def get_model(X, batch_size, image_dimension):
input_shape = (batch_size, 3, image_dimension, image_dimension)
all_parameters = []
#############################################
# a first convolution with 32 (3, 3) filters
output, output_test, params, output_shape = convolutional(
X, X, input_shape, 32, (3, 3))
all_parameters += params
# maxpool with size=(2, 2)
output, output_test, params, output_shape = maxpool(
output, output_test, output_shape, (2, 2))
# relu activation
output, output_test, params, output_shape = activation(
output, output_test, output_shape, 'relu')
#############################################
# a second convolution with 32 (5, 5) filters
output, output_test, params, output_shape = convolutional(
output, output_test, output_shape, 32, (5, 5))
all_parameters += params
# maxpool with size=(2, 2)
output, output_test, params, output_shape = maxpool(
output, output_test, output_shape, (2, 2))
# relu activation
output, output_test, params, output_shape = activation(
output, output_test, output_shape, 'relu')
#############################################
# MLP first layer
output = output.flatten(2)
output_test = output_test.flatten(2)
output, output_test, params, output_shape = linear(
output, output_test,
(output_shape[0], output_shape[1] * output_shape[2] * output_shape[3]),
500)
all_parameters += params
output, output_test, params, output_shape = activation(
output, output_test, output_shape, 'relu')
#############################################
# MLP second layer
output, output_test, params, output_shape = linear(output, output_test,
output_shape, 1)
all_parameters += params
output, output_test, params, output_shape = activation(
output, output_test, output_shape, 'sigmoid')
#
return output, output_test, all_parameters
def __init__(self, input_nc, output_nc, ngf=32):
super().__init__()
self.in_dim = input_nc
self.out_dim = ngf
self.final_out_dim = output_nc
act_fn = nn.LeakyReLU(0.2, inplace=True)
act_fn_2 = nn.ReLU()
# Encoder
self.down_1 = CoordConv_residual_conv(self.in_dim, self.out_dim,
act_fn)
self.pool_1 = maxpool()
self.down_2 = CoordConv_residual_conv(self.out_dim, self.out_dim * 2,
act_fn)
self.pool_2 = maxpool()
self.down_3 = CoordConv_residual_conv(self.out_dim * 2,
self.out_dim * 4, act_fn)
self.pool_3 = maxpool()
self.down_4 = CoordConv_residual_conv(self.out_dim * 4,
self.out_dim * 8, act_fn)
self.pool_4 = maxpool()
# Bridge between Encoder-Decoder
self.bridge = CoordConv_residual_conv(self.out_dim * 8,
self.out_dim * 16, act_fn)
# Decoder
self.deconv_1 = conv_decod_block(self.out_dim * 16, self.out_dim * 8,
act_fn_2)
self.up_1 = CoordConv_residual_conv(self.out_dim * 8, self.out_dim * 8,
act_fn_2)
self.deconv_2 = conv_decod_block(self.out_dim * 8, self.out_dim * 4,
act_fn_2)
self.up_2 = CoordConv_residual_conv(self.out_dim * 4, self.out_dim * 4,
act_fn_2)
self.deconv_3 = conv_decod_block(self.out_dim * 4, self.out_dim * 2,
act_fn_2)
self.up_3 = CoordConv_residual_conv(self.out_dim * 2, self.out_dim * 2,
act_fn_2)
self.deconv_4 = conv_decod_block(self.out_dim * 2, self.out_dim,
act_fn_2)
self.up_4 = CoordConv_residual_conv(self.out_dim, self.out_dim,
act_fn_2)
self.out = nn.Conv2d(self.out_dim,
self.final_out_dim,
kernel_size=3,
stride=1,
padding=1)
# Params initialization
for m in self.modules():
if isinstance(m, nn.Conv2d):
n = m.kernel_size[0] * m.kernel_size[1] * m.out_channels
m.weight.data.normal_(0, math.sqrt(2. / n))
elif isinstance(m, nn.BatchNorm2d):
