def encoder_layer(img_in, mask_in, filters, kernel_size, bottleneck=True):
conv, mask = PConv2D(filters, kernel_size, strides=2, padding='same')([img_in, mask_in])
if bottleneck:
conv = BatchNormalization(name='EncBN'+str(encoder_layer.counter))(conv, training=train_bn)
conv = Activation('relu')(conv)
encoder_layer.counter += 1
return conv, mask
def decoder_layer(img_in, mask_in, e_conv, e_mask, filters, kernel_size, bottleneck=True):
up_img = UpSampling2D(size=(2,2))(img_in)
up_mask = UpSampling2D(size=(2,2))(mask_in)
concat_img = Concatenate(axis=3)([e_conv,up_img])
concat_mask = Concatenate(axis=3)([e_mask,up_mask])
conv, mask = PConv2D(filters, kernel_size, padding='same')([concat_img, concat_mask])
if bottleneck:
conv = BatchNormalization()(conv)
conv = LeakyReLU(alpha=0.2)(conv)
return conv, mask
def decoder_layer(data_in,
mask_in,
e_conv,
e_mask,
filters,
kernel_size,
bn=True):
up_data = UpSampling2D(size=(2, 2))(data_in)
up_mask = UpSampling2D(size=(2, 2))(mask_in)
concat_data = Concatenate(axis=3)([e_conv, up_data])
concat_mask = Concatenate(axis=3)([e_mask, up_mask])
conv, mask = PConv2D(filters, kernel_size,
padding='same')([concat_data, concat_mask])
if bn:
conv = BatchNormalization()(conv)
conv = LeakyReLU(alpha=0.2)(conv)
return conv, mask
def decoder_layer(img_in,
mask_in,
e_conv,
e_mask,
filters,
kernel_size,
bn=True):
# up-sample and concatenate
up_img = UpSampling2D(size=(2, 2))(img_in)
up_mask = UpSampling2D(size=(2, 2))(mask_in)
concat_img = Concatenate(axis=3)([e_conv, up_img])
concat_mask = Concatenate(axis=3)([e_mask, up_mask])
conv, mask = PConv2D(filters, kernel_size,
padding='same')([concat_img, concat_mask])
# add batch normalization if desired
if bn:
conv = BatchNormalization()(conv)
conv = LeakyReLU(alpha=0.2)(conv)
return conv, mask
axes[2].imshow(masked_img)
#plt.show()
plt.savefig('masked_img_from_PConv_test.jpg')
# Input images and masks
input_img = Input(shape=(
shape[0],
shape[1],
shape[2],
))
input_mask = Input(shape=(
shape[0],
shape[1],
shape[2],
))
output_img, output_mask1 = PConv2D(8, kernel_size=(7, 7),
strides=(2, 2))([input_img, input_mask])
output_img, output_mask2 = PConv2D(16, kernel_size=(5, 5),
strides=(2, 2))([output_img, output_mask1])
output_img, output_mask3 = PConv2D(32, kernel_size=(5, 5),
strides=(2, 2))([output_img, output_mask2])
output_img, output_mask4 = PConv2D(64, kernel_size=(3, 3),
strides=(2, 2))([output_img, output_mask3])
output_img, output_mask5 = PConv2D(64, kernel_size=(3, 3),
strides=(2, 2))([output_img, output_mask4])
output_img, output_mask6 = PConv2D(64, kernel_size=(3, 3),
strides=(2, 2))([output_img, output_mask5])
output_img, output_mask7 = PConv2D(64, kernel_size=(3, 3),
strides=(2, 2))([output_img, output_mask6])
output_img, output_mask8 = PConv2D(64, kernel_size=(3, 3),
strides=(2, 2))([output_img, output_mask7])