job.
EDIT: Link to nice visualization of transposed convolution: https://towardsdatascience.com/types-of-convolutions-in-deep-learning-717013397f4d