m.weight.data.fill_(1)
m.bias.data.zero_()
print(f"Initialized {self.__class__.__name__} succesfully")
def get_model(X, batch_size, image_dimension): input_shape = (batch_size, 3, image_dimension, image_dimension) all_parameters = [] ############################################# # a first convolution with 32 (3, 3) filters output, output_test, params, output_shape = convolutional(X, X, input_shape, 32, (3, 3)) all_parameters += params # maxpool with size=(2, 2) output, output_test, params, output_shape = maxpool(output, output_test, output_shape, (2, 2)) # relu activation output, output_test, params, output_shape = activation(output, output_test, output_shape, 'relu') ############################################# # a second convolution with 32 (3, 3) filters output, output_test, params, output_shape = convolutional(output, output_test, output_shape, 32, (3, 3)) all_parameters += params # maxpool with size=(2, 2) output, output_test, params, output_shape = maxpool(output, output_test, output_shape, (2, 2)) # relu activation output, output_test, params, output_shape = activation(output, output_test, output_shape, 'relu') ############################################# # a third convolution with 32 (3, 3) filters output, output_test, params, output_shape = convolutional(output, output_test, output_shape, 32, (3, 3)) all_parameters += params # maxpool with size=(2, 2) output, output_test, params, output_shape = maxpool(output, output_test, output_shape, (2, 2)) # relu activation output, output_test, params, output_shape = activation(output, output_test, output_shape, 'relu') ############################################# # MLP first layer output = output.flatten(2) output_test = output_test.flatten(2) output, output_test, params, output_shape = linear(output, output_test, (output_shape[0], output_shape[1]*output_shape[2]*output_shape[3]), 500) all_parameters += params output, output_test, params, output_shape = activation(output, output_test, output_shape, 'relu') ############################################# # MLP second layer output, output_test, params, output_shape = linear(output, output_test, output_shape, 1) all_parameters += params output, output_test, params, output_shape = activation(output, output_test, output_shape, 'sigmoid') # return output, output_test, all_parameters
def __call__(self, x):
x = tf.cast(x, dtype=tf.float32)
self.conv1 = ll.conv2dx(x, self.model_weights[0], 1) # 1st Layer
self.conv1 = ll.conv2dx(self.conv1, self.model_weights[1], 1)
self.conv1 = ll.conv2dx(self.conv1, self.model_weights[2], 1)
self.pool1 = ll.maxpool(self.conv1, 2, 2)
self.conv2 = ll.conv2dx(self.pool1, self.model_weights[3],
1) # 2nd Layer
self.conv2 = ll.conv2dx(self.conv2, self.model_weights[4], 1)
self.conv2 = ll.conv2dx(self.conv2, self.model_weights[5], 1)
self.pool2 = ll.maxpool(self.conv2, 2, 2)
self.conv3 = ll.conv2dx(self.pool2, self.model_weights[6],
1) # 3rd Layer
self.conv3 = ll.conv2dx(self.conv3, self.model_weights[7], 1)
self.conv3 = ll.conv2dx(self.conv3, self.model_weights[8], 1)
self.pool3 = ll.maxpool(self.conv3, 2, 2)
self.conv4 = ll.conv2dx(self.pool3, self.model_weights[9],
1) # 4th Layer
self.conv4 = ll.conv2dx(self.conv4, self.model_weights[10], 1)
self.conv4 = ll.conv2dx(self.conv4, self.model_weights[11], 1)
self.pool4 = ll.maxpool(self.conv4, 2, 2)
self.conv5 = ll.conv2dx(self.pool4, self.model_weights[12],
1) # 5th Layer
self.conv5 = ll.conv2dx(self.conv5, self.model_weights[13], 1)
