172 lines
4.7 KiB
Python
172 lines
4.7 KiB
Python
import tensorflow as tf
|
|
from convnext.models.convnext_tf import ConvNeXt, ConvNeXtReverse, Block
|
|
|
|
|
|
|
|
class Bottleneck(tf.keras.Model):
|
|
|
|
def __init__(self, dim, latent_dim):
|
|
super(Bottleneck, self).__init__()
|
|
|
|
self.bottleneck = tf.keras.Sequential(
|
|
[Block(dim=dim, drop_path=0,
|
|
layer_scale_init_value=1e-6, prefix=f'bottleneck{j}') for j in range(5)]
|
|
)
|
|
self.flatten = tf.keras.layers.Flatten()
|
|
self.dense = tf.keras.layers.Dense(latent_dim)
|
|
|
|
def call(self, inputs, training=None):
|
|
x = inputs
|
|
|
|
x = self.bottleneck(x)
|
|
x = self.flatten(x)
|
|
x = self.dense(x)
|
|
|
|
return x
|
|
|
|
|
|
class Decoder(tf.keras.Model):
|
|
|
|
def __init__(self, bottleneck_size, latent_dim):
|
|
super(Decoder, self).__init__()
|
|
|
|
self.dense = tf.keras.layers.Dense(8 * 4 * bottleneck_size)
|
|
self.reshape = tf.keras.layers.Reshape((8, 4, bottleneck_size))
|
|
self.decoder = ConvNeXtReverse(depths=list(reversed([3, 3, 9, 3, 3])), dims=list(reversed([bottleneck_size, 128, 128, 64, 16])))
|
|
|
|
def call(self, inputs, training=None):
|
|
x = inputs
|
|
|
|
x = self.dense(x)
|
|
x = self.reshape(x)
|
|
x = self.decoder(x)
|
|
|
|
return x
|
|
|
|
|
|
class AutoEncoder(tf.keras.Model):
|
|
|
|
def __init__(self):
|
|
super(AutoEncoder, self).__init__()
|
|
|
|
|
|
bottleneck_size = 32
|
|
latent_dim = 128
|
|
|
|
self.encoder = ConvNeXt(depths=[3, 3, 9, 3, 3], dims=[32, 64, 128, 128, bottleneck_size], include_top=False)
|
|
self.bottleneck = Bottleneck(bottleneck_size, latent_dim)
|
|
self.decoder = Decoder(bottleneck_size, latent_dim)
|
|
|
|
def call(self, inputs, training=None):
|
|
x = inputs
|
|
|
|
x = tf.transpose(x, [0,2,3,1])
|
|
x = self.encoder(x, training=training)
|
|
|
|
x = self.bottleneck(x, training=training)
|
|
|
|
x = self.decoder(x, training=training)
|
|
x = tf.transpose(x, [0,3,1,2])
|
|
|
|
# x = x * uv_mask[:,:, tf.newaxis]
|
|
# x = x * uv_mask[:,tf.newaxis,:,:]
|
|
|
|
return x
|
|
|
|
|
|
class Decoder32(tf.keras.Model):
|
|
|
|
def __init__(self, bottleneck_size, latent_dim):
|
|
super(Decoder32, self).__init__()
|
|
|
|
self.dense = tf.keras.layers.Dense(4 * 2 * bottleneck_size)
|
|
self.reshape = tf.keras.layers.Reshape((4, 2, bottleneck_size))
|
|
self.decoder = ConvNeXtReverse(depths=list(reversed([27, 27])), dims=list(reversed([bottleneck_size, 256])))
|
|
|
|
def call(self, inputs, training=None):
|
|
x = inputs
|
|
|
|
x = self.dense(x)
|
|
x = self.reshape(x)
|
|
x = self.decoder(x)
|
|
|
|
return x
|
|
|
|
|
|
class AutoEncoder32(tf.keras.Model):
|
|
|
|
def __init__(self):
|
|
super(AutoEncoder32, self).__init__()
|
|
|
|
|
|
bottleneck_size = 512
|
|
latent_dim = 128
|
|
|
|
self.encoder = ConvNeXt(depths=[27, 27], dims=[256, bottleneck_size], include_top=False)
|
|
self.bottleneck = Bottleneck(bottleneck_size, latent_dim)
|
|
self.decoder = Decoder32(bottleneck_size, latent_dim)
|
|
|
|
def call(self, inputs, training=None):
|
|
x = inputs
|
|
|
|
x = tf.transpose(x, [0,2,3,1])
|
|
x = self.encoder(x, training=training)
|
|
|
|
x = self.bottleneck(x, training=training)
|
|
|
|
x = self.decoder(x, training=training)
|
|
x = tf.transpose(x, [0,3,1,2])
|
|
|
|
# x = x * uv_mask[:,:, tf.newaxis]
|
|
# x = x * uv_mask[:,tf.newaxis,:,:]
|
|
|
|
return x
|
|
|
|
|
|
class Decoder128(tf.keras.Model):
|
|
|
|
def __init__(self, bottleneck_size, latent_dim):
|
|
super(Decoder128, self).__init__()
|
|
|
|
self.dense = tf.keras.layers.Dense(4 * 2 * bottleneck_size)
|
|
self.reshape = tf.keras.layers.Reshape((4, 2, bottleneck_size))
|
|
self.decoder = ConvNeXtReverse(depths=list(reversed([16, 16, 9, 9])), dims=list(reversed([bottleneck_size, 256, 128, 64])))
|
|
|
|
def call(self, inputs, training=None):
|
|
x = inputs
|
|
|
|
x = self.dense(x)
|
|
x = self.reshape(x)
|
|
x = self.decoder(x)
|
|
|
|
return x
|
|
|
|
|
|
class AutoEncoder128(tf.keras.Model):
|
|
|
|
def __init__(self):
|
|
super(AutoEncoder128, self).__init__()
|
|
|
|
|
|
bottleneck_size = 512
|
|
latent_dim = 128
|
|
|
|
self.encoder = ConvNeXt(depths=[16, 16, 9, 9], dims=[64, 128, 256, bottleneck_size], include_top=False)
|
|
self.bottleneck = Bottleneck(bottleneck_size, latent_dim)
|
|
self.decoder = Decoder128(bottleneck_size, latent_dim)
|
|
|
|
def call(self, inputs, training=None):
|
|
x = inputs
|
|
|
|
x = tf.transpose(x, [0,2,3,1])
|
|
x = self.encoder(x, training=training)
|
|
|
|
x = self.bottleneck(x, training=training)
|
|
|
|
x = self.decoder(x, training=training)
|
|
x = tf.transpose(x, [0,3,1,2])
|
|
|
|
# x = x * uv_mask[:,:, tf.newaxis]
|
|
# x = x * uv_mask[:,tf.newaxis,:,:]
|
|
|
|
return x |