self.conv5 = ll.conv2dx(self.conv5, self.model_weights[14], 1)
self.pool5 = ll.maxpool(self.conv5, 2, 2)
self.conv6 = ll.conv2dx(self.pool5, self.model_weights[15],
1) # 6th Layer
self.conv6 = ll.conv2dx(self.conv6, self.model_weights[16], 1)
self.conv6 = ll.conv2dx(self.conv6, self.model_weights[17], 1)
self.pool6 = ll.maxpool(self.conv6, 2, 2)
self.flatten_layer = tf.reshape(self.pool6,
shape=(tf.shape(self.pool6)[0],
-1)) # flatten
self.dense1 = ll.dense(self.flatten_layer, self.model_weights[18],
self.dropout_rate)
self.dense2 = ll.dense(self.dense1, self.model_weights[19],
self.dropout_rate)
self.dense3 = ll.dense(self.dense2, self.model_weights[20],
self.dropout_rate)
self.dense4 = ll.dense(self.dense3, self.model_weights[21],
self.dropout_rate)
self.dense5 = ll.dense(self.dense4, self.model_weights[22],
self.dropout_rate)
self.dense6 = tf.matmul(self.dense5, self.model_weights[23])
return tf.nn.softmax(self.dense6)
def get_model(X, batch_size, image_dimension): input_shape = (batch_size, 3, image_dimension[0], image_dimension[1]) all_parameters = [] acc_parameters = [] ############################################# # a first convolution with 64 (3, 3) filters output, output_test, params, output_shape = convolutional(X, X, input_shape, 64, (3, 3)) all_parameters += params # maxpool with size=(2, 2) output, output_test, params, output_shape = maxpool(output, output_test, output_shape, (2, 2)) # relu activation output, output_test, params, output_shape = activation(output, output_test, output_shape, 'relu') ############################################# # a second convolution with 128 (3, 3) filters output, output_test, params, output_shape = convolutional(output, output_test, output_shape, 128, (3, 3)) all_parameters += params # maxpool with size=(2, 2) output, output_test, params, output_shape = maxpool(output, output_test, output_shape, (2, 2)) # relu activation output, output_test, params, output_shape = activation(output, output_test, output_shape, 'relu') ############################################# # 2 convolutional layers with 256 (3, 3) filters output, output_test, params, output_shape = convolutional(output, output_test, output_shape, 256, (3, 3)) all_parameters += params output, output_test, params, output_shape = activation(output, output_test, output_shape, 'relu') output, output_test, params, output_shape = convolutional(output, output_test, output_shape, 256, (3, 3)) all_parameters += params # maxpool with size=(2, 2) output, output_test, params, output_shape = maxpool(output, output_test, output_shape, (2, 2)) # relu activation output, output_test, params, output_shape = activation(output, output_test, output_shape, 'relu') ############################################# # Fully connected output, output_test, params, output_shape = convolutional(output, output_test, output_shape, 1024, (1, 1)) all_parameters += params output, output_test, params, output_shape = activation(output, output_test, output_shape, 'relu') output, output_test, params, output_shape = convolutional(output, output_test, output_shape, 1024, (1, 1)) all_parameters += params # maxpool with size=(4, 4) and fully connected output, output_test, params, output_shape = avgpool(output, output_test, output_shape, (4, 4)) output, output_test, params, output_shape = convolutional(output, output_test, output_shape, 10, (1, 1)) all_parameters += params output, output_test, params, output_shape, cacc_parameters = batch_norm(output, output_test, output_shape) acc_parameters += cacc_parameters all_parameters += params # softmax output = multi_dim_softmax(output) output_test = multi_dim_softmax(output_test) # return output, output_test, all_parameters, acc_parameters
def build(color_inputs, num_classes, is_training):
"""
Build unet network:
----------
Args:
color_inputs: Tensor, [batch_size, height, width, 3]
num_classes: Integer, number of segmentation (annotation) labels
is_training: Boolean, in training mode or not (for dropout & bn)
Returns:
logits: Tensor, predicted annotated image flattened
[batch_size * height * width, num_classes]
"""
dropout_keep_prob = tf.where(is_training, 0.2, 1.0)
# Encoder Section
# Block 1
color_conv1_1 = layers.conv_btn(color_inputs, [3, 3], 64, 'conv1_1', is_training = is_training)
color_conv1_2 = layers.conv_btn(color_conv1_1, [3, 3], 64, 'conv1_2', is_training = is_training)
color_pool1 = layers.maxpool(color_conv1_2, [2, 2], 'pool1')
# Block 2
color_conv2_1 = layers.conv_btn(color_pool1, [3, 3], 128, 'conv2_1', is_training = is_training)
color_conv2_2 = layers.conv_btn(color_conv2_1, [3, 3], 128, 'conv2_2', is_training = is_training)
color_pool2 = layers.maxpool(color_conv2_2, [2, 2], 'pool2')
# Block 3
color_conv3_1 = layers.conv_btn(color_pool2, [3, 3], 256, 'conv3_1', is_training = is_training)
color_conv3_2 = layers.conv_btn(color_conv3_1, [3, 3], 256, 'conv3_2', is_training = is_training)
color_pool3 = layers.maxpool(color_conv3_2, [2, 2], 'pool3')
color_drop3 = layers.dropout(color_pool3, dropout_keep_prob, 'drop3')
# Block 4
color_conv4_1 = layers.conv_btn(color_drop3, [3, 3], 512, 'conv4_1', is_training = is_training)
color_conv4_2 = layers.conv_btn(color_conv4_1, [3, 3], 512, 'conv4_2', is_training = is_training)
color_pool4 = layers.maxpool(color_conv4_2, [2, 2], 'pool4')
color_drop4 = layers.dropout(color_pool4, dropout_keep_prob, 'drop4')
# Block 5
color_conv5_1 = layers.conv_btn(color_drop4, [3, 3], 1024, 'conv5_1', is_training = is_training)
color_conv5_2 = layers.conv_btn(color_conv5_1, [3, 3], 1024, 'conv5_2', is_training = is_training)
color_drop5 = layers.dropout(color_conv5_2, dropout_keep_prob, 'drop5')
# Decoder Section
# Block 1
upsample6 = layers.deconv_upsample(color_drop5, 2, 'upsample6')
concat6 = layers.concat(upsample6, color_conv4_2, 'contcat6')
color_conv6_1 = layers.conv_btn(concat6, [3, 3], 512, 'conv6_1', is_training = is_training)
color_conv6_2 = layers.conv_btn(color_conv6_1, [3, 3], 512, 'conv6_1', is_training = is_training)
color_drop6 = layers.dropout(color_conv6_2, dropout_keep_prob, 'drop6')
# Block 2
upsample7 = layers.deconv_upsample(color_drop6, 2, 'upsample7')
concat7 = layers.concat(upsample7, color_conv3_2, 'concat7')
color_conv7_1 = layers.conv_btn(concat7, [3, 3], 256, 'conv7_1', is_training = is_training)
color_conv7_2 = layers.conv_btn(color_conv7_1, [3, 3], 256, 'conv7_1', is_training = is_training)
color_drop7 = layers.dropout(color_conv7_2, dropout_keep_prob, 'drop7')
# Block 3
upsample8 = layers.deconv_upsample(color_drop7, 2, 'upsample8')
concat8 = layers.concat(upsample8, color_conv2_2, 'concat8')
color_conv8_1 = layers.conv_btn(concat8, [3, 3], 128, 'conv8_1', is_training = is_training)
color_conv8_2 = layers.conv_btn(color_conv8_1, [3, 3], 128, 'conv8_1', is_training = is_training)
# Block 4
upsample9 = layers.deconv_upsample(color_conv9_2, 2, 'upsample9')
concat9 = layers.concat(upsample8, color_conv1_2, 'concat9')
color_conv9_1 = layers.conv_btn(concat9, [3, 3], 64, 'conv9_1', is_training = is_training)
color_conv9_2 = layers.conv_btn(color_conv9_1, [3, 3], 64, 'conv9_1', is_training = is_training)
# Block 5
score = layers.conv(color_conv9_2, [1, 1], num_classes, 'score', activation_fn = None)
logits = tf.reshape(score, (-1, num_classes))
return logits
def build_30s(color_inputs, num_classes, is_training):
"""
Build unet network:
----------
Args:
color_inputs: Tensor, [batch_size, length, 3]
num_classes: Integer, number of segmentation (annotation) labels
is_training: Boolean, in training mode or not (for dropout & bn)
Returns:
logits: Tensor, predicted annotated image flattened
[batch_size * length, num_classes]
"""
dropout_keep_prob = tf.where(is_training, 0.2, 1.0)
# Encoder Section
# Block 1
# color_conv1_1 = layers.conv_btn(color_inputs, [3, 3], 64, 'conv1_1', is_training = is_training)
color_conv1_1 = layers.conv_btn1(color_inputs,
3,
32,
'conv1_1',
is_training=is_training)
#layers.conv1(current_layer, c, ksize, stride=2, scope='conv{}'.format(i + 1), padding='SAME')
color_conv1_2 = layers.conv_btn1(color_conv1_1,
3,
32,
'conv1_2',
is_training=is_training)
color_pool1 = layers.maxpool(color_conv1_2, 4, 'pool1')
# Block 2
color_conv2_1 = layers.conv_btn1(color_pool1,
3,
32,
'conv2_1',
is_training=is_training)
color_conv2_2 = layers.conv_btn1(color_conv2_1,
3,
32,
'conv2_2',
is_training=is_training)
color_pool2 = layers.maxpool(color_conv2_2, 4, 'pool2')
# Block 3
color_conv3_1 = layers.conv_btn1(color_pool2,
3,
64,
'conv3_1',
is_training=is_training)
color_conv3_2 = layers.conv_btn1(color_conv3_1,
3,
64,
'conv3_2',
is_training=is_training)
color_pool3 = layers.maxpool(color_conv3_2, 4, 'pool3')
color_drop3 = layers.dropout(color_pool3, dropout_keep_prob, 'drop3')
# Block 4
color_conv4_1 = layers.conv_btn1(color_drop3,
3,
64,
'conv4_1',
is_training=is_training)
color_conv4_2 = layers.conv_btn1(color_conv4_1,
3,
64,
'conv4_2',
is_training=is_training)
color_pool4 = layers.maxpool(color_conv4_2, 4, 'pool4')
color_drop4 = layers.dropout(color_pool4, dropout_keep_prob, 'drop4')
# Block 5
color_conv5_1 = layers.conv_btn1(color_drop4,
3,
128,
'conv5_1',
is_training=is_training)
color_conv5_2 = layers.conv_btn1(color_conv5_1,
3,
128,
'conv5_2',
is_training=is_training)
color_drop5 = layers.dropout(color_conv5_2, dropout_keep_prob, 'drop5')
# Decoder Section
# Block 1
upsample61 = layers.deconv_upsample(color_drop5, 4, 'upsample6')
upsample61 = Cropping1D(cropping=((0, 1)))(upsample61)
concat6 = layers.concat(upsample61, color_conv4_2, 'concat6')
color_conv6_1 = layers.conv_btn1(concat6,
3,
128,
'conv6_1',
is_training=is_training)
# color_conv6_2 = layers.conv_btn1(color_conv6_1, 6, 128, 'conv6_2', is_training = is_training)
color_drop6 = layers.dropout(color_conv6_1, dropout_keep_prob, 'drop6')
# Block 2
upsample7 = layers.deconv_upsample(color_drop6, 4, 'upsample7')
# upsample7 = Cropping1D(cropping=((0, 1)))(upsample7)
concat7 = layers.concat(upsample7, color_conv3_2, 'concat7')
color_conv7_1 = layers.conv_btn1(concat7,
3,
64,
'conv7_1',
is_training=is_training)
# color_conv7_2 = layers.conv_btn1(color_conv7_1, 6, 64, 'conv7_1', is_training = is_training)
color_drop7 = layers.dropout(color_conv7_1, dropout_keep_prob, 'drop7')
# Block 3
upsample81 = layers.deconv_upsample(color_drop7, 4, 'upsample8')
upsample81 = Cropping1D(cropping=((0, 1)))(upsample81)
concat8 = layers.concat(upsample81, color_conv2_2, 'concat8')
color_conv8_1 = layers.conv_btn1(concat8,
3,
32,
'conv8_1',
is_training=is_training)
# color_conv8_2 = layers.conv_btn1(color_conv8_1, 3, 32, 'conv8_1', is_training = is_training)
# Block 4
upsample91 = layers.deconv_upsample(color_conv8_1, 4, 'upsample9')
upsample91 = Cropping1D(cropping=((1, 2)))(upsample91)
concat9 = layers.concat(upsample91, color_conv1_2, 'concat9')
color_conv9_1 = layers.conv_btn1(concat9,
3,
32,
'conv9_1',
is_training=is_training)
# color_conv9_2 = layers.conv_btn1(color_conv9_1, 3, 32, 'conv9_1', is_training = is_training)
# Block 5
score = layers.conv(color_conv9_1,
1,
num_classes,
'score',
activation_fn=None)
logits = tf.reshape(score, (-1, num_classes))
return logits
def get_model(X, batch_size, image_dimension):
input_shape = (batch_size, 3, image_dimension[0], image_dimension[1])
all_parameters = []
acc_parameters = []
#############################################
# a first convolution with 64 (3, 3) filters
output, output_test, params, output_shape = convolutional(
X, X, input_shape, 64, (3, 3))
all_parameters += params
# maxpool with size=(2, 2)
output, output_test, params, output_shape = maxpool(
output, output_test, output_shape, (2, 2))
# relu activation
output, output_test, params, output_shape = activation(
output, output_test, output_shape, 'relu')
#############################################
# a second convolution with 128 (3, 3) filters
output, output_test, params, output_shape = convolutional(
output, output_test, output_shape, 128, (3, 3))
all_parameters += params
# maxpool with size=(2, 2)
output, output_test, params, output_shape = maxpool(
output, output_test, output_shape, (2, 2))
# relu activation
output, output_test, params, output_shape = activation(
output, output_test, output_shape, 'relu')
#############################################
# 2 convolutional layers with 256 (3, 3) filters
output, output_test, params, output_shape = convolutional(
output, output_test, output_shape, 256, (3, 3))
all_parameters += params
output, output_test, params, output_shape = activation(
output, output_test, output_shape, 'relu')
output, output_test, params, output_shape = convolutional(
output, output_test, output_shape, 256, (3, 3))
all_parameters += params
# maxpool with size=(2, 2)
output, output_test, params, output_shape = maxpool(
output, output_test, output_shape, (2, 2))
# relu activation
output, output_test, params, output_shape = activation(
output, output_test, output_shape, 'relu')
#############################################
# Fully connected
output, output_test, params, output_shape = convolutional(
output, output_test, output_shape, 1024, (1, 1))
all_parameters += params
output, output_test, params, output_shape = activation(
output, output_test, output_shape, 'relu')
output, output_test, params, output_shape = convolutional(
output, output_test, output_shape, 1024, (1, 1))
all_parameters += params
# maxpool with size=(4, 4) and fully connected
output, output_test, params, output_shape = avgpool(
output, output_test, output_shape, (4, 4))
output, output_test, params, output_shape = convolutional(
output, output_test, output_shape, 10, (1, 1))
all_parameters += params
output, output_test, params, output_shape, cacc_parameters = batch_norm(
output, output_test, output_shape)
acc_parameters += cacc_parameters
all_parameters += params
# softmax
output = multi_dim_softmax(output)
output_test = multi_dim_softmax(output_test)
#
return output, output_test, all_parameters, acc_parameters